2904 lines
139 KiB
Python
2904 lines
139 KiB
Python
|
# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
|
||
|
|
|
||
|
|
from __future__ import annotations
|
||
|
|
|
||
|
|
import typing_extensions
|
||
|
|
from typing import List, Union, Iterable, Optional
|
||
|
|
from functools import partial
|
||
|
|
from typing_extensions import Literal, overload
|
||
|
|
|
||
|
|
import httpx
|
||
|
|
|
||
|
|
from ..... import _legacy_response
|
||
|
|
from .steps import (
|
||
|
|
Steps,
|
||
|
|
AsyncSteps,
|
||
|
|
StepsWithRawResponse,
|
||
|
|
AsyncStepsWithRawResponse,
|
||
|
|
StepsWithStreamingResponse,
|
||
|
|
AsyncStepsWithStreamingResponse,
|
||
|
|
)
|
||
|
|
from ....._types import NOT_GIVEN, Body, Query, Headers, NotGiven
|
||
|
|
from ....._utils import (
|
||
|
|
is_given,
|
||
|
|
required_args,
|
||
|
|
maybe_transform,
|
||
|
|
async_maybe_transform,
|
||
|
|
)
|
||
|
|
from ....._compat import cached_property
|
||
|
|
from ....._resource import SyncAPIResource, AsyncAPIResource
|
||
|
|
from ....._response import to_streamed_response_wrapper, async_to_streamed_response_wrapper
|
||
|
|
from ....._streaming import Stream, AsyncStream
|
||
|
|
from .....pagination import SyncCursorPage, AsyncCursorPage
|
||
|
|
from ....._base_client import AsyncPaginator, make_request_options
|
||
|
|
from .....lib.streaming import (
|
||
|
|
AssistantEventHandler,
|
||
|
|
AssistantEventHandlerT,
|
||
|
|
AssistantStreamManager,
|
||
|
|
AsyncAssistantEventHandler,
|
||
|
|
AsyncAssistantEventHandlerT,
|
||
|
|
AsyncAssistantStreamManager,
|
||
|
|
)
|
||
|
|
from .....types.chat_model import ChatModel
|
||
|
|
from .....types.beta.threads import (
|
||
|
|
run_list_params,
|
||
|
|
run_create_params,
|
||
|
|
run_update_params,
|
||
|
|
run_submit_tool_outputs_params,
|
||
|
|
)
|
||
|
|
from .....types.beta.threads.run import Run
|
||
|
|
from .....types.beta.assistant_tool_param import AssistantToolParam
|
||
|
|
from .....types.beta.assistant_stream_event import AssistantStreamEvent
|
||
|
|
from .....types.beta.threads.runs.run_step_include import RunStepInclude
|
||
|
|
from .....types.beta.assistant_tool_choice_option_param import AssistantToolChoiceOptionParam
|
||
|
|
from .....types.beta.assistant_response_format_option_param import AssistantResponseFormatOptionParam
|
||
|
|
|
||
|
|
__all__ = ["Runs", "AsyncRuns"]
|
||
|
|
|
||
|
|
|
||
|
|
class Runs(SyncAPIResource):
|
||
|
|
@cached_property
|
||
|
|
def steps(self) -> Steps:
|
||
|
|
return Steps(self._client)
|
||
|
|
|
||
|
|
@cached_property
|
||
|
|
def with_raw_response(self) -> RunsWithRawResponse:
|
||
|
|
"""
|
||
|
|
This property can be used as a prefix for any HTTP method call to return
|
||
|
|
the raw response object instead of the parsed content.
|
||
|
|
|
||
|
|
For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
|
||
|
|
"""
|
||
|
|
return RunsWithRawResponse(self)
|
||
|
|
|
||
|
|
@cached_property
|
||
|
|
def with_streaming_response(self) -> RunsWithStreamingResponse:
|
||
|
|
"""
|
||
|
|
An alternative to `.with_raw_response` that doesn't eagerly read the response body.
|
||
|
|
|
||
|
|
For more information, see https://www.github.com/openai/openai-python#with_streaming_response
|
||
|
|
"""
|
||
|
|
return RunsWithStreamingResponse(self)
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def create(
|
||
|
|
self,
|
||
|
|
thread_id: str,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
Create a run.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
assistant_id: The ID of the
|
||
|
|
[assistant](https://platform.openai.com/docs/api-reference/assistants) to use to
|
||
|
|
execute this run.
|
||
|
|
|
||
|
|
include: A list of additional fields to include in the response. Currently the only
|
||
|
|
supported value is `step_details.tool_calls[*].file_search.results[*].content`
|
||
|
|
to fetch the file search result content.
|
||
|
|
|
||
|
|
See the
|
||
|
|
[file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
|
||
|
|
for more information.
|
||
|
|
|
||
|
|
additional_instructions: Appends additional instructions at the end of the instructions for the run. This
|
||
|
|
is useful for modifying the behavior on a per-run basis without overriding other
|
||
|
|
instructions.
|
||
|
|
|
||
|
|
additional_messages: Adds additional messages to the thread before creating the run.
|
||
|
|
|
||
|
|
instructions: Overrides the
|
||
|
|
[instructions](https://platform.openai.com/docs/api-reference/assistants/createAssistant)
|
||
|
|
of the assistant. This is useful for modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
max_completion_tokens: 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.
|
||
|
|
|
||
|
|
max_prompt_tokens: 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.
|
||
|
|
|
||
|
|
metadata: 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. Keys
|
||
|
|
can be a maximum of 64 characters long and values can be a maximum of 512
|
||
|
|
characters long.
|
||
|
|
|
||
|
|
model: The ID of the [Model](https://platform.openai.com/docs/api-reference/models) to
|
||
|
|
be used to execute this run. If a value is provided here, it will override the
|
||
|
|
model associated with the assistant. If not, the model associated with the
|
||
|
|
assistant will be used.
|
||
|
|
|
||
|
|
parallel_tool_calls: Whether to enable
|
||
|
|
[parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
|
||
|
|
during tool use.
|
||
|
|
|
||
|
|
response_format: Specifies the format that the model must output. Compatible with
|
||
|
|
[GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
|
||
|
|
[GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
|
||
|
|
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](https://platform.openai.com/docs/guides/structured-outputs).
|
||
|
|
|
||
|
|
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.
|
||
|
|
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
temperature: 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.
|
||
|
|
|
||
|
|
tool_choice: 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.
|
||
|
|
|
||
|
|
tools: Override the tools the assistant can use for this run. This is useful for
|
||
|
|
modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
top_p: 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.
|
||
|
|
|
||
|
|
truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
|
||
|
|
control the intial context window of the run.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def create(
|
||
|
|
self,
|
||
|
|
thread_id: str,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
stream: Literal[True],
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Stream[AssistantStreamEvent]:
|
||
|
|
"""
|
||
|
|
Create a run.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
assistant_id: The ID of the
|
||
|
|
[assistant](https://platform.openai.com/docs/api-reference/assistants) to use to
|
||
|
|
execute this run.
|
||
|
|
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
include: A list of additional fields to include in the response. Currently the only
|
||
|
|
supported value is `step_details.tool_calls[*].file_search.results[*].content`
|
||
|
|
to fetch the file search result content.
|
||
|
|
|
||
|
|
See the
|
||
|
|
[file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
|
||
|
|
for more information.
|
||
|
|
|
||
|
|
additional_instructions: Appends additional instructions at the end of the instructions for the run. This
|
||
|
|
is useful for modifying the behavior on a per-run basis without overriding other
|
||
|
|
instructions.
|
||
|
|
|
||
|
|
additional_messages: Adds additional messages to the thread before creating the run.
|
||
|
|
|
||
|
|
instructions: Overrides the
|
||
|
|
[instructions](https://platform.openai.com/docs/api-reference/assistants/createAssistant)
|
||
|
|
of the assistant. This is useful for modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
max_completion_tokens: 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.
|
||
|
|
|
||
|
|
max_prompt_tokens: 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.
|
||
|
|
|
||
|
|
metadata: 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. Keys
|
||
|
|
can be a maximum of 64 characters long and values can be a maximum of 512
|
||
|
|
characters long.
|
||
|
|
|
||
|
|
model: The ID of the [Model](https://platform.openai.com/docs/api-reference/models) to
|
||
|
|
be used to execute this run. If a value is provided here, it will override the
|
||
|
|
model associated with the assistant. If not, the model associated with the
|
||
|
|
assistant will be used.
|
||
|
|
|
||
|
|
parallel_tool_calls: Whether to enable
|
||
|
|
[parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
|
||
|
|
during tool use.
|
||
|
|
|
||
|
|
response_format: Specifies the format that the model must output. Compatible with
|
||
|
|
[GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
|
||
|
|
[GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
|
||
|
|
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](https://platform.openai.com/docs/guides/structured-outputs).
|
||
|
|
|
||
|
|
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.
|
||
|
|
|
||
|
|
temperature: 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.
|
||
|
|
|
||
|
|
tool_choice: 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.
|
||
|
|
|
||
|
|
tools: Override the tools the assistant can use for this run. This is useful for
|
||
|
|
modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
top_p: 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.
|
||
|
|
|
||
|
|
truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
|
||
|
|
control the intial context window of the run.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def create(
|
||
|
|
self,
|
||
|
|
thread_id: str,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
stream: bool,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run | Stream[AssistantStreamEvent]:
|
||
|
|
"""
|
||
|
|
Create a run.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
assistant_id: The ID of the
|
||
|
|
[assistant](https://platform.openai.com/docs/api-reference/assistants) to use to
|
||
|
|
execute this run.
|
||
|
|
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
include: A list of additional fields to include in the response. Currently the only
|
||
|
|
supported value is `step_details.tool_calls[*].file_search.results[*].content`
|
||
|
|
to fetch the file search result content.
|
||
|
|
|
||
|
|
See the
|
||
|
|
[file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
|
||
|
|
for more information.
|
||
|
|
|
||
|
|
additional_instructions: Appends additional instructions at the end of the instructions for the run. This
|
||
|
|
is useful for modifying the behavior on a per-run basis without overriding other
|
||
|
|
instructions.
|
||
|
|
|
||
|
|
additional_messages: Adds additional messages to the thread before creating the run.
|
||
|
|
|
||
|
|
instructions: Overrides the
|
||
|
|
[instructions](https://platform.openai.com/docs/api-reference/assistants/createAssistant)
|
||
|
|
of the assistant. This is useful for modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
max_completion_tokens: 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.
|
||
|
|
|
||
|
|
max_prompt_tokens: 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.
|
||
|
|
|
||
|
|
metadata: 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. Keys
|
||
|
|
can be a maximum of 64 characters long and values can be a maximum of 512
|
||
|
|
characters long.
|
||
|
|
|
||
|
|
model: The ID of the [Model](https://platform.openai.com/docs/api-reference/models) to
|
||
|
|
be used to execute this run. If a value is provided here, it will override the
|
||
|
|
model associated with the assistant. If not, the model associated with the
|
||
|
|
assistant will be used.
|
||
|
|
|
||
|
|
parallel_tool_calls: Whether to enable
|
||
|
|
[parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
|
||
|
|
during tool use.
|
||
|
|
|
||
|
|
response_format: Specifies the format that the model must output. Compatible with
|
||
|
|
[GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
|
||
|
|
[GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
|
||
|
|
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](https://platform.openai.com/docs/guides/structured-outputs).
|
||
|
|
|
||
|
|
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.
|
||
|
|
|
||
|
|
temperature: 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.
|
||
|
|
|
||
|
|
tool_choice: 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.
|
||
|
|
|
||
|
|
tools: Override the tools the assistant can use for this run. This is useful for
|
||
|
|
modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
top_p: 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.
|
||
|
|
|
||
|
|
truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
|
||
|
|
control the intial context window of the run.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@required_args(["assistant_id"], ["assistant_id", "stream"])
|
||
|
|
def create(
|
||
|
|
self,
|
||
|
|
thread_id: str,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run | Stream[AssistantStreamEvent]:
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return self._post(
|
||
|
|
f"/threads/{thread_id}/runs",
|
||
|
|
body=maybe_transform(
|
||
|
|
{
|
||
|
|
"assistant_id": assistant_id,
|
||
|
|
"additional_instructions": additional_instructions,
|
||
|
|
"additional_messages": additional_messages,
|
||
|
|
"instructions": instructions,
|
||
|
|
"max_completion_tokens": max_completion_tokens,
|
||
|
|
"max_prompt_tokens": max_prompt_tokens,
|
||
|
|
"metadata": metadata,
|
||
|
|
"model": model,
|
||
|
|
"parallel_tool_calls": parallel_tool_calls,
|
||
|
|
"response_format": response_format,
|
||
|
|
"stream": stream,
|
||
|
|
"temperature": temperature,
|
||
|
|
"tool_choice": tool_choice,
|
||
|
|
"tools": tools,
|
||
|
|
"top_p": top_p,
|
||
|
|
"truncation_strategy": truncation_strategy,
|
||
|
|
},
|
||
|
|
run_create_params.RunCreateParams,
|
||
|
|
),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
query=maybe_transform({"include": include}, run_create_params.RunCreateParams),
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
stream=stream or False,
|
||
|
|
stream_cls=Stream[AssistantStreamEvent],
|
||
|
|
)
|
||
|
|
|
||
|
|
def retrieve(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
Retrieves a run.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
if not run_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return self._get(
|
||
|
|
f"/threads/{thread_id}/runs/{run_id}",
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
)
|
||
|
|
|
||
|
|
def update(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
Modifies a run.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
metadata: 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. Keys
|
||
|
|
can be a maximum of 64 characters long and values can be a maximum of 512
|
||
|
|
characters long.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
if not run_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return self._post(
|
||
|
|
f"/threads/{thread_id}/runs/{run_id}",
|
||
|
|
body=maybe_transform({"metadata": metadata}, run_update_params.RunUpdateParams),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
)
|
||
|
|
|
||
|
|
def list(
|
||
|
|
self,
|
||
|
|
thread_id: str,
|
||
|
|
*,
|
||
|
|
after: str | NotGiven = NOT_GIVEN,
|
||
|
|
before: str | NotGiven = NOT_GIVEN,
|
||
|
|
limit: int | NotGiven = NOT_GIVEN,
|
||
|
|
order: Literal["asc", "desc"] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> SyncCursorPage[Run]:
|
||
|
|
"""
|
||
|
|
Returns a list of runs belonging to a thread.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
after: A cursor for use in pagination. `after` is an object ID that defines your place
|
||
|
|
in the list. For instance, if you make a list request and receive 100 objects,
|
||
|
|
ending with obj_foo, your subsequent call can include after=obj_foo in order to
|
||
|
|
fetch the next page of the list.
|
||
|
|
|
||
|
|
before: A cursor for use in pagination. `before` is an object ID that defines your place
|
||
|
|
in the list. For instance, if you make a list request and receive 100 objects,
|
||
|
|
starting with obj_foo, your subsequent call can include before=obj_foo in order
|
||
|
|
to fetch the previous page of the list.
|
||
|
|
|
||
|
|
limit: A limit on the number of objects to be returned. Limit can range between 1 and
|
||
|
|
100, and the default is 20.
|
||
|
|
|
||
|
|
order: Sort order by the `created_at` timestamp of the objects. `asc` for ascending
|
||
|
|
order and `desc` for descending order.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return self._get_api_list(
|
||
|
|
f"/threads/{thread_id}/runs",
|
||
|
|
page=SyncCursorPage[Run],
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
query=maybe_transform(
|
||
|
|
{
|
||
|
|
"after": after,
|
||
|
|
"before": before,
|
||
|
|
"limit": limit,
|
||
|
|
"order": order,
|
||
|
|
},
|
||
|
|
run_list_params.RunListParams,
|
||
|
|
),
|
||
|
|
),
|
||
|
|
model=Run,
|
||
|
|
)
|
||
|
|
|
||
|
|
def cancel(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
Cancels a run that is `in_progress`.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
if not run_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return self._post(
|
||
|
|
f"/threads/{thread_id}/runs/{run_id}/cancel",
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
)
|
||
|
|
|
||
|
|
def create_and_poll(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
poll_interval_ms: int | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
A helper to create a run an poll for a terminal state. More information on Run
|
||
|
|
lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
run = self.create(
|
||
|
|
thread_id=thread_id,
|
||
|
|
assistant_id=assistant_id,
|
||
|
|
include=include,
|
||
|
|
additional_instructions=additional_instructions,
|
||
|
|
additional_messages=additional_messages,
|
||
|
|
instructions=instructions,
|
||
|
|
max_completion_tokens=max_completion_tokens,
|
||
|
|
max_prompt_tokens=max_prompt_tokens,
|
||
|
|
metadata=metadata,
|
||
|
|
model=model,
|
||
|
|
response_format=response_format,
|
||
|
|
temperature=temperature,
|
||
|
|
tool_choice=tool_choice,
|
||
|
|
parallel_tool_calls=parallel_tool_calls,
|
||
|
|
# We assume we are not streaming when polling
|
||
|
|
stream=False,
|
||
|
|
tools=tools,
|
||
|
|
truncation_strategy=truncation_strategy,
|
||
|
|
top_p=top_p,
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
)
|
||
|
|
return self.poll(
|
||
|
|
run.id,
|
||
|
|
thread_id=thread_id,
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
poll_interval_ms=poll_interval_ms,
|
||
|
|
timeout=timeout,
|
||
|
|
)
|
||
|
|
|
||
|
|
@overload
|
||
|
|
@typing_extensions.deprecated("use `stream` instead")
|
||
|
|
def create_and_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AssistantStreamManager[AssistantEventHandler]:
|
||
|
|
"""Create a Run stream"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
@typing_extensions.deprecated("use `stream` instead")
|
||
|
|
def create_and_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AssistantEventHandlerT,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AssistantStreamManager[AssistantEventHandlerT]:
|
||
|
|
"""Create a Run stream"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@typing_extensions.deprecated("use `stream` instead")
|
||
|
|
def create_and_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AssistantEventHandlerT | None = None,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AssistantStreamManager[AssistantEventHandler] | AssistantStreamManager[AssistantEventHandlerT]:
|
||
|
|
"""Create a Run stream"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
|
||
|
|
extra_headers = {
|
||
|
|
"OpenAI-Beta": "assistants=v2",
|
||
|
|
"X-Stainless-Stream-Helper": "threads.runs.create_and_stream",
|
||
|
|
"X-Stainless-Custom-Event-Handler": "true" if event_handler else "false",
|
||
|
|
**(extra_headers or {}),
|
||
|
|
}
|
||
|
|
make_request = partial(
|
||
|
|
self._post,
|
||
|
|
f"/threads/{thread_id}/runs",
|
||
|
|
body=maybe_transform(
|
||
|
|
{
|
||
|
|
"assistant_id": assistant_id,
|
||
|
|
"additional_instructions": additional_instructions,
|
||
|
|
"additional_messages": additional_messages,
|
||
|
|
"instructions": instructions,
|
||
|
|
"max_completion_tokens": max_completion_tokens,
|
||
|
|
"max_prompt_tokens": max_prompt_tokens,
|
||
|
|
"metadata": metadata,
|
||
|
|
"model": model,
|
||
|
|
"response_format": response_format,
|
||
|
|
"temperature": temperature,
|
||
|
|
"tool_choice": tool_choice,
|
||
|
|
"stream": True,
|
||
|
|
"tools": tools,
|
||
|
|
"truncation_strategy": truncation_strategy,
|
||
|
|
"parallel_tool_calls": parallel_tool_calls,
|
||
|
|
"top_p": top_p,
|
||
|
|
},
|
||
|
|
run_create_params.RunCreateParams,
|
||
|
|
),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
stream=True,
|
||
|
|
stream_cls=Stream[AssistantStreamEvent],
|
||
|
|
)
|
||
|
|
return AssistantStreamManager(make_request, event_handler=event_handler or AssistantEventHandler())
|
||
|
|
|
||
|
|
def poll(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
thread_id: str,
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
poll_interval_ms: int | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
A helper to poll a run status until it reaches a terminal state. More
|
||
|
|
information on Run lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
extra_headers = {"X-Stainless-Poll-Helper": "true", **(extra_headers or {})}
|
||
|
|
|
||
|
|
if is_given(poll_interval_ms):
|
||
|
|
extra_headers["X-Stainless-Custom-Poll-Interval"] = str(poll_interval_ms)
|
||
|
|
|
||
|
|
terminal_states = {"requires_action", "cancelled", "completed", "failed", "expired", "incomplete"}
|
||
|
|
while True:
|
||
|
|
response = self.with_raw_response.retrieve(
|
||
|
|
thread_id=thread_id,
|
||
|
|
run_id=run_id,
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_body=extra_body,
|
||
|
|
extra_query=extra_query,
|
||
|
|
timeout=timeout,
|
||
|
|
)
|
||
|
|
|
||
|
|
run = response.parse()
|
||
|
|
# Return if we reached a terminal state
|
||
|
|
if run.status in terminal_states:
|
||
|
|
return run
|
||
|
|
|
||
|
|
if not is_given(poll_interval_ms):
|
||
|
|
from_header = response.headers.get("openai-poll-after-ms")
|
||
|
|
if from_header is not None:
|
||
|
|
poll_interval_ms = int(from_header)
|
||
|
|
else:
|
||
|
|
poll_interval_ms = 1000
|
||
|
|
|
||
|
|
self._sleep(poll_interval_ms / 1000)
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AssistantStreamManager[AssistantEventHandler]:
|
||
|
|
"""Create a Run stream"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AssistantEventHandlerT,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AssistantStreamManager[AssistantEventHandlerT]:
|
||
|
|
"""Create a Run stream"""
|
||
|
|
...
|
||
|
|
|
||
|
|
def stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AssistantEventHandlerT | None = None,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AssistantStreamManager[AssistantEventHandler] | AssistantStreamManager[AssistantEventHandlerT]:
|
||
|
|
"""Create a Run stream"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
|
||
|
|
extra_headers = {
|
||
|
|
"OpenAI-Beta": "assistants=v2",
|
||
|
|
"X-Stainless-Stream-Helper": "threads.runs.create_and_stream",
|
||
|
|
"X-Stainless-Custom-Event-Handler": "true" if event_handler else "false",
|
||
|
|
**(extra_headers or {}),
|
||
|
|
}
|
||
|
|
make_request = partial(
|
||
|
|
self._post,
|
||
|
|
f"/threads/{thread_id}/runs",
|
||
|
|
body=maybe_transform(
|
||
|
|
{
|
||
|
|
"assistant_id": assistant_id,
|
||
|
|
"additional_instructions": additional_instructions,
|
||
|
|
"additional_messages": additional_messages,
|
||
|
|
"instructions": instructions,
|
||
|
|
"max_completion_tokens": max_completion_tokens,
|
||
|
|
"max_prompt_tokens": max_prompt_tokens,
|
||
|
|
"metadata": metadata,
|
||
|
|
"model": model,
|
||
|
|
"response_format": response_format,
|
||
|
|
"temperature": temperature,
|
||
|
|
"tool_choice": tool_choice,
|
||
|
|
"stream": True,
|
||
|
|
"tools": tools,
|
||
|
|
"parallel_tool_calls": parallel_tool_calls,
|
||
|
|
"truncation_strategy": truncation_strategy,
|
||
|
|
"top_p": top_p,
|
||
|
|
},
|
||
|
|
run_create_params.RunCreateParams,
|
||
|
|
),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
query=maybe_transform({"include": include}, run_create_params.RunCreateParams),
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
stream=True,
|
||
|
|
stream_cls=Stream[AssistantStreamEvent],
|
||
|
|
)
|
||
|
|
return AssistantStreamManager(make_request, event_handler=event_handler or AssistantEventHandler())
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def submit_tool_outputs(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
When a run has the `status: "requires_action"` and `required_action.type` is
|
||
|
|
`submit_tool_outputs`, this endpoint can be used to submit the outputs from the
|
||
|
|
tool calls once they're all completed. All outputs must be submitted in a single
|
||
|
|
request.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tool_outputs: A list of tools for which the outputs are being submitted.
|
||
|
|
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def submit_tool_outputs(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
stream: Literal[True],
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Stream[AssistantStreamEvent]:
|
||
|
|
"""
|
||
|
|
When a run has the `status: "requires_action"` and `required_action.type` is
|
||
|
|
`submit_tool_outputs`, this endpoint can be used to submit the outputs from the
|
||
|
|
tool calls once they're all completed. All outputs must be submitted in a single
|
||
|
|
request.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
tool_outputs: A list of tools for which the outputs are being submitted.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def submit_tool_outputs(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
stream: bool,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run | Stream[AssistantStreamEvent]:
|
||
|
|
"""
|
||
|
|
When a run has the `status: "requires_action"` and `required_action.type` is
|
||
|
|
`submit_tool_outputs`, this endpoint can be used to submit the outputs from the
|
||
|
|
tool calls once they're all completed. All outputs must be submitted in a single
|
||
|
|
request.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
tool_outputs: A list of tools for which the outputs are being submitted.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@required_args(["thread_id", "tool_outputs"], ["thread_id", "stream", "tool_outputs"])
|
||
|
|
def submit_tool_outputs(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run | Stream[AssistantStreamEvent]:
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
if not run_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return self._post(
|
||
|
|
f"/threads/{thread_id}/runs/{run_id}/submit_tool_outputs",
|
||
|
|
body=maybe_transform(
|
||
|
|
{
|
||
|
|
"tool_outputs": tool_outputs,
|
||
|
|
"stream": stream,
|
||
|
|
},
|
||
|
|
run_submit_tool_outputs_params.RunSubmitToolOutputsParams,
|
||
|
|
),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
stream=stream or False,
|
||
|
|
stream_cls=Stream[AssistantStreamEvent],
|
||
|
|
)
|
||
|
|
|
||
|
|
def submit_tool_outputs_and_poll(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
run_id: str,
|
||
|
|
thread_id: str,
|
||
|
|
poll_interval_ms: int | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
A helper to submit a tool output to a run and poll for a terminal run state.
|
||
|
|
More information on Run lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
run = self.submit_tool_outputs(
|
||
|
|
run_id=run_id,
|
||
|
|
thread_id=thread_id,
|
||
|
|
tool_outputs=tool_outputs,
|
||
|
|
stream=False,
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
)
|
||
|
|
return self.poll(
|
||
|
|
run_id=run.id,
|
||
|
|
thread_id=thread_id,
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
poll_interval_ms=poll_interval_ms,
|
||
|
|
)
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def submit_tool_outputs_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
run_id: str,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AssistantStreamManager[AssistantEventHandler]:
|
||
|
|
"""
|
||
|
|
Submit the tool outputs from a previous run and stream the run to a terminal
|
||
|
|
state. More information on Run lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def submit_tool_outputs_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
run_id: str,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AssistantEventHandlerT,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AssistantStreamManager[AssistantEventHandlerT]:
|
||
|
|
"""
|
||
|
|
Submit the tool outputs from a previous run and stream the run to a terminal
|
||
|
|
state. More information on Run lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
def submit_tool_outputs_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
run_id: str,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AssistantEventHandlerT | None = None,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AssistantStreamManager[AssistantEventHandler] | AssistantStreamManager[AssistantEventHandlerT]:
|
||
|
|
"""
|
||
|
|
Submit the tool outputs from a previous run and stream the run to a terminal
|
||
|
|
state. More information on Run lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
if not run_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
|
||
|
|
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
|
||
|
|
extra_headers = {
|
||
|
|
"OpenAI-Beta": "assistants=v2",
|
||
|
|
"X-Stainless-Stream-Helper": "threads.runs.submit_tool_outputs_stream",
|
||
|
|
"X-Stainless-Custom-Event-Handler": "true" if event_handler else "false",
|
||
|
|
**(extra_headers or {}),
|
||
|
|
}
|
||
|
|
request = partial(
|
||
|
|
self._post,
|
||
|
|
f"/threads/{thread_id}/runs/{run_id}/submit_tool_outputs",
|
||
|
|
body=maybe_transform(
|
||
|
|
{
|
||
|
|
"tool_outputs": tool_outputs,
|
||
|
|
"stream": True,
|
||
|
|
},
|
||
|
|
run_submit_tool_outputs_params.RunSubmitToolOutputsParams,
|
||
|
|
),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
stream=True,
|
||
|
|
stream_cls=Stream[AssistantStreamEvent],
|
||
|
|
)
|
||
|
|
return AssistantStreamManager(request, event_handler=event_handler or AssistantEventHandler())
|
||
|
|
|
||
|
|
|
||
|
|
class AsyncRuns(AsyncAPIResource):
|
||
|
|
@cached_property
|
||
|
|
def steps(self) -> AsyncSteps:
|
||
|
|
return AsyncSteps(self._client)
|
||
|
|
|
||
|
|
@cached_property
|
||
|
|
def with_raw_response(self) -> AsyncRunsWithRawResponse:
|
||
|
|
"""
|
||
|
|
This property can be used as a prefix for any HTTP method call to return
|
||
|
|
the raw response object instead of the parsed content.
|
||
|
|
|
||
|
|
For more information, see https://www.github.com/openai/openai-python#accessing-raw-response-data-eg-headers
|
||
|
|
"""
|
||
|
|
return AsyncRunsWithRawResponse(self)
|
||
|
|
|
||
|
|
@cached_property
|
||
|
|
def with_streaming_response(self) -> AsyncRunsWithStreamingResponse:
|
||
|
|
"""
|
||
|
|
An alternative to `.with_raw_response` that doesn't eagerly read the response body.
|
||
|
|
|
||
|
|
For more information, see https://www.github.com/openai/openai-python#with_streaming_response
|
||
|
|
"""
|
||
|
|
return AsyncRunsWithStreamingResponse(self)
|
||
|
|
|
||
|
|
@overload
|
||
|
|
async def create(
|
||
|
|
self,
|
||
|
|
thread_id: str,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
Create a run.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
assistant_id: The ID of the
|
||
|
|
[assistant](https://platform.openai.com/docs/api-reference/assistants) to use to
|
||
|
|
execute this run.
|
||
|
|
|
||
|
|
include: A list of additional fields to include in the response. Currently the only
|
||
|
|
supported value is `step_details.tool_calls[*].file_search.results[*].content`
|
||
|
|
to fetch the file search result content.
|
||
|
|
|
||
|
|
See the
|
||
|
|
[file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
|
||
|
|
for more information.
|
||
|
|
|
||
|
|
additional_instructions: Appends additional instructions at the end of the instructions for the run. This
|
||
|
|
is useful for modifying the behavior on a per-run basis without overriding other
|
||
|
|
instructions.
|
||
|
|
|
||
|
|
additional_messages: Adds additional messages to the thread before creating the run.
|
||
|
|
|
||
|
|
instructions: Overrides the
|
||
|
|
[instructions](https://platform.openai.com/docs/api-reference/assistants/createAssistant)
|
||
|
|
of the assistant. This is useful for modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
max_completion_tokens: 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.
|
||
|
|
|
||
|
|
max_prompt_tokens: 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.
|
||
|
|
|
||
|
|
metadata: 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. Keys
|
||
|
|
can be a maximum of 64 characters long and values can be a maximum of 512
|
||
|
|
characters long.
|
||
|
|
|
||
|
|
model: The ID of the [Model](https://platform.openai.com/docs/api-reference/models) to
|
||
|
|
be used to execute this run. If a value is provided here, it will override the
|
||
|
|
model associated with the assistant. If not, the model associated with the
|
||
|
|
assistant will be used.
|
||
|
|
|
||
|
|
parallel_tool_calls: Whether to enable
|
||
|
|
[parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
|
||
|
|
during tool use.
|
||
|
|
|
||
|
|
response_format: Specifies the format that the model must output. Compatible with
|
||
|
|
[GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
|
||
|
|
[GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
|
||
|
|
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](https://platform.openai.com/docs/guides/structured-outputs).
|
||
|
|
|
||
|
|
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.
|
||
|
|
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
temperature: 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.
|
||
|
|
|
||
|
|
tool_choice: 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.
|
||
|
|
|
||
|
|
tools: Override the tools the assistant can use for this run. This is useful for
|
||
|
|
modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
top_p: 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.
|
||
|
|
|
||
|
|
truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
|
||
|
|
control the intial context window of the run.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
async def create(
|
||
|
|
self,
|
||
|
|
thread_id: str,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
stream: Literal[True],
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AsyncStream[AssistantStreamEvent]:
|
||
|
|
"""
|
||
|
|
Create a run.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
assistant_id: The ID of the
|
||
|
|
[assistant](https://platform.openai.com/docs/api-reference/assistants) to use to
|
||
|
|
execute this run.
|
||
|
|
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
include: A list of additional fields to include in the response. Currently the only
|
||
|
|
supported value is `step_details.tool_calls[*].file_search.results[*].content`
|
||
|
|
to fetch the file search result content.
|
||
|
|
|
||
|
|
See the
|
||
|
|
[file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
|
||
|
|
for more information.
|
||
|
|
|
||
|
|
additional_instructions: Appends additional instructions at the end of the instructions for the run. This
|
||
|
|
is useful for modifying the behavior on a per-run basis without overriding other
|
||
|
|
instructions.
|
||
|
|
|
||
|
|
additional_messages: Adds additional messages to the thread before creating the run.
|
||
|
|
|
||
|
|
instructions: Overrides the
|
||
|
|
[instructions](https://platform.openai.com/docs/api-reference/assistants/createAssistant)
|
||
|
|
of the assistant. This is useful for modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
max_completion_tokens: 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.
|
||
|
|
|
||
|
|
max_prompt_tokens: 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.
|
||
|
|
|
||
|
|
metadata: 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. Keys
|
||
|
|
can be a maximum of 64 characters long and values can be a maximum of 512
|
||
|
|
characters long.
|
||
|
|
|
||
|
|
model: The ID of the [Model](https://platform.openai.com/docs/api-reference/models) to
|
||
|
|
be used to execute this run. If a value is provided here, it will override the
|
||
|
|
model associated with the assistant. If not, the model associated with the
|
||
|
|
assistant will be used.
|
||
|
|
|
||
|
|
parallel_tool_calls: Whether to enable
|
||
|
|
[parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
|
||
|
|
during tool use.
|
||
|
|
|
||
|
|
response_format: Specifies the format that the model must output. Compatible with
|
||
|
|
[GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
|
||
|
|
[GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
|
||
|
|
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](https://platform.openai.com/docs/guides/structured-outputs).
|
||
|
|
|
||
|
|
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.
|
||
|
|
|
||
|
|
temperature: 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.
|
||
|
|
|
||
|
|
tool_choice: 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.
|
||
|
|
|
||
|
|
tools: Override the tools the assistant can use for this run. This is useful for
|
||
|
|
modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
top_p: 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.
|
||
|
|
|
||
|
|
truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
|
||
|
|
control the intial context window of the run.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
async def create(
|
||
|
|
self,
|
||
|
|
thread_id: str,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
stream: bool,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run | AsyncStream[AssistantStreamEvent]:
|
||
|
|
"""
|
||
|
|
Create a run.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
assistant_id: The ID of the
|
||
|
|
[assistant](https://platform.openai.com/docs/api-reference/assistants) to use to
|
||
|
|
execute this run.
|
||
|
|
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
include: A list of additional fields to include in the response. Currently the only
|
||
|
|
supported value is `step_details.tool_calls[*].file_search.results[*].content`
|
||
|
|
to fetch the file search result content.
|
||
|
|
|
||
|
|
See the
|
||
|
|
[file search tool documentation](https://platform.openai.com/docs/assistants/tools/file-search#customizing-file-search-settings)
|
||
|
|
for more information.
|
||
|
|
|
||
|
|
additional_instructions: Appends additional instructions at the end of the instructions for the run. This
|
||
|
|
is useful for modifying the behavior on a per-run basis without overriding other
|
||
|
|
instructions.
|
||
|
|
|
||
|
|
additional_messages: Adds additional messages to the thread before creating the run.
|
||
|
|
|
||
|
|
instructions: Overrides the
|
||
|
|
[instructions](https://platform.openai.com/docs/api-reference/assistants/createAssistant)
|
||
|
|
of the assistant. This is useful for modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
max_completion_tokens: 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.
|
||
|
|
|
||
|
|
max_prompt_tokens: 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.
|
||
|
|
|
||
|
|
metadata: 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. Keys
|
||
|
|
can be a maximum of 64 characters long and values can be a maximum of 512
|
||
|
|
characters long.
|
||
|
|
|
||
|
|
model: The ID of the [Model](https://platform.openai.com/docs/api-reference/models) to
|
||
|
|
be used to execute this run. If a value is provided here, it will override the
|
||
|
|
model associated with the assistant. If not, the model associated with the
|
||
|
|
assistant will be used.
|
||
|
|
|
||
|
|
parallel_tool_calls: Whether to enable
|
||
|
|
[parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
|
||
|
|
during tool use.
|
||
|
|
|
||
|
|
response_format: Specifies the format that the model must output. Compatible with
|
||
|
|
[GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
|
||
|
|
[GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
|
||
|
|
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](https://platform.openai.com/docs/guides/structured-outputs).
|
||
|
|
|
||
|
|
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.
|
||
|
|
|
||
|
|
temperature: 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.
|
||
|
|
|
||
|
|
tool_choice: 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.
|
||
|
|
|
||
|
|
tools: Override the tools the assistant can use for this run. This is useful for
|
||
|
|
modifying the behavior on a per-run basis.
|
||
|
|
|
||
|
|
top_p: 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.
|
||
|
|
|
||
|
|
truncation_strategy: Controls for how a thread will be truncated prior to the run. Use this to
|
||
|
|
control the intial context window of the run.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@required_args(["assistant_id"], ["assistant_id", "stream"])
|
||
|
|
async def create(
|
||
|
|
self,
|
||
|
|
thread_id: str,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run | AsyncStream[AssistantStreamEvent]:
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return await self._post(
|
||
|
|
f"/threads/{thread_id}/runs",
|
||
|
|
body=await async_maybe_transform(
|
||
|
|
{
|
||
|
|
"assistant_id": assistant_id,
|
||
|
|
"additional_instructions": additional_instructions,
|
||
|
|
"additional_messages": additional_messages,
|
||
|
|
"instructions": instructions,
|
||
|
|
"max_completion_tokens": max_completion_tokens,
|
||
|
|
"max_prompt_tokens": max_prompt_tokens,
|
||
|
|
"metadata": metadata,
|
||
|
|
"model": model,
|
||
|
|
"parallel_tool_calls": parallel_tool_calls,
|
||
|
|
"response_format": response_format,
|
||
|
|
"stream": stream,
|
||
|
|
"temperature": temperature,
|
||
|
|
"tool_choice": tool_choice,
|
||
|
|
"tools": tools,
|
||
|
|
"top_p": top_p,
|
||
|
|
"truncation_strategy": truncation_strategy,
|
||
|
|
},
|
||
|
|
run_create_params.RunCreateParams,
|
||
|
|
),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
query=await async_maybe_transform({"include": include}, run_create_params.RunCreateParams),
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
stream=stream or False,
|
||
|
|
stream_cls=AsyncStream[AssistantStreamEvent],
|
||
|
|
)
|
||
|
|
|
||
|
|
async def retrieve(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
Retrieves a run.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
if not run_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return await self._get(
|
||
|
|
f"/threads/{thread_id}/runs/{run_id}",
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
)
|
||
|
|
|
||
|
|
async def update(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
Modifies a run.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
metadata: 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. Keys
|
||
|
|
can be a maximum of 64 characters long and values can be a maximum of 512
|
||
|
|
characters long.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
if not run_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return await self._post(
|
||
|
|
f"/threads/{thread_id}/runs/{run_id}",
|
||
|
|
body=await async_maybe_transform({"metadata": metadata}, run_update_params.RunUpdateParams),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
)
|
||
|
|
|
||
|
|
def list(
|
||
|
|
self,
|
||
|
|
thread_id: str,
|
||
|
|
*,
|
||
|
|
after: str | NotGiven = NOT_GIVEN,
|
||
|
|
before: str | NotGiven = NOT_GIVEN,
|
||
|
|
limit: int | NotGiven = NOT_GIVEN,
|
||
|
|
order: Literal["asc", "desc"] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AsyncPaginator[Run, AsyncCursorPage[Run]]:
|
||
|
|
"""
|
||
|
|
Returns a list of runs belonging to a thread.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
after: A cursor for use in pagination. `after` is an object ID that defines your place
|
||
|
|
in the list. For instance, if you make a list request and receive 100 objects,
|
||
|
|
ending with obj_foo, your subsequent call can include after=obj_foo in order to
|
||
|
|
fetch the next page of the list.
|
||
|
|
|
||
|
|
before: A cursor for use in pagination. `before` is an object ID that defines your place
|
||
|
|
in the list. For instance, if you make a list request and receive 100 objects,
|
||
|
|
starting with obj_foo, your subsequent call can include before=obj_foo in order
|
||
|
|
to fetch the previous page of the list.
|
||
|
|
|
||
|
|
limit: A limit on the number of objects to be returned. Limit can range between 1 and
|
||
|
|
100, and the default is 20.
|
||
|
|
|
||
|
|
order: Sort order by the `created_at` timestamp of the objects. `asc` for ascending
|
||
|
|
order and `desc` for descending order.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return self._get_api_list(
|
||
|
|
f"/threads/{thread_id}/runs",
|
||
|
|
page=AsyncCursorPage[Run],
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
query=maybe_transform(
|
||
|
|
{
|
||
|
|
"after": after,
|
||
|
|
"before": before,
|
||
|
|
"limit": limit,
|
||
|
|
"order": order,
|
||
|
|
},
|
||
|
|
run_list_params.RunListParams,
|
||
|
|
),
|
||
|
|
),
|
||
|
|
model=Run,
|
||
|
|
)
|
||
|
|
|
||
|
|
async def cancel(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
Cancels a run that is `in_progress`.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
if not run_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return await self._post(
|
||
|
|
f"/threads/{thread_id}/runs/{run_id}/cancel",
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
)
|
||
|
|
|
||
|
|
async def create_and_poll(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
poll_interval_ms: int | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
A helper to create a run an poll for a terminal state. More information on Run
|
||
|
|
lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
run = await self.create(
|
||
|
|
thread_id=thread_id,
|
||
|
|
assistant_id=assistant_id,
|
||
|
|
include=include,
|
||
|
|
additional_instructions=additional_instructions,
|
||
|
|
additional_messages=additional_messages,
|
||
|
|
instructions=instructions,
|
||
|
|
max_completion_tokens=max_completion_tokens,
|
||
|
|
max_prompt_tokens=max_prompt_tokens,
|
||
|
|
metadata=metadata,
|
||
|
|
model=model,
|
||
|
|
response_format=response_format,
|
||
|
|
temperature=temperature,
|
||
|
|
tool_choice=tool_choice,
|
||
|
|
parallel_tool_calls=parallel_tool_calls,
|
||
|
|
# We assume we are not streaming when polling
|
||
|
|
stream=False,
|
||
|
|
tools=tools,
|
||
|
|
truncation_strategy=truncation_strategy,
|
||
|
|
top_p=top_p,
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
)
|
||
|
|
return await self.poll(
|
||
|
|
run.id,
|
||
|
|
thread_id=thread_id,
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
poll_interval_ms=poll_interval_ms,
|
||
|
|
timeout=timeout,
|
||
|
|
)
|
||
|
|
|
||
|
|
@overload
|
||
|
|
@typing_extensions.deprecated("use `stream` instead")
|
||
|
|
def create_and_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AsyncAssistantStreamManager[AsyncAssistantEventHandler]:
|
||
|
|
"""Create a Run stream"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
@typing_extensions.deprecated("use `stream` instead")
|
||
|
|
def create_and_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AsyncAssistantEventHandlerT,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AsyncAssistantStreamManager[AsyncAssistantEventHandlerT]:
|
||
|
|
"""Create a Run stream"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@typing_extensions.deprecated("use `stream` instead")
|
||
|
|
def create_and_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AsyncAssistantEventHandlerT | None = None,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> (
|
||
|
|
AsyncAssistantStreamManager[AsyncAssistantEventHandler]
|
||
|
|
| AsyncAssistantStreamManager[AsyncAssistantEventHandlerT]
|
||
|
|
):
|
||
|
|
"""Create a Run stream"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
|
||
|
|
extra_headers = {
|
||
|
|
"OpenAI-Beta": "assistants=v2",
|
||
|
|
"X-Stainless-Stream-Helper": "threads.runs.create_and_stream",
|
||
|
|
"X-Stainless-Custom-Event-Handler": "true" if event_handler else "false",
|
||
|
|
**(extra_headers or {}),
|
||
|
|
}
|
||
|
|
request = self._post(
|
||
|
|
f"/threads/{thread_id}/runs",
|
||
|
|
body=maybe_transform(
|
||
|
|
{
|
||
|
|
"assistant_id": assistant_id,
|
||
|
|
"additional_instructions": additional_instructions,
|
||
|
|
"additional_messages": additional_messages,
|
||
|
|
"instructions": instructions,
|
||
|
|
"max_completion_tokens": max_completion_tokens,
|
||
|
|
"max_prompt_tokens": max_prompt_tokens,
|
||
|
|
"metadata": metadata,
|
||
|
|
"model": model,
|
||
|
|
"response_format": response_format,
|
||
|
|
"temperature": temperature,
|
||
|
|
"tool_choice": tool_choice,
|
||
|
|
"stream": True,
|
||
|
|
"tools": tools,
|
||
|
|
"truncation_strategy": truncation_strategy,
|
||
|
|
"top_p": top_p,
|
||
|
|
"parallel_tool_calls": parallel_tool_calls,
|
||
|
|
},
|
||
|
|
run_create_params.RunCreateParams,
|
||
|
|
),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
stream=True,
|
||
|
|
stream_cls=AsyncStream[AssistantStreamEvent],
|
||
|
|
)
|
||
|
|
return AsyncAssistantStreamManager(request, event_handler=event_handler or AsyncAssistantEventHandler())
|
||
|
|
|
||
|
|
async def poll(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
thread_id: str,
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
poll_interval_ms: int | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
A helper to poll a run status until it reaches a terminal state. More
|
||
|
|
information on Run lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
extra_headers = {"X-Stainless-Poll-Helper": "true", **(extra_headers or {})}
|
||
|
|
|
||
|
|
if is_given(poll_interval_ms):
|
||
|
|
extra_headers["X-Stainless-Custom-Poll-Interval"] = str(poll_interval_ms)
|
||
|
|
|
||
|
|
terminal_states = {"requires_action", "cancelled", "completed", "failed", "expired", "incomplete"}
|
||
|
|
while True:
|
||
|
|
response = await self.with_raw_response.retrieve(
|
||
|
|
thread_id=thread_id,
|
||
|
|
run_id=run_id,
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_body=extra_body,
|
||
|
|
extra_query=extra_query,
|
||
|
|
timeout=timeout,
|
||
|
|
)
|
||
|
|
|
||
|
|
run = response.parse()
|
||
|
|
# Return if we reached a terminal state
|
||
|
|
if run.status in terminal_states:
|
||
|
|
return run
|
||
|
|
|
||
|
|
if not is_given(poll_interval_ms):
|
||
|
|
from_header = response.headers.get("openai-poll-after-ms")
|
||
|
|
if from_header is not None:
|
||
|
|
poll_interval_ms = int(from_header)
|
||
|
|
else:
|
||
|
|
poll_interval_ms = 1000
|
||
|
|
|
||
|
|
await self._sleep(poll_interval_ms / 1000)
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AsyncAssistantStreamManager[AsyncAssistantEventHandler]:
|
||
|
|
"""Create a Run stream"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AsyncAssistantEventHandlerT,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AsyncAssistantStreamManager[AsyncAssistantEventHandlerT]:
|
||
|
|
"""Create a Run stream"""
|
||
|
|
...
|
||
|
|
|
||
|
|
def stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
assistant_id: str,
|
||
|
|
include: List[RunStepInclude] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
additional_messages: Optional[Iterable[run_create_params.AdditionalMessage]] | NotGiven = NOT_GIVEN,
|
||
|
|
instructions: Optional[str] | NotGiven = NOT_GIVEN,
|
||
|
|
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
max_prompt_tokens: Optional[int] | NotGiven = NOT_GIVEN,
|
||
|
|
metadata: Optional[object] | NotGiven = NOT_GIVEN,
|
||
|
|
model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
|
||
|
|
parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
|
||
|
|
response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
temperature: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
|
||
|
|
tools: Optional[Iterable[AssistantToolParam]] | NotGiven = NOT_GIVEN,
|
||
|
|
top_p: Optional[float] | NotGiven = NOT_GIVEN,
|
||
|
|
truncation_strategy: Optional[run_create_params.TruncationStrategy] | NotGiven = NOT_GIVEN,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AsyncAssistantEventHandlerT | None = None,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> (
|
||
|
|
AsyncAssistantStreamManager[AsyncAssistantEventHandler]
|
||
|
|
| AsyncAssistantStreamManager[AsyncAssistantEventHandlerT]
|
||
|
|
):
|
||
|
|
"""Create a Run stream"""
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
|
||
|
|
extra_headers = {
|
||
|
|
"OpenAI-Beta": "assistants=v2",
|
||
|
|
"X-Stainless-Stream-Helper": "threads.runs.create_and_stream",
|
||
|
|
"X-Stainless-Custom-Event-Handler": "true" if event_handler else "false",
|
||
|
|
**(extra_headers or {}),
|
||
|
|
}
|
||
|
|
request = self._post(
|
||
|
|
f"/threads/{thread_id}/runs",
|
||
|
|
body=maybe_transform(
|
||
|
|
{
|
||
|
|
"assistant_id": assistant_id,
|
||
|
|
"additional_instructions": additional_instructions,
|
||
|
|
"additional_messages": additional_messages,
|
||
|
|
"instructions": instructions,
|
||
|
|
"max_completion_tokens": max_completion_tokens,
|
||
|
|
"max_prompt_tokens": max_prompt_tokens,
|
||
|
|
"metadata": metadata,
|
||
|
|
"model": model,
|
||
|
|
"response_format": response_format,
|
||
|
|
"temperature": temperature,
|
||
|
|
"tool_choice": tool_choice,
|
||
|
|
"stream": True,
|
||
|
|
"tools": tools,
|
||
|
|
"parallel_tool_calls": parallel_tool_calls,
|
||
|
|
"truncation_strategy": truncation_strategy,
|
||
|
|
"top_p": top_p,
|
||
|
|
},
|
||
|
|
run_create_params.RunCreateParams,
|
||
|
|
),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
query=maybe_transform({"include": include}, run_create_params.RunCreateParams),
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
stream=True,
|
||
|
|
stream_cls=AsyncStream[AssistantStreamEvent],
|
||
|
|
)
|
||
|
|
return AsyncAssistantStreamManager(request, event_handler=event_handler or AsyncAssistantEventHandler())
|
||
|
|
|
||
|
|
@overload
|
||
|
|
async def submit_tool_outputs(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
When a run has the `status: "requires_action"` and `required_action.type` is
|
||
|
|
`submit_tool_outputs`, this endpoint can be used to submit the outputs from the
|
||
|
|
tool calls once they're all completed. All outputs must be submitted in a single
|
||
|
|
request.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tool_outputs: A list of tools for which the outputs are being submitted.
|
||
|
|
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
async def submit_tool_outputs(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
stream: Literal[True],
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AsyncStream[AssistantStreamEvent]:
|
||
|
|
"""
|
||
|
|
When a run has the `status: "requires_action"` and `required_action.type` is
|
||
|
|
`submit_tool_outputs`, this endpoint can be used to submit the outputs from the
|
||
|
|
tool calls once they're all completed. All outputs must be submitted in a single
|
||
|
|
request.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
tool_outputs: A list of tools for which the outputs are being submitted.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
async def submit_tool_outputs(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
stream: bool,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run | AsyncStream[AssistantStreamEvent]:
|
||
|
|
"""
|
||
|
|
When a run has the `status: "requires_action"` and `required_action.type` is
|
||
|
|
`submit_tool_outputs`, this endpoint can be used to submit the outputs from the
|
||
|
|
tool calls once they're all completed. All outputs must be submitted in a single
|
||
|
|
request.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
stream: 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.
|
||
|
|
|
||
|
|
tool_outputs: A list of tools for which the outputs are being submitted.
|
||
|
|
|
||
|
|
extra_headers: Send extra headers
|
||
|
|
|
||
|
|
extra_query: Add additional query parameters to the request
|
||
|
|
|
||
|
|
extra_body: Add additional JSON properties to the request
|
||
|
|
|
||
|
|
timeout: Override the client-level default timeout for this request, in seconds
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@required_args(["thread_id", "tool_outputs"], ["thread_id", "stream", "tool_outputs"])
|
||
|
|
async def submit_tool_outputs(
|
||
|
|
self,
|
||
|
|
run_id: str,
|
||
|
|
*,
|
||
|
|
thread_id: str,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run | AsyncStream[AssistantStreamEvent]:
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
if not run_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
|
||
|
|
extra_headers = {"OpenAI-Beta": "assistants=v2", **(extra_headers or {})}
|
||
|
|
return await self._post(
|
||
|
|
f"/threads/{thread_id}/runs/{run_id}/submit_tool_outputs",
|
||
|
|
body=await async_maybe_transform(
|
||
|
|
{
|
||
|
|
"tool_outputs": tool_outputs,
|
||
|
|
"stream": stream,
|
||
|
|
},
|
||
|
|
run_submit_tool_outputs_params.RunSubmitToolOutputsParams,
|
||
|
|
),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
stream=stream or False,
|
||
|
|
stream_cls=AsyncStream[AssistantStreamEvent],
|
||
|
|
)
|
||
|
|
|
||
|
|
async def submit_tool_outputs_and_poll(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
run_id: str,
|
||
|
|
thread_id: str,
|
||
|
|
poll_interval_ms: int | NotGiven = NOT_GIVEN,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> Run:
|
||
|
|
"""
|
||
|
|
A helper to submit a tool output to a run and poll for a terminal run state.
|
||
|
|
More information on Run lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
run = await self.submit_tool_outputs(
|
||
|
|
run_id=run_id,
|
||
|
|
thread_id=thread_id,
|
||
|
|
tool_outputs=tool_outputs,
|
||
|
|
stream=False,
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
)
|
||
|
|
return await self.poll(
|
||
|
|
run_id=run.id,
|
||
|
|
thread_id=thread_id,
|
||
|
|
extra_headers=extra_headers,
|
||
|
|
extra_query=extra_query,
|
||
|
|
extra_body=extra_body,
|
||
|
|
timeout=timeout,
|
||
|
|
poll_interval_ms=poll_interval_ms,
|
||
|
|
)
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def submit_tool_outputs_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
run_id: str,
|
||
|
|
thread_id: str,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AsyncAssistantStreamManager[AsyncAssistantEventHandler]:
|
||
|
|
"""
|
||
|
|
Submit the tool outputs from a previous run and stream the run to a terminal
|
||
|
|
state. More information on Run lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
@overload
|
||
|
|
def submit_tool_outputs_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
run_id: str,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AsyncAssistantEventHandlerT,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> AsyncAssistantStreamManager[AsyncAssistantEventHandlerT]:
|
||
|
|
"""
|
||
|
|
Submit the tool outputs from a previous run and stream the run to a terminal
|
||
|
|
state. More information on Run lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
...
|
||
|
|
|
||
|
|
def submit_tool_outputs_stream(
|
||
|
|
self,
|
||
|
|
*,
|
||
|
|
tool_outputs: Iterable[run_submit_tool_outputs_params.ToolOutput],
|
||
|
|
run_id: str,
|
||
|
|
thread_id: str,
|
||
|
|
event_handler: AsyncAssistantEventHandlerT | None = None,
|
||
|
|
# Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
|
||
|
|
# The extra values given here take precedence over values defined on the client or passed to this method.
|
||
|
|
extra_headers: Headers | None = None,
|
||
|
|
extra_query: Query | None = None,
|
||
|
|
extra_body: Body | None = None,
|
||
|
|
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
|
||
|
|
) -> (
|
||
|
|
AsyncAssistantStreamManager[AsyncAssistantEventHandler]
|
||
|
|
| AsyncAssistantStreamManager[AsyncAssistantEventHandlerT]
|
||
|
|
):
|
||
|
|
"""
|
||
|
|
Submit the tool outputs from a previous run and stream the run to a terminal
|
||
|
|
state. More information on Run lifecycles can be found here:
|
||
|
|
https://platform.openai.com/docs/assistants/how-it-works/runs-and-run-steps
|
||
|
|
"""
|
||
|
|
if not run_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `run_id` but received {run_id!r}")
|
||
|
|
|
||
|
|
if not thread_id:
|
||
|
|
raise ValueError(f"Expected a non-empty value for `thread_id` but received {thread_id!r}")
|
||
|
|
|
||
|
|
extra_headers = {
|
||
|
|
"OpenAI-Beta": "assistants=v2",
|
||
|
|
"X-Stainless-Stream-Helper": "threads.runs.submit_tool_outputs_stream",
|
||
|
|
"X-Stainless-Custom-Event-Handler": "true" if event_handler else "false",
|
||
|
|
**(extra_headers or {}),
|
||
|
|
}
|
||
|
|
request = self._post(
|
||
|
|
f"/threads/{thread_id}/runs/{run_id}/submit_tool_outputs",
|
||
|
|
body=maybe_transform(
|
||
|
|
{
|
||
|
|
"tool_outputs": tool_outputs,
|
||
|
|
"stream": True,
|
||
|
|
},
|
||
|
|
run_submit_tool_outputs_params.RunSubmitToolOutputsParams,
|
||
|
|
),
|
||
|
|
options=make_request_options(
|
||
|
|
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
|
||
|
|
),
|
||
|
|
cast_to=Run,
|
||
|
|
stream=True,
|
||
|
|
stream_cls=AsyncStream[AssistantStreamEvent],
|
||
|
|
)
|
||
|
|
return AsyncAssistantStreamManager(request, event_handler=event_handler or AsyncAssistantEventHandler())
|
||
|
|
|
||
|
|
|
||
|
|
class RunsWithRawResponse:
|
||
|
|
def __init__(self, runs: Runs) -> None:
|
||
|
|
self._runs = runs
|
||
|
|
|
||
|
|
self.create = _legacy_response.to_raw_response_wrapper(
|
||
|
|
runs.create,
|
||
|
|
)
|
||
|
|
self.retrieve = _legacy_response.to_raw_response_wrapper(
|
||
|
|
runs.retrieve,
|
||
|
|
)
|
||
|
|
self.update = _legacy_response.to_raw_response_wrapper(
|
||
|
|
runs.update,
|
||
|
|
)
|
||
|
|
self.list = _legacy_response.to_raw_response_wrapper(
|
||
|
|
runs.list,
|
||
|
|
)
|
||
|
|
self.cancel = _legacy_response.to_raw_response_wrapper(
|
||
|
|
runs.cancel,
|
||
|
|
)
|
||
|
|
self.submit_tool_outputs = _legacy_response.to_raw_response_wrapper(
|
||
|
|
runs.submit_tool_outputs,
|
||
|
|
)
|
||
|
|
|
||
|
|
@cached_property
|
||
|
|
def steps(self) -> StepsWithRawResponse:
|
||
|
|
return StepsWithRawResponse(self._runs.steps)
|
||
|
|
|
||
|
|
|
||
|
|
class AsyncRunsWithRawResponse:
|
||
|
|
def __init__(self, runs: AsyncRuns) -> None:
|
||
|
|
self._runs = runs
|
||
|
|
|
||
|
|
self.create = _legacy_response.async_to_raw_response_wrapper(
|
||
|
|
runs.create,
|
||
|
|
)
|
||
|
|
self.retrieve = _legacy_response.async_to_raw_response_wrapper(
|
||
|
|
runs.retrieve,
|
||
|
|
)
|
||
|
|
self.update = _legacy_response.async_to_raw_response_wrapper(
|
||
|
|
runs.update,
|
||
|
|
)
|
||
|
|
self.list = _legacy_response.async_to_raw_response_wrapper(
|
||
|
|
runs.list,
|
||
|
|
)
|
||
|
|
self.cancel = _legacy_response.async_to_raw_response_wrapper(
|
||
|
|
runs.cancel,
|
||
|
|
)
|
||
|
|
self.submit_tool_outputs = _legacy_response.async_to_raw_response_wrapper(
|
||
|
|
runs.submit_tool_outputs,
|
||
|
|
)
|
||
|
|
|
||
|
|
@cached_property
|
||
|
|
def steps(self) -> AsyncStepsWithRawResponse:
|
||
|
|
return AsyncStepsWithRawResponse(self._runs.steps)
|
||
|
|
|
||
|
|
|
||
|
|
class RunsWithStreamingResponse:
|
||
|
|
def __init__(self, runs: Runs) -> None:
|
||
|
|
self._runs = runs
|
||
|
|
|
||
|
|
self.create = to_streamed_response_wrapper(
|
||
|
|
runs.create,
|
||
|
|
)
|
||
|
|
self.retrieve = to_streamed_response_wrapper(
|
||
|
|
runs.retrieve,
|
||
|
|
)
|
||
|
|
self.update = to_streamed_response_wrapper(
|
||
|
|
runs.update,
|
||
|
|
)
|
||
|
|
self.list = to_streamed_response_wrapper(
|
||
|
|
runs.list,
|
||
|
|
)
|
||
|
|
self.cancel = to_streamed_response_wrapper(
|
||
|
|
runs.cancel,
|
||
|
|
)
|
||
|
|
self.submit_tool_outputs = to_streamed_response_wrapper(
|
||
|
|
runs.submit_tool_outputs,
|
||
|
|
)
|
||
|
|
|
||
|
|
@cached_property
|
||
|
|
def steps(self) -> StepsWithStreamingResponse:
|
||
|
|
return StepsWithStreamingResponse(self._runs.steps)
|
||
|
|
|
||
|
|
|
||
|
|
class AsyncRunsWithStreamingResponse:
|
||
|
|
def __init__(self, runs: AsyncRuns) -> None:
|
||
|
|
self._runs = runs
|
||
|
|
|
||
|
|
self.create = async_to_streamed_response_wrapper(
|
||
|
|
runs.create,
|
||
|
|
)
|
||
|
|
self.retrieve = async_to_streamed_response_wrapper(
|
||
|
|
runs.retrieve,
|
||
|
|
)
|
||
|
|
self.update = async_to_streamed_response_wrapper(
|
||
|
|
runs.update,
|
||
|
|
)
|
||
|
|
self.list = async_to_streamed_response_wrapper(
|
||
|
|
runs.list,
|
||
|
|
)
|
||
|
|
self.cancel = async_to_streamed_response_wrapper(
|
||
|
|
runs.cancel,
|
||
|
|
)
|
||
|
|
self.submit_tool_outputs = async_to_streamed_response_wrapper(
|
||
|
|
runs.submit_tool_outputs,
|
||
|
|
)
|
||
|
|
|
||
|
|
@cached_property
|
||
|
|
def steps(self) -> AsyncStepsWithStreamingResponse:
|
||
|
|
return AsyncStepsWithStreamingResponse(self._runs.steps)
|