Create thread and run
Create a thread and run it in one request.
ParametersExpand Collapse
The ID of the assistant to use to execute this run.
Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis.
The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status incomplete. See incomplete_details for more info.
The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status incomplete. See incomplete_details for more info.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
Literal["gpt-5.2", "gpt-5.2-2025-12-11", "gpt-5.2-chat-latest", 69 more]
Whether to enable parallel function calling during tool use.
response_format: Optional[AssistantResponseFormatOptionParam]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
If true, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a data: [DONE] message.
What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
Options to create a new thread. If no thread is provided when running a
request, an empty thread will be created.
Options to create a new thread. If no thread is provided when running a request, an empty thread will be created.
messages: Optional[Iterable[ThreadMessage]]A list of messages to start the thread with.
A list of messages to start the thread with.
The text contents of the message.
The text contents of the message.
The text contents of the message.
Iterable[MessageContentPartParam]An array of content parts with a defined type, each can be of type text or images can be passed with image_url or image_file. Image types are only supported on Vision-compatible models.
An array of content parts with a defined type, each can be of type text or images can be passed with image_url or image_file. Image types are only supported on Vision-compatible models.
class ImageFileContentBlock: …References an image File in the content of a message.
References an image File in the content of a message.
The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Always image_file.
class ImageURLContentBlock: …References an image URL in the content of a message.
References an image URL in the content of a message.
The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
The type of the content part.
class TextContentBlockParam: …The text content that is part of a message.
The text content that is part of a message.
Text content to be sent to the model
Always text.
role: Literal["user", "assistant"]The role of the entity that is creating the message. Allowed values include:
user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.
The role of the entity that is creating the message. Allowed values include:
user: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages.assistant: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation.
attachments: Optional[Iterable[ThreadMessageAttachment]]A list of files attached to the message, and the tools they should be added to.
A list of files attached to the message, and the tools they should be added to.
The ID of the file to attach to the message.
tools: Optional[Iterable[ThreadMessageAttachmentTool]]The tools to add this file to.
The tools to add this file to.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class ThreadMessageAttachmentToolFileSearch: …
The type of tool being defined: file_search
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
tool_resources: Optional[ThreadToolResources]A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.
A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.
code_interpreter: Optional[ThreadToolResourcesCodeInterpreter]
A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.
file_search: Optional[ThreadToolResourcesFileSearch]
The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.
vector_stores: Optional[Iterable[ThreadToolResourcesFileSearchVectorStore]]A helper to create a vector store with file_ids and attach it to this thread. There can be a maximum of 1 vector store attached to the thread.
A helper to create a vector store with file_ids and attach it to this thread. There can be a maximum of 1 vector store attached to the thread.
chunking_strategy: Optional[ThreadToolResourcesFileSearchVectorStoreChunkingStrategy]The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.
The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.
class ThreadToolResourcesFileSearchVectorStoreChunkingStrategyAuto: …The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.
The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.
Always auto.
class ThreadToolResourcesFileSearchVectorStoreChunkingStrategyStatic: …
static: ThreadToolResourcesFileSearchVectorStoreChunkingStrategyStaticStatic
The number of tokens that overlap between chunks. The default value is 400.
Note that the overlap must not exceed half of max_chunk_size_tokens.
The maximum number of tokens in each chunk. The default value is 800. The minimum value is 100 and the maximum value is 4096.
Always static.
A list of file IDs to add to the vector store. There can be a maximum of 10000 files in a vector store.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
tool_choice: Optional[AssistantToolChoiceOptionParam]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.
A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.
code_interpreter: Optional[ToolResourcesCodeInterpreter]
A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.
file_search: Optional[ToolResourcesFileSearch]
The ID of the vector store attached to this assistant. There can be a maximum of 1 vector store attached to the assistant.
Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.
We generally recommend altering this or temperature but not both.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
ReturnsExpand Collapse
class Run: …Represents an execution run on a thread.
Represents an execution run on a thread.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
Represents an event emitted when streaming a Run.
Each event in a server-sent events stream has an event and data property:
event: thread.created
data: {"id": "thread_123", "object": "thread", ...}
We emit events whenever a new object is created, transitions to a new state, or is being
streamed in parts (deltas). For example, we emit thread.run.created when a new run
is created, thread.run.completed when a run completes, and so on. When an Assistant chooses
to create a message during a run, we emit a thread.message.created event, a
thread.message.in_progress event, many thread.message.delta events, and finally a
thread.message.completed event.
We may add additional events over time, so we recommend handling unknown events gracefully
in your code. See the Assistants API quickstart to learn how to
integrate the Assistants API with streaming.
Represents an event emitted when streaming a Run.
Each event in a server-sent events stream has an event and data property:
event: thread.created
data: {"id": "thread_123", "object": "thread", ...}We emit events whenever a new object is created, transitions to a new state, or is being
streamed in parts (deltas). For example, we emit thread.run.created when a new run
is created, thread.run.completed when a run completes, and so on. When an Assistant chooses
to create a message during a run, we emit a thread.message.created event, a
thread.message.in_progress event, many thread.message.delta events, and finally a
thread.message.completed event.
We may add additional events over time, so we recommend handling unknown events gracefully in your code. See the Assistants API quickstart to learn how to integrate the Assistants API with streaming.
class ThreadCreated: …Occurs when a new thread is created.
Occurs when a new thread is created.
The identifier, which can be referenced in API endpoints.
The Unix timestamp (in seconds) for when the thread was created.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.
tool_resources: Optional[ToolResources]A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.
A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.
code_interpreter: Optional[ToolResourcesCodeInterpreter]
A list of file IDs made available to the code_interpreter tool. There can be a maximum of 20 files associated with the tool.
file_search: Optional[ToolResourcesFileSearch]
The vector store attached to this thread. There can be a maximum of 1 vector store attached to the thread.
Whether to enable input audio transcription.
class ThreadRunCreated: …Occurs when a new run is created.
Occurs when a new run is created.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
class ThreadRunQueued: …Occurs when a run moves to a queued status.
Occurs when a run moves to a queued status.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
class ThreadRunInProgress: …Occurs when a run moves to an in_progress status.
Occurs when a run moves to an in_progress status.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
class ThreadRunRequiresAction: …Occurs when a run moves to a requires_action status.
Occurs when a run moves to a requires_action status.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
class ThreadRunCompleted: …Occurs when a run is completed.
Occurs when a run is completed.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
class ThreadRunIncomplete: …Occurs when a run ends with status incomplete.
Occurs when a run ends with status incomplete.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
class ThreadRunFailed: …Occurs when a run fails.
Occurs when a run fails.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
class ThreadRunCancelling: …Occurs when a run moves to a cancelling status.
Occurs when a run moves to a cancelling status.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
class ThreadRunCancelled: …Occurs when a run is cancelled.
Occurs when a run is cancelled.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
class ThreadRunExpired: …Occurs when a run expires.
Occurs when a run expires.
The identifier, which can be referenced in API endpoints.
The ID of the assistant used for execution of this run.
The Unix timestamp (in seconds) for when the run was cancelled.
The Unix timestamp (in seconds) for when the run was completed.
The Unix timestamp (in seconds) for when the run was created.
The Unix timestamp (in seconds) for when the run will expire.
The Unix timestamp (in seconds) for when the run failed.
incomplete_details: Optional[IncompleteDetails]Details on why the run is incomplete. Will be null if the run is not incomplete.
Details on why the run is incomplete. Will be null if the run is not incomplete.
reason: Optional[Literal["max_completion_tokens", "max_prompt_tokens"]]The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run.
The instructions that the assistant used for this run.
last_error: Optional[LastError]The last error associated with this run. Will be null if there are no errors.
The last error associated with this run. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded", "invalid_prompt"]One of server_error, rate_limit_exceeded, or invalid_prompt.
One of server_error, rate_limit_exceeded, or invalid_prompt.
A human-readable description of the error.
The maximum number of completion tokens specified to have been used over the course of the run.
The maximum number of prompt tokens specified to have been used over the course of the run.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The model that the assistant used for this run.
The object type, which is always thread.run.
Whether to enable parallel function calling during tool use.
required_action: Optional[RequiredAction]Details on the action required to continue the run. Will be null if no action is required.
Details on the action required to continue the run. Will be null if no action is required.
submit_tool_outputs: RequiredActionSubmitToolOutputsDetails on the tool outputs needed for this run to continue.
Details on the tool outputs needed for this run to continue.
A list of the relevant tool calls.
A list of the relevant tool calls.
The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the Submit tool outputs to run endpoint.
function: FunctionThe function definition.
The function definition.
The arguments that the model expects you to pass to the function.
The name of the function.
The type of tool call the output is required for. For now, this is always function.
For now, this is always submit_tool_outputs.
response_format: Optional[AssistantResponseFormatOption]Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.
Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.
Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.
auto is the default value
class ResponseFormatText: …Default response format. Used to generate text responses.
Default response format. Used to generate text responses.
The type of response format being defined. Always text.
class ResponseFormatJSONObject: …JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
JSON object response format. An older method of generating JSON responses.
Using json_schema is recommended for models that support it. Note that the
model will not generate JSON without a system or user message instructing it
to do so.
The type of response format being defined. Always json_object.
class ResponseFormatJSONSchema: …JSON Schema response format. Used to generate structured JSON responses.
Learn more about Structured Outputs.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
json_schema: JSONSchemaStructured Outputs configuration options, including a JSON Schema.
Structured Outputs configuration options, including a JSON Schema.
The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the response format is for, used by the model to determine how to respond in the format.
The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.
Whether to enable strict schema adherence when generating the output.
If set to true, the model will always follow the exact schema defined
in the schema field. Only a subset of JSON Schema is supported when
strict is true. To learn more, read the Structured Outputs
guide.
The type of response format being defined. Always json_schema.
The Unix timestamp (in seconds) for when the run was started.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.
The ID of the thread that was executed on as a part of this run.
tool_choice: Optional[AssistantToolChoiceOption]Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Controls which (if any) tool is called by the model.
none means the model will not call any tools and instead generates a message.
auto is the default value and means the model can pick between generating a message or calling one or more tools.
required means the model must call one or more tools before responding to the user.
Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.
Literal["none", "auto", "required"]none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.
class AssistantToolChoice: …Specifies a tool the model should use. Use to force the model to call a specific tool.
Specifies a tool the model should use. Use to force the model to call a specific tool.
type: Literal["function", "code_interpreter", "file_search"]The type of the tool. If type is function, the function name must be set
The type of the tool. If type is function, the function name must be set
function: Optional[AssistantToolChoiceFunction]
The name of the function to call.
The list of tools that the assistant used for this run.
The list of tools that the assistant used for this run.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class FileSearchTool: …
The type of tool being defined: file_search
file_search: Optional[FileSearch]Overrides for the file search tool.
Overrides for the file search tool.
The maximum number of results the file search tool should output. The default is 20 for gpt-4* models and 5 for gpt-3.5-turbo. This number should be between 1 and 50 inclusive.
Note that the file search tool may output fewer than max_num_results results. See the file search tool documentation for more information.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The ranking options for the file search. If not specified, the file search tool will use the auto ranker and a score_threshold of 0.
See the file search tool documentation for more information.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
ranker: Optional[Literal["auto", "default_2024_08_21"]]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
class FunctionTool: …
The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.
A description of what the function does, used by the model to choose when and how to call the function.
The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.
Omitting parameters defines a function with an empty parameter list.
Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. Learn more about Structured Outputs in the function calling guide.
The type of tool being defined: function
truncation_strategy: Optional[TruncationStrategy]Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
Controls for how a thread will be truncated prior to the run. Use this to control the initial context window of the run.
type: Literal["auto", "last_messages"]The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The truncation strategy to use for the thread. The default is auto. If set to last_messages, the thread will be truncated to the n most recent messages in the thread. When set to auto, messages in the middle of the thread will be dropped to fit the context length of the model, max_prompt_tokens.
The number of most recent messages from the thread when constructing the context for the run.
usage: Optional[Usage]Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Usage statistics related to the run. This value will be null if the run is not in a terminal state (i.e. in_progress, queued, etc.).
Number of completion tokens used over the course of the run.
Number of prompt tokens used over the course of the run.
Total number of tokens used (prompt + completion).
The sampling temperature used for this run. If not set, defaults to 1.
The nucleus sampling value used for this run. If not set, defaults to 1.
class ThreadRunStepCreated: …Occurs when a run step is created.
Occurs when a run step is created.
Represents a step in execution of a run.
Represents a step in execution of a run.
The identifier of the run step, which can be referenced in API endpoints.
The ID of the assistant associated with the run step.
The Unix timestamp (in seconds) for when the run step was cancelled.
The Unix timestamp (in seconds) for when the run step completed.
The Unix timestamp (in seconds) for when the run step was created.
The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.
The Unix timestamp (in seconds) for when the run step failed.
last_error: Optional[LastError]The last error associated with this run step. Will be null if there are no errors.
The last error associated with this run step. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded"]One of server_error or rate_limit_exceeded.
One of server_error or rate_limit_exceeded.
A human-readable description of the error.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.run.step.
The ID of the run that this run step is a part of.
status: Literal["in_progress", "cancelled", "failed", 2 more]The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
step_details: StepDetailsThe details of the run step.
The details of the run step.
class MessageCreationStepDetails: …Details of the message creation by the run step.
Details of the message creation by the run step.
message_creation: MessageCreation
The ID of the message that was created by this run step.
Always message_creation.
class ToolCallsStepDetails: …Details of the tool call.
Details of the tool call.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
class CodeInterpreterToolCall: …Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The ID of the tool call.
code_interpreter: CodeInterpreterThe Code Interpreter tool call definition.
The Code Interpreter tool call definition.
The input to the Code Interpreter tool call.
outputs: List[CodeInterpreterOutput]The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
class CodeInterpreterOutputLogs: …Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The text output from the Code Interpreter tool call.
Always logs.
class CodeInterpreterOutputImage: …
image: CodeInterpreterOutputImageImage
The file ID of the image.
Always image.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
class FileSearchToolCall: …
The ID of the tool call object.
file_search: FileSearchFor now, this is always going to be an empty object.
For now, this is always going to be an empty object.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search.
The ranking options for the file search.
ranker: Literal["auto", "default_2024_08_21"]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
results: Optional[List[FileSearchResult]]The results of the file search.
The results of the file search.
The ID of the file that result was found in.
The name of the file that result was found in.
The score of the result. All values must be a floating point number between 0 and 1.
content: Optional[List[FileSearchResultContent]]The content of the result that was found. The content is only included if requested via the include query parameter.
The content of the result that was found. The content is only included if requested via the include query parameter.
The text content of the file.
The type of the content.
The type of tool call. This is always going to be file_search for this type of tool call.
class FunctionToolCall: …
The ID of the tool call object.
function: FunctionThe definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The type of tool call. This is always going to be function for this type of tool call.
Always tool_calls.
The ID of the thread that was run.
type: Literal["message_creation", "tool_calls"]The type of run step, which can be either message_creation or tool_calls.
The type of run step, which can be either message_creation or tool_calls.
usage: Optional[Usage]Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Number of completion tokens used over the course of the run step.
Number of prompt tokens used over the course of the run step.
Total number of tokens used (prompt + completion).
class ThreadRunStepInProgress: …Occurs when a run step moves to an in_progress state.
Occurs when a run step moves to an in_progress state.
Represents a step in execution of a run.
Represents a step in execution of a run.
The identifier of the run step, which can be referenced in API endpoints.
The ID of the assistant associated with the run step.
The Unix timestamp (in seconds) for when the run step was cancelled.
The Unix timestamp (in seconds) for when the run step completed.
The Unix timestamp (in seconds) for when the run step was created.
The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.
The Unix timestamp (in seconds) for when the run step failed.
last_error: Optional[LastError]The last error associated with this run step. Will be null if there are no errors.
The last error associated with this run step. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded"]One of server_error or rate_limit_exceeded.
One of server_error or rate_limit_exceeded.
A human-readable description of the error.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.run.step.
The ID of the run that this run step is a part of.
status: Literal["in_progress", "cancelled", "failed", 2 more]The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
step_details: StepDetailsThe details of the run step.
The details of the run step.
class MessageCreationStepDetails: …Details of the message creation by the run step.
Details of the message creation by the run step.
message_creation: MessageCreation
The ID of the message that was created by this run step.
Always message_creation.
class ToolCallsStepDetails: …Details of the tool call.
Details of the tool call.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
class CodeInterpreterToolCall: …Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The ID of the tool call.
code_interpreter: CodeInterpreterThe Code Interpreter tool call definition.
The Code Interpreter tool call definition.
The input to the Code Interpreter tool call.
outputs: List[CodeInterpreterOutput]The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
class CodeInterpreterOutputLogs: …Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The text output from the Code Interpreter tool call.
Always logs.
class CodeInterpreterOutputImage: …
image: CodeInterpreterOutputImageImage
The file ID of the image.
Always image.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
class FileSearchToolCall: …
The ID of the tool call object.
file_search: FileSearchFor now, this is always going to be an empty object.
For now, this is always going to be an empty object.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search.
The ranking options for the file search.
ranker: Literal["auto", "default_2024_08_21"]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
results: Optional[List[FileSearchResult]]The results of the file search.
The results of the file search.
The ID of the file that result was found in.
The name of the file that result was found in.
The score of the result. All values must be a floating point number between 0 and 1.
content: Optional[List[FileSearchResultContent]]The content of the result that was found. The content is only included if requested via the include query parameter.
The content of the result that was found. The content is only included if requested via the include query parameter.
The text content of the file.
The type of the content.
The type of tool call. This is always going to be file_search for this type of tool call.
class FunctionToolCall: …
The ID of the tool call object.
function: FunctionThe definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The type of tool call. This is always going to be function for this type of tool call.
Always tool_calls.
The ID of the thread that was run.
type: Literal["message_creation", "tool_calls"]The type of run step, which can be either message_creation or tool_calls.
The type of run step, which can be either message_creation or tool_calls.
usage: Optional[Usage]Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Number of completion tokens used over the course of the run step.
Number of prompt tokens used over the course of the run step.
Total number of tokens used (prompt + completion).
class ThreadRunStepDelta: …Occurs when parts of a run step are being streamed.
Occurs when parts of a run step are being streamed.
Represents a run step delta i.e. any changed fields on a run step during streaming.
Represents a run step delta i.e. any changed fields on a run step during streaming.
The identifier of the run step, which can be referenced in API endpoints.
The delta containing the fields that have changed on the run step.
The delta containing the fields that have changed on the run step.
step_details: Optional[StepDetails]The details of the run step.
The details of the run step.
class RunStepDeltaMessageDelta: …Details of the message creation by the run step.
Details of the message creation by the run step.
Always message_creation.
message_creation: Optional[MessageCreation]
The ID of the message that was created by this run step.
class ToolCallDeltaObject: …Details of the tool call.
Details of the tool call.
Always tool_calls.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
class CodeInterpreterToolCallDelta: …Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
The ID of the tool call.
code_interpreter: Optional[CodeInterpreter]The Code Interpreter tool call definition.
The Code Interpreter tool call definition.
The input to the Code Interpreter tool call.
outputs: Optional[List[CodeInterpreterOutput]]The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
class CodeInterpreterLogs: …Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The index of the output in the outputs array.
Always logs.
The text output from the Code Interpreter tool call.
class CodeInterpreterOutputImage: …
The index of the output in the outputs array.
Always image.
image: Optional[Image]
The file ID of the image.
class FileSearchToolCallDelta: …
For now, this is always going to be an empty object.
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be file_search for this type of tool call.
The ID of the tool call object.
class FunctionToolCallDelta: …
The index of the tool call in the tool calls array.
The type of tool call. This is always going to be function for this type of tool call.
The ID of the tool call object.
function: Optional[Function]The definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The object type, which is always thread.run.step.delta.
class ThreadRunStepCompleted: …Occurs when a run step is completed.
Occurs when a run step is completed.
Represents a step in execution of a run.
Represents a step in execution of a run.
The identifier of the run step, which can be referenced in API endpoints.
The ID of the assistant associated with the run step.
The Unix timestamp (in seconds) for when the run step was cancelled.
The Unix timestamp (in seconds) for when the run step completed.
The Unix timestamp (in seconds) for when the run step was created.
The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.
The Unix timestamp (in seconds) for when the run step failed.
last_error: Optional[LastError]The last error associated with this run step. Will be null if there are no errors.
The last error associated with this run step. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded"]One of server_error or rate_limit_exceeded.
One of server_error or rate_limit_exceeded.
A human-readable description of the error.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.run.step.
The ID of the run that this run step is a part of.
status: Literal["in_progress", "cancelled", "failed", 2 more]The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
step_details: StepDetailsThe details of the run step.
The details of the run step.
class MessageCreationStepDetails: …Details of the message creation by the run step.
Details of the message creation by the run step.
message_creation: MessageCreation
The ID of the message that was created by this run step.
Always message_creation.
class ToolCallsStepDetails: …Details of the tool call.
Details of the tool call.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
class CodeInterpreterToolCall: …Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The ID of the tool call.
code_interpreter: CodeInterpreterThe Code Interpreter tool call definition.
The Code Interpreter tool call definition.
The input to the Code Interpreter tool call.
outputs: List[CodeInterpreterOutput]The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
class CodeInterpreterOutputLogs: …Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The text output from the Code Interpreter tool call.
Always logs.
class CodeInterpreterOutputImage: …
image: CodeInterpreterOutputImageImage
The file ID of the image.
Always image.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
class FileSearchToolCall: …
The ID of the tool call object.
file_search: FileSearchFor now, this is always going to be an empty object.
For now, this is always going to be an empty object.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search.
The ranking options for the file search.
ranker: Literal["auto", "default_2024_08_21"]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
results: Optional[List[FileSearchResult]]The results of the file search.
The results of the file search.
The ID of the file that result was found in.
The name of the file that result was found in.
The score of the result. All values must be a floating point number between 0 and 1.
content: Optional[List[FileSearchResultContent]]The content of the result that was found. The content is only included if requested via the include query parameter.
The content of the result that was found. The content is only included if requested via the include query parameter.
The text content of the file.
The type of the content.
The type of tool call. This is always going to be file_search for this type of tool call.
class FunctionToolCall: …
The ID of the tool call object.
function: FunctionThe definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The type of tool call. This is always going to be function for this type of tool call.
Always tool_calls.
The ID of the thread that was run.
type: Literal["message_creation", "tool_calls"]The type of run step, which can be either message_creation or tool_calls.
The type of run step, which can be either message_creation or tool_calls.
usage: Optional[Usage]Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Number of completion tokens used over the course of the run step.
Number of prompt tokens used over the course of the run step.
Total number of tokens used (prompt + completion).
class ThreadRunStepFailed: …Occurs when a run step fails.
Occurs when a run step fails.
Represents a step in execution of a run.
Represents a step in execution of a run.
The identifier of the run step, which can be referenced in API endpoints.
The ID of the assistant associated with the run step.
The Unix timestamp (in seconds) for when the run step was cancelled.
The Unix timestamp (in seconds) for when the run step completed.
The Unix timestamp (in seconds) for when the run step was created.
The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.
The Unix timestamp (in seconds) for when the run step failed.
last_error: Optional[LastError]The last error associated with this run step. Will be null if there are no errors.
The last error associated with this run step. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded"]One of server_error or rate_limit_exceeded.
One of server_error or rate_limit_exceeded.
A human-readable description of the error.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.run.step.
The ID of the run that this run step is a part of.
status: Literal["in_progress", "cancelled", "failed", 2 more]The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
step_details: StepDetailsThe details of the run step.
The details of the run step.
class MessageCreationStepDetails: …Details of the message creation by the run step.
Details of the message creation by the run step.
message_creation: MessageCreation
The ID of the message that was created by this run step.
Always message_creation.
class ToolCallsStepDetails: …Details of the tool call.
Details of the tool call.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
class CodeInterpreterToolCall: …Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The ID of the tool call.
code_interpreter: CodeInterpreterThe Code Interpreter tool call definition.
The Code Interpreter tool call definition.
The input to the Code Interpreter tool call.
outputs: List[CodeInterpreterOutput]The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
class CodeInterpreterOutputLogs: …Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The text output from the Code Interpreter tool call.
Always logs.
class CodeInterpreterOutputImage: …
image: CodeInterpreterOutputImageImage
The file ID of the image.
Always image.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
class FileSearchToolCall: …
The ID of the tool call object.
file_search: FileSearchFor now, this is always going to be an empty object.
For now, this is always going to be an empty object.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search.
The ranking options for the file search.
ranker: Literal["auto", "default_2024_08_21"]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
results: Optional[List[FileSearchResult]]The results of the file search.
The results of the file search.
The ID of the file that result was found in.
The name of the file that result was found in.
The score of the result. All values must be a floating point number between 0 and 1.
content: Optional[List[FileSearchResultContent]]The content of the result that was found. The content is only included if requested via the include query parameter.
The content of the result that was found. The content is only included if requested via the include query parameter.
The text content of the file.
The type of the content.
The type of tool call. This is always going to be file_search for this type of tool call.
class FunctionToolCall: …
The ID of the tool call object.
function: FunctionThe definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The type of tool call. This is always going to be function for this type of tool call.
Always tool_calls.
The ID of the thread that was run.
type: Literal["message_creation", "tool_calls"]The type of run step, which can be either message_creation or tool_calls.
The type of run step, which can be either message_creation or tool_calls.
usage: Optional[Usage]Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Number of completion tokens used over the course of the run step.
Number of prompt tokens used over the course of the run step.
Total number of tokens used (prompt + completion).
class ThreadRunStepCancelled: …Occurs when a run step is cancelled.
Occurs when a run step is cancelled.
Represents a step in execution of a run.
Represents a step in execution of a run.
The identifier of the run step, which can be referenced in API endpoints.
The ID of the assistant associated with the run step.
The Unix timestamp (in seconds) for when the run step was cancelled.
The Unix timestamp (in seconds) for when the run step completed.
The Unix timestamp (in seconds) for when the run step was created.
The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.
The Unix timestamp (in seconds) for when the run step failed.
last_error: Optional[LastError]The last error associated with this run step. Will be null if there are no errors.
The last error associated with this run step. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded"]One of server_error or rate_limit_exceeded.
One of server_error or rate_limit_exceeded.
A human-readable description of the error.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.run.step.
The ID of the run that this run step is a part of.
status: Literal["in_progress", "cancelled", "failed", 2 more]The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
step_details: StepDetailsThe details of the run step.
The details of the run step.
class MessageCreationStepDetails: …Details of the message creation by the run step.
Details of the message creation by the run step.
message_creation: MessageCreation
The ID of the message that was created by this run step.
Always message_creation.
class ToolCallsStepDetails: …Details of the tool call.
Details of the tool call.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
class CodeInterpreterToolCall: …Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The ID of the tool call.
code_interpreter: CodeInterpreterThe Code Interpreter tool call definition.
The Code Interpreter tool call definition.
The input to the Code Interpreter tool call.
outputs: List[CodeInterpreterOutput]The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
class CodeInterpreterOutputLogs: …Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The text output from the Code Interpreter tool call.
Always logs.
class CodeInterpreterOutputImage: …
image: CodeInterpreterOutputImageImage
The file ID of the image.
Always image.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
class FileSearchToolCall: …
The ID of the tool call object.
file_search: FileSearchFor now, this is always going to be an empty object.
For now, this is always going to be an empty object.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search.
The ranking options for the file search.
ranker: Literal["auto", "default_2024_08_21"]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
results: Optional[List[FileSearchResult]]The results of the file search.
The results of the file search.
The ID of the file that result was found in.
The name of the file that result was found in.
The score of the result. All values must be a floating point number between 0 and 1.
content: Optional[List[FileSearchResultContent]]The content of the result that was found. The content is only included if requested via the include query parameter.
The content of the result that was found. The content is only included if requested via the include query parameter.
The text content of the file.
The type of the content.
The type of tool call. This is always going to be file_search for this type of tool call.
class FunctionToolCall: …
The ID of the tool call object.
function: FunctionThe definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The type of tool call. This is always going to be function for this type of tool call.
Always tool_calls.
The ID of the thread that was run.
type: Literal["message_creation", "tool_calls"]The type of run step, which can be either message_creation or tool_calls.
The type of run step, which can be either message_creation or tool_calls.
usage: Optional[Usage]Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Number of completion tokens used over the course of the run step.
Number of prompt tokens used over the course of the run step.
Total number of tokens used (prompt + completion).
class ThreadRunStepExpired: …Occurs when a run step expires.
Occurs when a run step expires.
Represents a step in execution of a run.
Represents a step in execution of a run.
The identifier of the run step, which can be referenced in API endpoints.
The ID of the assistant associated with the run step.
The Unix timestamp (in seconds) for when the run step was cancelled.
The Unix timestamp (in seconds) for when the run step completed.
The Unix timestamp (in seconds) for when the run step was created.
The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired.
The Unix timestamp (in seconds) for when the run step failed.
last_error: Optional[LastError]The last error associated with this run step. Will be null if there are no errors.
The last error associated with this run step. Will be null if there are no errors.
code: Literal["server_error", "rate_limit_exceeded"]One of server_error or rate_limit_exceeded.
One of server_error or rate_limit_exceeded.
A human-readable description of the error.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.run.step.
The ID of the run that this run step is a part of.
status: Literal["in_progress", "cancelled", "failed", 2 more]The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
The status of the run step, which can be either in_progress, cancelled, failed, completed, or expired.
step_details: StepDetailsThe details of the run step.
The details of the run step.
class MessageCreationStepDetails: …Details of the message creation by the run step.
Details of the message creation by the run step.
message_creation: MessageCreation
The ID of the message that was created by this run step.
Always message_creation.
class ToolCallsStepDetails: …Details of the tool call.
Details of the tool call.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
An array of tool calls the run step was involved in. These can be associated with one of three types of tools: code_interpreter, file_search, or function.
class CodeInterpreterToolCall: …Details of the Code Interpreter tool call the run step was involved in.
Details of the Code Interpreter tool call the run step was involved in.
The ID of the tool call.
code_interpreter: CodeInterpreterThe Code Interpreter tool call definition.
The Code Interpreter tool call definition.
The input to the Code Interpreter tool call.
outputs: List[CodeInterpreterOutput]The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (logs) or images (image). Each of these are represented by a different object type.
class CodeInterpreterOutputLogs: …Text output from the Code Interpreter tool call as part of a run step.
Text output from the Code Interpreter tool call as part of a run step.
The text output from the Code Interpreter tool call.
Always logs.
class CodeInterpreterOutputImage: …
image: CodeInterpreterOutputImageImage
The file ID of the image.
Always image.
The type of tool call. This is always going to be code_interpreter for this type of tool call.
class FileSearchToolCall: …
The ID of the tool call object.
file_search: FileSearchFor now, this is always going to be an empty object.
For now, this is always going to be an empty object.
ranking_options: Optional[FileSearchRankingOptions]The ranking options for the file search.
The ranking options for the file search.
ranker: Literal["auto", "default_2024_08_21"]The ranker to use for the file search. If not specified will use the auto ranker.
The ranker to use for the file search. If not specified will use the auto ranker.
The score threshold for the file search. All values must be a floating point number between 0 and 1.
results: Optional[List[FileSearchResult]]The results of the file search.
The results of the file search.
The ID of the file that result was found in.
The name of the file that result was found in.
The score of the result. All values must be a floating point number between 0 and 1.
content: Optional[List[FileSearchResultContent]]The content of the result that was found. The content is only included if requested via the include query parameter.
The content of the result that was found. The content is only included if requested via the include query parameter.
The text content of the file.
The type of the content.
The type of tool call. This is always going to be file_search for this type of tool call.
class FunctionToolCall: …
The ID of the tool call object.
function: FunctionThe definition of the function that was called.
The definition of the function that was called.
The arguments passed to the function.
The name of the function.
The output of the function. This will be null if the outputs have not been submitted yet.
The type of tool call. This is always going to be function for this type of tool call.
Always tool_calls.
The ID of the thread that was run.
type: Literal["message_creation", "tool_calls"]The type of run step, which can be either message_creation or tool_calls.
The type of run step, which can be either message_creation or tool_calls.
usage: Optional[Usage]Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Usage statistics related to the run step. This value will be null while the run step's status is in_progress.
Number of completion tokens used over the course of the run step.
Number of prompt tokens used over the course of the run step.
Total number of tokens used (prompt + completion).
class ThreadMessageCreated: …Occurs when a message is created.
Occurs when a message is created.
The identifier, which can be referenced in API endpoints.
If applicable, the ID of the assistant that authored this message.
attachments: Optional[List[Attachment]]A list of files attached to the message, and the tools they were added to.
A list of files attached to the message, and the tools they were added to.
The ID of the file to attach to the message.
tools: Optional[List[AttachmentTool]]The tools to add this file to.
The tools to add this file to.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class AttachmentToolAssistantToolsFileSearchTypeOnly: …
The type of tool being defined: file_search
The Unix timestamp (in seconds) for when the message was completed.
The content of the message in array of text and/or images.
The content of the message in array of text and/or images.
class ImageFileContentBlock: …References an image File in the content of a message.
References an image File in the content of a message.
The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Always image_file.
class ImageURLContentBlock: …References an image URL in the content of a message.
References an image URL in the content of a message.
The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
The type of the content part.
class TextContentBlock: …The text content that is part of a message.
The text content that is part of a message.
class FileCitationAnnotation: …A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
file_citation: FileCitation
The ID of the specific File the citation is from.
The text in the message content that needs to be replaced.
Always file_citation.
class FilePathAnnotation: …A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
file_path: FilePath
The ID of the file that was generated.
The text in the message content that needs to be replaced.
Always file_path.
The data that makes up the text.
Always text.
class RefusalContentBlock: …The refusal content generated by the assistant.
The refusal content generated by the assistant.
Always refusal.
The Unix timestamp (in seconds) for when the message was created.
The Unix timestamp (in seconds) for when the message was marked as incomplete.
incomplete_details: Optional[IncompleteDetails]On an incomplete message, details about why the message is incomplete.
On an incomplete message, details about why the message is incomplete.
reason: Literal["content_filter", "max_tokens", "run_cancelled", 2 more]The reason the message is incomplete.
The reason the message is incomplete.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.message.
role: Literal["user", "assistant"]The entity that produced the message. One of user or assistant.
The entity that produced the message. One of user or assistant.
The ID of the run associated with the creation of this message. Value is null when messages are created manually using the create message or create thread endpoints.
status: Literal["in_progress", "incomplete", "completed"]The status of the message, which can be either in_progress, incomplete, or completed.
The status of the message, which can be either in_progress, incomplete, or completed.
The thread ID that this message belongs to.
class ThreadMessageInProgress: …Occurs when a message moves to an in_progress state.
Occurs when a message moves to an in_progress state.
The identifier, which can be referenced in API endpoints.
If applicable, the ID of the assistant that authored this message.
attachments: Optional[List[Attachment]]A list of files attached to the message, and the tools they were added to.
A list of files attached to the message, and the tools they were added to.
The ID of the file to attach to the message.
tools: Optional[List[AttachmentTool]]The tools to add this file to.
The tools to add this file to.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class AttachmentToolAssistantToolsFileSearchTypeOnly: …
The type of tool being defined: file_search
The Unix timestamp (in seconds) for when the message was completed.
The content of the message in array of text and/or images.
The content of the message in array of text and/or images.
class ImageFileContentBlock: …References an image File in the content of a message.
References an image File in the content of a message.
The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Always image_file.
class ImageURLContentBlock: …References an image URL in the content of a message.
References an image URL in the content of a message.
The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
The type of the content part.
class TextContentBlock: …The text content that is part of a message.
The text content that is part of a message.
class FileCitationAnnotation: …A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
file_citation: FileCitation
The ID of the specific File the citation is from.
The text in the message content that needs to be replaced.
Always file_citation.
class FilePathAnnotation: …A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
file_path: FilePath
The ID of the file that was generated.
The text in the message content that needs to be replaced.
Always file_path.
The data that makes up the text.
Always text.
class RefusalContentBlock: …The refusal content generated by the assistant.
The refusal content generated by the assistant.
Always refusal.
The Unix timestamp (in seconds) for when the message was created.
The Unix timestamp (in seconds) for when the message was marked as incomplete.
incomplete_details: Optional[IncompleteDetails]On an incomplete message, details about why the message is incomplete.
On an incomplete message, details about why the message is incomplete.
reason: Literal["content_filter", "max_tokens", "run_cancelled", 2 more]The reason the message is incomplete.
The reason the message is incomplete.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.message.
role: Literal["user", "assistant"]The entity that produced the message. One of user or assistant.
The entity that produced the message. One of user or assistant.
The ID of the run associated with the creation of this message. Value is null when messages are created manually using the create message or create thread endpoints.
status: Literal["in_progress", "incomplete", "completed"]The status of the message, which can be either in_progress, incomplete, or completed.
The status of the message, which can be either in_progress, incomplete, or completed.
The thread ID that this message belongs to.
class ThreadMessageDelta: …Occurs when parts of a Message are being streamed.
Occurs when parts of a Message are being streamed.
Represents a message delta i.e. any changed fields on a message during streaming.
Represents a message delta i.e. any changed fields on a message during streaming.
The identifier of the message, which can be referenced in API endpoints.
The delta containing the fields that have changed on the Message.
The delta containing the fields that have changed on the Message.
The content of the message in array of text and/or images.
The content of the message in array of text and/or images.
class ImageFileDeltaBlock: …References an image File in the content of a message.
References an image File in the content of a message.
The index of the content part in the message.
Always image_file.
image_file: Optional[ImageFileDelta]
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.
class TextDeltaBlock: …The text content that is part of a message.
The text content that is part of a message.
The index of the content part in the message.
Always text.
text: Optional[TextDelta]
class FileCitationDeltaAnnotation: …A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
The index of the annotation in the text content part.
Always file_citation.
file_citation: Optional[FileCitation]
The ID of the specific File the citation is from.
The specific quote in the file.
The text in the message content that needs to be replaced.
class FilePathDeltaAnnotation: …A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
The index of the annotation in the text content part.
Always file_path.
file_path: Optional[FilePath]
The ID of the file that was generated.
The text in the message content that needs to be replaced.
The data that makes up the text.
class RefusalDeltaBlock: …The refusal content that is part of a message.
The refusal content that is part of a message.
The index of the refusal part in the message.
Always refusal.
class ImageURLDeltaBlock: …References an image URL in the content of a message.
References an image URL in the content of a message.
The index of the content part in the message.
Always image_url.
image_url: Optional[ImageURLDelta]
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high.
Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high.
The URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.
role: Optional[Literal["user", "assistant"]]The entity that produced the message. One of user or assistant.
The entity that produced the message. One of user or assistant.
The object type, which is always thread.message.delta.
class ThreadMessageCompleted: …Occurs when a message is completed.
Occurs when a message is completed.
The identifier, which can be referenced in API endpoints.
If applicable, the ID of the assistant that authored this message.
attachments: Optional[List[Attachment]]A list of files attached to the message, and the tools they were added to.
A list of files attached to the message, and the tools they were added to.
The ID of the file to attach to the message.
tools: Optional[List[AttachmentTool]]The tools to add this file to.
The tools to add this file to.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class AttachmentToolAssistantToolsFileSearchTypeOnly: …
The type of tool being defined: file_search
The Unix timestamp (in seconds) for when the message was completed.
The content of the message in array of text and/or images.
The content of the message in array of text and/or images.
class ImageFileContentBlock: …References an image File in the content of a message.
References an image File in the content of a message.
The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Always image_file.
class ImageURLContentBlock: …References an image URL in the content of a message.
References an image URL in the content of a message.
The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
The type of the content part.
class TextContentBlock: …The text content that is part of a message.
The text content that is part of a message.
class FileCitationAnnotation: …A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
file_citation: FileCitation
The ID of the specific File the citation is from.
The text in the message content that needs to be replaced.
Always file_citation.
class FilePathAnnotation: …A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
file_path: FilePath
The ID of the file that was generated.
The text in the message content that needs to be replaced.
Always file_path.
The data that makes up the text.
Always text.
class RefusalContentBlock: …The refusal content generated by the assistant.
The refusal content generated by the assistant.
Always refusal.
The Unix timestamp (in seconds) for when the message was created.
The Unix timestamp (in seconds) for when the message was marked as incomplete.
incomplete_details: Optional[IncompleteDetails]On an incomplete message, details about why the message is incomplete.
On an incomplete message, details about why the message is incomplete.
reason: Literal["content_filter", "max_tokens", "run_cancelled", 2 more]The reason the message is incomplete.
The reason the message is incomplete.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.message.
role: Literal["user", "assistant"]The entity that produced the message. One of user or assistant.
The entity that produced the message. One of user or assistant.
The ID of the run associated with the creation of this message. Value is null when messages are created manually using the create message or create thread endpoints.
status: Literal["in_progress", "incomplete", "completed"]The status of the message, which can be either in_progress, incomplete, or completed.
The status of the message, which can be either in_progress, incomplete, or completed.
The thread ID that this message belongs to.
class ThreadMessageIncomplete: …Occurs when a message ends before it is completed.
Occurs when a message ends before it is completed.
The identifier, which can be referenced in API endpoints.
If applicable, the ID of the assistant that authored this message.
attachments: Optional[List[Attachment]]A list of files attached to the message, and the tools they were added to.
A list of files attached to the message, and the tools they were added to.
The ID of the file to attach to the message.
tools: Optional[List[AttachmentTool]]The tools to add this file to.
The tools to add this file to.
class CodeInterpreterTool: …
The type of tool being defined: code_interpreter
class AttachmentToolAssistantToolsFileSearchTypeOnly: …
The type of tool being defined: file_search
The Unix timestamp (in seconds) for when the message was completed.
The content of the message in array of text and/or images.
The content of the message in array of text and/or images.
class ImageFileContentBlock: …References an image File in the content of a message.
References an image File in the content of a message.
The File ID of the image in the message content. Set purpose="vision" when uploading the File if you need to later display the file content.
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Specifies the detail level of the image if specified by the user. low uses fewer tokens, you can opt in to high resolution using high.
Always image_file.
class ImageURLContentBlock: …References an image URL in the content of a message.
References an image URL in the content of a message.
The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp.
detail: Optional[Literal["auto", "low", "high"]]Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
Specifies the detail level of the image. low uses fewer tokens, you can opt in to high resolution using high. Default value is auto
The type of the content part.
class TextContentBlock: …The text content that is part of a message.
The text content that is part of a message.
class FileCitationAnnotation: …A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files.
file_citation: FileCitation
The ID of the specific File the citation is from.
The text in the message content that needs to be replaced.
Always file_citation.
class FilePathAnnotation: …A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
A URL for the file that's generated when the assistant used the code_interpreter tool to generate a file.
file_path: FilePath
The ID of the file that was generated.
The text in the message content that needs to be replaced.
Always file_path.
The data that makes up the text.
Always text.
class RefusalContentBlock: …The refusal content generated by the assistant.
The refusal content generated by the assistant.
Always refusal.
The Unix timestamp (in seconds) for when the message was created.
The Unix timestamp (in seconds) for when the message was marked as incomplete.
incomplete_details: Optional[IncompleteDetails]On an incomplete message, details about why the message is incomplete.
On an incomplete message, details about why the message is incomplete.
reason: Literal["content_filter", "max_tokens", "run_cancelled", 2 more]The reason the message is incomplete.
The reason the message is incomplete.
Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.
Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
The object type, which is always thread.message.
role: Literal["user", "assistant"]The entity that produced the message. One of user or assistant.
The entity that produced the message. One of user or assistant.
The ID of the run associated with the creation of this message. Value is null when messages are created manually using the create message or create thread endpoints.
status: Literal["in_progress", "incomplete", "completed"]The status of the message, which can be either in_progress, incomplete, or completed.
The status of the message, which can be either in_progress, incomplete, or completed.
The thread ID that this message belongs to.
class ErrorEvent: …Occurs when an error occurs. This can happen due to an internal server error or a timeout.
Occurs when an error occurs. This can happen due to an internal server error or a timeout.
Create thread and run
from openai import OpenAI
client = OpenAI()
run = client.beta.threads.create_and_run(
assistant_id="asst_abc123",
thread={
"messages": [
{"role": "user", "content": "Explain deep learning to a 5 year old."}
]
}
)
print(run)
{
"id": "run_abc123",
"object": "thread.run",
"created_at": 1699076792,
"assistant_id": "asst_abc123",
"thread_id": "thread_abc123",
"status": "queued",
"started_at": null,
"expires_at": 1699077392,
"cancelled_at": null,
"failed_at": null,
"completed_at": null,
"required_action": null,
"last_error": null,
"model": "gpt-4o",
"instructions": "You are a helpful assistant.",
"tools": [],
"tool_resources": {},
"metadata": {},
"temperature": 1.0,
"top_p": 1.0,
"max_completion_tokens": null,
"max_prompt_tokens": null,
"truncation_strategy": {
"type": "auto",
"last_messages": null
},
"incomplete_details": null,
"usage": null,
"response_format": "auto",
"tool_choice": "auto",
"parallel_tool_calls": true
}
Create thread and run
from openai import OpenAI
client = OpenAI()
stream = client.beta.threads.create_and_run(
assistant_id="asst_123",
thread={
"messages": [
{"role": "user", "content": "Hello"}
]
},
stream=True
)
for event in stream:
print(event)
event: thread.created
data: {"id":"thread_123","object":"thread","created_at":1710348075,"metadata":{}}
event: thread.run.created
data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}
event: thread.run.queued
data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}
event: thread.run.in_progress
data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}
event: thread.run.step.created
data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null}
event: thread.run.step.in_progress
data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null}
event: thread.message.created
data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[], "metadata":{}}
event: thread.message.in_progress
data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[], "metadata":{}}
event: thread.message.delta
data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}}
...
event: thread.message.delta
data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" today"}}]}}
event: thread.message.delta
data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}}
event: thread.message.completed
data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710348077,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! How can I assist you today?","annotations":[]}}], "metadata":{}}
event: thread.run.step.completed
data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710348077,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}}
event: thread.run.completed
{"id":"run_123","object":"thread.run","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1713226836,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1713226837,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":345,"completion_tokens":11,"total_tokens":356},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}
event: done
data: [DONE]
Create thread and run
from openai import OpenAI
client = OpenAI()
tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location"],
},
}
}
]
stream = client.beta.threads.create_and_run(
thread={
"messages": [
{"role": "user", "content": "What is the weather like in San Francisco?"}
]
},
assistant_id="asst_abc123",
tools=tools,
stream=True
)
for event in stream:
print(event)
event: thread.created
data: {"id":"thread_123","object":"thread","created_at":1710351818,"metadata":{}}
event: thread.run.created
data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}}
event: thread.run.queued
data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}}
event: thread.run.in_progress
data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710351818,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}}
event: thread.run.step.created
data: {"id":"step_001","object":"thread.run.step","created_at":1710351819,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710352418,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[]},"usage":null}
event: thread.run.step.in_progress
data: {"id":"step_001","object":"thread.run.step","created_at":1710351819,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710352418,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[]},"usage":null}
event: thread.run.step.delta
data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"id":"call_XXNp8YGaFrjrSjgqxtC8JJ1B","type":"function","function":{"name":"get_current_weather","arguments":"","output":null}}]}}}
event: thread.run.step.delta
data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"{\""}}]}}}
event: thread.run.step.delta
data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"location"}}]}}}
...
event: thread.run.step.delta
data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"ahrenheit"}}]}}}
event: thread.run.step.delta
data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"\"}"}}]}}}
event: thread.run.requires_action
data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"requires_action","started_at":1710351818,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":{"type":"submit_tool_outputs","submit_tool_outputs":{"tool_calls":[{"id":"call_XXNp8YGaFrjrSjgqxtC8JJ1B","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\":\"San Francisco, CA\",\"unit\":\"fahrenheit\"}"}}]}},"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":345,"completion_tokens":11,"total_tokens":356},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}}
event: done
data: [DONE]
Returns Examples
{
"id": "id",
"assistant_id": "assistant_id",
"cancelled_at": 0,
"completed_at": 0,
"created_at": 0,
"expires_at": 0,
"failed_at": 0,
"incomplete_details": {
"reason": "max_completion_tokens"
},
"instructions": "instructions",
"last_error": {
"code": "server_error",
"message": "message"
},
"max_completion_tokens": 256,
"max_prompt_tokens": 256,
"metadata": {
"foo": "string"
},
"model": "model",
"object": "thread.run",
"parallel_tool_calls": true,
"required_action": {
"submit_tool_outputs": {
"tool_calls": [
{
"id": "id",
"function": {
"arguments": "arguments",
"name": "name"
},
"type": "function"
}
]
},
"type": "submit_tool_outputs"
},
"response_format": "auto",
"started_at": 0,
"status": "queued",
"thread_id": "thread_id",
"tool_choice": "none",
"tools": [
{
"type": "code_interpreter"
}
],
"truncation_strategy": {
"type": "auto",
"last_messages": 1
},
"usage": {
"completion_tokens": 0,
"prompt_tokens": 0,
"total_tokens": 0
},
"temperature": 0,
"top_p": 0
}