Iyeoluwads/email_alerts
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
adfb625ae9600ad38fdddc71f93df7c28d2e1fbe
email_alerts/venv/lib/python3.11/site-packages/groq/resources/chat/completions.py
T
Iyeoluwa Akinrinola adfb625ae9 Initial commit: Email alerts application
2025-07-25 11:31:36 +01:00

830 lines
44 KiB
Python
Raw Blame History

# File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
from __future__ import annotations
from typing import Dict, List, Union, Iterable, Optional, overload
from typing_extensions import Literal
import httpx
from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven
from ..._utils import maybe_transform, async_maybe_transform
from ..._compat import cached_property
from ..._resource import SyncAPIResource, AsyncAPIResource
from ..._response import (
to_raw_response_wrapper,
to_streamed_response_wrapper,
async_to_raw_response_wrapper,
async_to_streamed_response_wrapper,
)
from ..._streaming import Stream, AsyncStream
from ...types.chat import completion_create_params
from ..._base_client import make_request_options
from ...types.chat.chat_completion import ChatCompletion
from ...types.chat.chat_completion_chunk import ChatCompletionChunk
from ...types.chat.chat_completion_tool_param import ChatCompletionToolParam
from ...types.chat.chat_completion_message_param import ChatCompletionMessageParam
from ...types.chat.chat_completion_tool_choice_option_param import ChatCompletionToolChoiceOptionParam
__all__ = ["Completions", "AsyncCompletions"]
class Completions(SyncAPIResource):
@cached_property
def with_raw_response(self) -> CompletionsWithRawResponse:
"""
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/groq/groq-python#accessing-raw-response-data-eg-headers
"""
return CompletionsWithRawResponse(self)
@cached_property
def with_streaming_response(self) -> CompletionsWithStreamingResponse:
"""
An alternative to `.with_raw_response` that doesn't eagerly read the response body.
For more information, see https://www.github.com/groq/groq-python#with_streaming_response
"""
return CompletionsWithStreamingResponse(self)
@overload
def create(
self,
*,
messages: Iterable[ChatCompletionMessageParam],
model: str,
exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
store: Optional[bool] | NotGiven = NOT_GIVEN,
stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: Optional[str] | 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,
) -> ChatCompletion:
...
@overload
def create(
self,
*,
messages: Iterable[ChatCompletionMessageParam],
model: str,
exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
store: Optional[bool] | NotGiven = NOT_GIVEN,
stream: Literal[True],
temperature: Optional[float] | NotGiven = NOT_GIVEN,
tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: Optional[str] | 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[ChatCompletionChunk]:
...
@overload
def create(
self,
*,
messages: Iterable[ChatCompletionMessageParam],
model: str,
exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
store: Optional[bool] | NotGiven = NOT_GIVEN,
stream: bool,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: Optional[str] | 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,
) -> ChatCompletion | Stream[ChatCompletionChunk]:
...
def create(
self,
*,
messages: Iterable[ChatCompletionMessageParam],
model: Union[
str,
Literal[
"gemma2-9b-it",
"llama-3.3-70b-versatile",
"llama-3.1-8b-instant",
"llama-guard-3-8b",
"llama3-70b-8192",
"llama3-8b-8192",
],
],
exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
store: Optional[bool] | NotGiven = NOT_GIVEN,
stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: Optional[str] | 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,
) -> ChatCompletion | Stream[ChatCompletionChunk]:
"""
Creates a model response for the given chat conversation.
Args:
messages: A list of messages comprising the conversation so far.
model: ID of the model to use. For details on which models are compatible with the Chat
API, see available [models](https://console.groq.com/docs/models)
exclude_domains: Deprecated: Use search_settings.exclude_domains instead. A list of domains to
exclude from the search results when the model uses a web search tool.
frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
existing frequency in the text so far, decreasing the model's likelihood to
repeat the same line verbatim.
function_call: Deprecated in favor of `tool_choice`.
Controls which (if any) function is called by the model. `none` means the model
will not call a function and instead generates a message. `auto` means the model
can pick between generating a message or calling a function. Specifying a
particular function via `{"name": "my_function"}` forces the model to call that
function.
`none` is the default when no functions are present. `auto` is the default if
functions are present.
functions: Deprecated in favor of `tools`.
A list of functions the model may generate JSON inputs for.
include_domains: Deprecated: Use search_settings.include_domains instead. A list of domains to
include in the search results when the model uses a web search tool.
logit_bias: This is not yet supported by any of our models. Modify the likelihood of
specified tokens appearing in the completion.
logprobs: This is not yet supported by any of our models. Whether to return log
probabilities of the output tokens or not. If true, returns the log
probabilities of each output token returned in the `content` of `message`.
max_completion_tokens: The maximum number of tokens that can be generated in the chat completion. The
total length of input tokens and generated tokens is limited by the model's
context length.
max_tokens: Deprecated in favor of `max_completion_tokens`. The maximum number of tokens
that can be generated in the chat completion. The total length of input tokens
and generated tokens is limited by the model's context length.
metadata: This parameter is not currently supported.
n: How many chat completion choices to generate for each input message. Note that
the current moment, only n=1 is supported. Other values will result in a 400
response.
parallel_tool_calls: Whether to enable parallel function calling during tool use.
presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
whether they appear in the text so far, increasing the model's likelihood to
talk about new topics.
reasoning_effort: this field is only available for qwen3 models. Set to 'none' to disable
reasoning. Set to 'default' or null to let Qwen reason.
reasoning_format: Specifies how to output reasoning tokens
response_format: An object specifying the format that the model must output. Setting to
`{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs
which ensures the model will match your supplied JSON schema. json_schema
response format is only supported on llama 4 models. Setting to
`{ "type": "json_object" }` enables the older JSON mode, which ensures the
message the model generates is valid JSON. Using `json_schema` is preferred for
models that support it.
search_settings: Settings for web search functionality when the model uses a web search tool.
seed: If specified, our system will make a best effort to sample deterministically,
such that repeated requests with the same `seed` and parameters should return
the same result. Determinism is not guaranteed, and you should refer to the
`system_fingerprint` response parameter to monitor changes in the backend.
service_tier: The service tier to use for the request. Defaults to `on_demand`.
- `auto` will automatically select the highest tier available within the rate
limits of your organization.
- `flex` uses the flex tier, which will succeed or fail quickly.
stop: Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
store: This parameter is not currently supported.
stream: If set, partial message deltas will be sent. Tokens will be sent as data-only
[server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
as they become available, with the stream terminated by a `data: [DONE]`
message. [Example code](/docs/text-chat#streaming-a-chat-completion).
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. We generally recommend altering this or top_p but not
both.
tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
not call any tool and instead generates a message. `auto` means the model can
pick between generating a message or calling one or more tools. `required` means
the model must call one or more tools. Specifying a particular tool via
`{"type": "function", "function": {"name": "my_function"}}` forces the model to
call that tool.
`none` is the default when no tools are present. `auto` is the default if tools
are present.
tools: A list of tools the model may call. Currently, only functions are supported as a
tool. Use this to provide a list of functions the model may generate JSON inputs
for. A max of 128 functions are supported.
top_logprobs: This is not yet supported by any of our models. An integer between 0 and 20
specifying the number of most likely tokens to return at each token position,
each with an associated log probability. `logprobs` must be set to `true` if
this parameter is used.
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.
user: A unique identifier representing your end-user, which can help us monitor and
detect abuse.
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
"""
return self._post(
"/openai/v1/chat/completions",
body=maybe_transform(
{
"messages": messages,
"model": model,
"exclude_domains": exclude_domains,
"frequency_penalty": frequency_penalty,
"function_call": function_call,
"functions": functions,
"include_domains": include_domains,
"logit_bias": logit_bias,
"logprobs": logprobs,
"max_completion_tokens": max_completion_tokens,
"max_tokens": max_tokens,
"metadata": metadata,
"n": n,
"parallel_tool_calls": parallel_tool_calls,
"presence_penalty": presence_penalty,
"reasoning_effort": reasoning_effort,
"reasoning_format": reasoning_format,
"response_format": response_format,
"search_settings": search_settings,
"seed": seed,
"service_tier": service_tier,
"stop": stop,
"store": store,
"stream": stream,
"temperature": temperature,
"tool_choice": tool_choice,
"tools": tools,
"top_logprobs": top_logprobs,
"top_p": top_p,
"user": user,
},
completion_create_params.CompletionCreateParams,
),
options=make_request_options(
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
),
cast_to=ChatCompletion,
stream=stream or False,
stream_cls=Stream[ChatCompletionChunk],
)
class AsyncCompletions(AsyncAPIResource):
@cached_property
def with_raw_response(self) -> AsyncCompletionsWithRawResponse:
"""
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/groq/groq-python#accessing-raw-response-data-eg-headers
"""
return AsyncCompletionsWithRawResponse(self)
@cached_property
def with_streaming_response(self) -> AsyncCompletionsWithStreamingResponse:
"""
An alternative to `.with_raw_response` that doesn't eagerly read the response body.
For more information, see https://www.github.com/groq/groq-python#with_streaming_response
"""
return AsyncCompletionsWithStreamingResponse(self)
@overload
async def create(
self,
*,
messages: Iterable[ChatCompletionMessageParam],
model: str,
exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
store: Optional[bool] | NotGiven = NOT_GIVEN,
stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: Optional[str] | 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,
) -> ChatCompletion:
...
@overload
async def create(
self,
*,
messages: Iterable[ChatCompletionMessageParam],
model: str,
exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
store: Optional[bool] | NotGiven = NOT_GIVEN,
stream: Literal[True],
temperature: Optional[float] | NotGiven = NOT_GIVEN,
tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: Optional[str] | 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[ChatCompletionChunk]:
...
@overload
async def create(
self,
*,
messages: Iterable[ChatCompletionMessageParam],
model: str,
exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
store: Optional[bool] | NotGiven = NOT_GIVEN,
stream: bool,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: Optional[str] | 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,
) -> ChatCompletion | AsyncStream[ChatCompletionChunk]:
...
async def create(
self,
*,
messages: Iterable[ChatCompletionMessageParam],
model: Union[
str,
Literal[
"gemma2-9b-it",
"llama-3.3-70b-versatile",
"llama-3.1-8b-instant",
"llama-guard-3-8b",
"llama3-70b-8192",
"llama3-8b-8192",
],
],
exclude_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
frequency_penalty: Optional[float] | NotGiven = NOT_GIVEN,
function_call: Optional[completion_create_params.FunctionCall] | NotGiven = NOT_GIVEN,
functions: Optional[Iterable[completion_create_params.Function]] | NotGiven = NOT_GIVEN,
include_domains: Optional[List[str]] | NotGiven = NOT_GIVEN,
logit_bias: Optional[Dict[str, int]] | NotGiven = NOT_GIVEN,
logprobs: Optional[bool] | NotGiven = NOT_GIVEN,
max_completion_tokens: Optional[int] | NotGiven = NOT_GIVEN,
max_tokens: Optional[int] | NotGiven = NOT_GIVEN,
metadata: Optional[Dict[str, str]] | NotGiven = NOT_GIVEN,
n: Optional[int] | NotGiven = NOT_GIVEN,
parallel_tool_calls: Optional[bool] | NotGiven = NOT_GIVEN,
presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
reasoning_effort: Optional[Literal["none", "default"]] | NotGiven = NOT_GIVEN,
reasoning_format: Optional[Literal["hidden", "raw", "parsed"]] | NotGiven = NOT_GIVEN,
response_format: Optional[completion_create_params.ResponseFormat] | NotGiven = NOT_GIVEN,
search_settings: Optional[completion_create_params.SearchSettings] | NotGiven = NOT_GIVEN,
seed: Optional[int] | NotGiven = NOT_GIVEN,
service_tier: Optional[Literal["auto", "on_demand", "flex", "performance"]] | NotGiven = NOT_GIVEN,
stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
store: Optional[bool] | NotGiven = NOT_GIVEN,
stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
temperature: Optional[float] | NotGiven = NOT_GIVEN,
tool_choice: Optional[ChatCompletionToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
tools: Optional[Iterable[ChatCompletionToolParam]] | NotGiven = NOT_GIVEN,
top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
top_p: Optional[float] | NotGiven = NOT_GIVEN,
user: Optional[str] | 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,
) -> ChatCompletion | AsyncStream[ChatCompletionChunk]:
"""
Creates a model response for the given chat conversation.
Args:
messages: A list of messages comprising the conversation so far.
model: ID of the model to use. For details on which models are compatible with the Chat
API, see available [models](https://console.groq.com/docs/models)
exclude_domains: Deprecated: Use search_settings.exclude_domains instead. A list of domains to
exclude from the search results when the model uses a web search tool.
frequency_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on their
existing frequency in the text so far, decreasing the model's likelihood to
repeat the same line verbatim.
function_call: Deprecated in favor of `tool_choice`.
Controls which (if any) function is called by the model. `none` means the model
will not call a function and instead generates a message. `auto` means the model
can pick between generating a message or calling a function. Specifying a
particular function via `{"name": "my_function"}` forces the model to call that
function.
`none` is the default when no functions are present. `auto` is the default if
functions are present.
functions: Deprecated in favor of `tools`.
A list of functions the model may generate JSON inputs for.
include_domains: Deprecated: Use search_settings.include_domains instead. A list of domains to
include in the search results when the model uses a web search tool.
logit_bias: This is not yet supported by any of our models. Modify the likelihood of
specified tokens appearing in the completion.
logprobs: This is not yet supported by any of our models. Whether to return log
probabilities of the output tokens or not. If true, returns the log
probabilities of each output token returned in the `content` of `message`.
max_completion_tokens: The maximum number of tokens that can be generated in the chat completion. The
total length of input tokens and generated tokens is limited by the model's
context length.
max_tokens: Deprecated in favor of `max_completion_tokens`. The maximum number of tokens
that can be generated in the chat completion. The total length of input tokens
and generated tokens is limited by the model's context length.
metadata: This parameter is not currently supported.
n: How many chat completion choices to generate for each input message. Note that
the current moment, only n=1 is supported. Other values will result in a 400
response.
parallel_tool_calls: Whether to enable parallel function calling during tool use.
presence_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens based on
whether they appear in the text so far, increasing the model's likelihood to
talk about new topics.
reasoning_effort: this field is only available for qwen3 models. Set to 'none' to disable
reasoning. Set to 'default' or null to let Qwen reason.
reasoning_format: Specifies how to output reasoning tokens
response_format: An object specifying the format that the model must output. Setting to
`{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs
which ensures the model will match your supplied JSON schema. json_schema
response format is only supported on llama 4 models. Setting to
`{ "type": "json_object" }` enables the older JSON mode, which ensures the
message the model generates is valid JSON. Using `json_schema` is preferred for
models that support it.
search_settings: Settings for web search functionality when the model uses a web search tool.
seed: If specified, our system will make a best effort to sample deterministically,
such that repeated requests with the same `seed` and parameters should return
the same result. Determinism is not guaranteed, and you should refer to the
`system_fingerprint` response parameter to monitor changes in the backend.
service_tier: The service tier to use for the request. Defaults to `on_demand`.
- `auto` will automatically select the highest tier available within the rate
limits of your organization.
- `flex` uses the flex tier, which will succeed or fail quickly.
stop: Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
store: This parameter is not currently supported.
stream: If set, partial message deltas will be sent. Tokens will be sent as data-only
[server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format)
as they become available, with the stream terminated by a `data: [DONE]`
message. [Example code](/docs/text-chat#streaming-a-chat-completion).
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. We generally recommend altering this or top_p but not
both.
tool_choice: Controls which (if any) tool is called by the model. `none` means the model will
not call any tool and instead generates a message. `auto` means the model can
pick between generating a message or calling one or more tools. `required` means
the model must call one or more tools. Specifying a particular tool via
`{"type": "function", "function": {"name": "my_function"}}` forces the model to
call that tool.
`none` is the default when no tools are present. `auto` is the default if tools
are present.
tools: A list of tools the model may call. Currently, only functions are supported as a
tool. Use this to provide a list of functions the model may generate JSON inputs
for. A max of 128 functions are supported.
top_logprobs: This is not yet supported by any of our models. An integer between 0 and 20
specifying the number of most likely tokens to return at each token position,
each with an associated log probability. `logprobs` must be set to `true` if
this parameter is used.
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.
user: A unique identifier representing your end-user, which can help us monitor and
detect abuse.
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
"""
return await self._post(
"/openai/v1/chat/completions",
body=await async_maybe_transform(
{
"messages": messages,
"model": model,
"exclude_domains": exclude_domains,
"frequency_penalty": frequency_penalty,
"function_call": function_call,
"functions": functions,
"include_domains": include_domains,
"logit_bias": logit_bias,
"logprobs": logprobs,
"max_completion_tokens": max_completion_tokens,
"max_tokens": max_tokens,
"metadata": metadata,
"n": n,
"parallel_tool_calls": parallel_tool_calls,
"presence_penalty": presence_penalty,
"reasoning_effort": reasoning_effort,
"reasoning_format": reasoning_format,
"response_format": response_format,
"search_settings": search_settings,
"seed": seed,
"service_tier": service_tier,
"stop": stop,
"store": store,
"stream": stream,
"temperature": temperature,
"tool_choice": tool_choice,
"tools": tools,
"top_logprobs": top_logprobs,
"top_p": top_p,
"user": user,
},
completion_create_params.CompletionCreateParams,
),
options=make_request_options(
extra_headers=extra_headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
),
cast_to=ChatCompletion,
stream=stream or False,
stream_cls=AsyncStream[ChatCompletionChunk],
)
class CompletionsWithRawResponse:
def __init__(self, completions: Completions) -> None:
self._completions = completions
self.create = to_raw_response_wrapper(
completions.create,
)
class AsyncCompletionsWithRawResponse:
def __init__(self, completions: AsyncCompletions) -> None:
self._completions = completions
self.create = async_to_raw_response_wrapper(
completions.create,
)
class CompletionsWithStreamingResponse:
def __init__(self, completions: Completions) -> None:
self._completions = completions
self.create = to_streamed_response_wrapper(
completions.create,
)
class AsyncCompletionsWithStreamingResponse:
def __init__(self, completions: AsyncCompletions) -> None:
self._completions = completions
self.create = async_to_streamed_response_wrapper(
completions.create,
)
Reference in New Issue View Git Blame Copy Permalink