c63a5cfe-b235-4fbe-8bbb-82a9e02a482a-python 0.1.0a7__py3-none-any.whl → 0.1.0a9__py3-none-any.whl

gradientai/resources/chat/completions.py

@@ -3,11 +3,12 @@
 from __future__ import annotations
 
 from typing import Dict, List, Union, Iterable, Optional
+from typing_extensions import Literal, overload
 
 import httpx
 
 from ..._types import NOT_GIVEN, Body, Query, Headers, NotGiven
-from ..._utils import maybe_transform, async_maybe_transform
+from ..._utils import required_args, maybe_transform, async_maybe_transform
 from ..._compat import cached_property
 from ..._resource import SyncAPIResource, AsyncAPIResource
 from ..._response import (
@@ -16,8 +17,10 @@ from ..._response import (
     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_chunk import ChatCompletionChunk
 from ...types.chat.completion_create_response import CompletionCreateResponse
 
 __all__ = ["CompletionsResource", "AsyncCompletionsResource"]
@@ -43,6 +46,7 @@ class CompletionsResource(SyncAPIResource):
         """
         return CompletionsResourceWithStreamingResponse(self)
 
+    @overload
     def create(
         self,
         *,
@@ -57,7 +61,7 @@ class CompletionsResource(SyncAPIResource):
         n: Optional[int] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
-        stream: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
         stream_options: Optional[completion_create_params.StreamOptions] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
@@ -154,6 +158,263 @@ class CompletionsResource(SyncAPIResource):
           timeout: Override the client-level default timeout for this request, in seconds
         """
 
+        ...
+
+    @overload
+    def create(
+        self,
+        *,
+        messages: Iterable[completion_create_params.Message],
+        model: str,
+        stream: Literal[True],
+        frequency_penalty: Optional[float] | 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,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        stream_options: Optional[completion_create_params.StreamOptions] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: 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]:
+        """
+        Creates a model response for the given chat conversation.
+
+        Args:
+          messages: A list of messages comprising the conversation so far.
+
+          model: Model ID used to generate the response.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using server-sent events.
+
+          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.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: 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 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.
+
+          max_tokens: The maximum number of tokens that can be generated in the completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+
+          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, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          n: How many chat completion choices to generate for each input message. Note that
+              you will be charged based on the number of generated tokens across all of the
+              choices. Keep `n` as `1` to minimize costs.
+
+          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.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          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.
+
+          top_logprobs: 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 DigitalOcean to
+              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
+        """
+        ...
+
+    @overload
+    def create(
+        self,
+        *,
+        messages: Iterable[completion_create_params.Message],
+        model: str,
+        stream: bool,
+        frequency_penalty: Optional[float] | 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,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        stream_options: Optional[completion_create_params.StreamOptions] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: 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,
+    ) -> CompletionCreateResponse | Stream[ChatCompletionChunk]:
+        """
+        Creates a model response for the given chat conversation.
+
+        Args:
+          messages: A list of messages comprising the conversation so far.
+
+          model: Model ID used to generate the response.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using server-sent events.
+
+          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.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: 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 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.
+
+          max_tokens: The maximum number of tokens that can be generated in the completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+
+          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, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          n: How many chat completion choices to generate for each input message. Note that
+              you will be charged based on the number of generated tokens across all of the
+              choices. Keep `n` as `1` to minimize costs.
+
+          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.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          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.
+
+          top_logprobs: 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 DigitalOcean to
+              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
+        """
+        ...
+
+    @required_args(["messages", "model"], ["messages", "model", "stream"])
+    def create(
+        self,
+        *,
+        messages: Iterable[completion_create_params.Message],
+        model: str,
+        frequency_penalty: Optional[float] | 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,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
+        stream_options: Optional[completion_create_params.StreamOptions] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: 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,
+    ) -> CompletionCreateResponse | Stream[ChatCompletionChunk]:
+
         # This method requires an inference_key to be set via client argument or environment variable
         if not self._client.inference_key:
             raise TypeError(
@@ -186,12 +447,16 @@ class CompletionsResource(SyncAPIResource):
                     "top_p": top_p,
                     "user": user,
                 },
-                completion_create_params.CompletionCreateParams,
+                completion_create_params.CompletionCreateParamsStreaming
+                if stream
+                else completion_create_params.CompletionCreateParamsNonStreaming,
             ),
             options=make_request_options(
                 extra_headers=headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
             cast_to=CompletionCreateResponse,
+            stream=stream or False,
+            stream_cls=Stream[ChatCompletionChunk],
         )
 
 
@@ -215,6 +480,7 @@ class AsyncCompletionsResource(AsyncAPIResource):
         """
         return AsyncCompletionsResourceWithStreamingResponse(self)
 
+    @overload
     async def create(
         self,
         *,
@@ -229,7 +495,7 @@ class AsyncCompletionsResource(AsyncAPIResource):
         n: Optional[int] | NotGiven = NOT_GIVEN,
         presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
         stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
-        stream: Optional[bool] | NotGiven = NOT_GIVEN,
+        stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
         stream_options: Optional[completion_create_params.StreamOptions] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
@@ -326,6 +592,263 @@ class AsyncCompletionsResource(AsyncAPIResource):
           timeout: Override the client-level default timeout for this request, in seconds
         """
 
+        ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        messages: Iterable[completion_create_params.Message],
+        model: str,
+        stream: Literal[True],
+        frequency_penalty: Optional[float] | 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,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        stream_options: Optional[completion_create_params.StreamOptions] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: 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]:
+        """
+        Creates a model response for the given chat conversation.
+
+        Args:
+          messages: A list of messages comprising the conversation so far.
+
+          model: Model ID used to generate the response.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using server-sent events.
+
+          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.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: 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 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.
+
+          max_tokens: The maximum number of tokens that can be generated in the completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+
+          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, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          n: How many chat completion choices to generate for each input message. Note that
+              you will be charged based on the number of generated tokens across all of the
+              choices. Keep `n` as `1` to minimize costs.
+
+          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.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          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.
+
+          top_logprobs: 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 DigitalOcean to
+              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
+        """
+        ...
+
+    @overload
+    async def create(
+        self,
+        *,
+        messages: Iterable[completion_create_params.Message],
+        model: str,
+        stream: bool,
+        frequency_penalty: Optional[float] | 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,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        stream_options: Optional[completion_create_params.StreamOptions] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: 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,
+    ) -> CompletionCreateResponse | AsyncStream[ChatCompletionChunk]:
+        """
+        Creates a model response for the given chat conversation.
+
+        Args:
+          messages: A list of messages comprising the conversation so far.
+
+          model: Model ID used to generate the response.
+
+          stream: If set to true, the model response data will be streamed to the client as it is
+              generated using server-sent events.
+
+          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.
+
+          logit_bias: Modify the likelihood of specified tokens appearing in the completion.
+
+              Accepts a JSON object that maps tokens (specified by their token ID in the
+              tokenizer) to an associated bias value from -100 to 100. Mathematically, the
+              bias is added to the logits generated by the model prior to sampling. The exact
+              effect will vary per model, but values between -1 and 1 should decrease or
+              increase likelihood of selection; values like -100 or 100 should result in a ban
+              or exclusive selection of the relevant token.
+
+          logprobs: 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 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.
+
+          max_tokens: The maximum number of tokens that can be generated in the completion.
+
+              The token count of your prompt plus `max_tokens` cannot exceed the model's
+              context length.
+
+          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, and
+              querying for objects via API or the dashboard.
+
+              Keys are strings with a maximum length of 64 characters. Values are strings with
+              a maximum length of 512 characters.
+
+          n: How many chat completion choices to generate for each input message. Note that
+              you will be charged based on the number of generated tokens across all of the
+              choices. Keep `n` as `1` to minimize costs.
+
+          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.
+
+          stop: Up to 4 sequences where the API will stop generating further tokens. The
+              returned text will not contain the stop sequence.
+
+          stream_options: Options for streaming response. Only set this when you set `stream: true`.
+
+          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.
+
+          top_logprobs: 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 DigitalOcean to
+              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
+        """
+        ...
+
+    @required_args(["messages", "model"], ["messages", "model", "stream"])
+    async def create(
+        self,
+        *,
+        messages: Iterable[completion_create_params.Message],
+        model: str,
+        frequency_penalty: Optional[float] | 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,
+        presence_penalty: Optional[float] | NotGiven = NOT_GIVEN,
+        stop: Union[Optional[str], List[str], None] | NotGiven = NOT_GIVEN,
+        stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
+        stream_options: Optional[completion_create_params.StreamOptions] | NotGiven = NOT_GIVEN,
+        temperature: Optional[float] | NotGiven = NOT_GIVEN,
+        top_logprobs: Optional[int] | NotGiven = NOT_GIVEN,
+        top_p: Optional[float] | NotGiven = NOT_GIVEN,
+        user: 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,
+    ) -> CompletionCreateResponse | AsyncStream[ChatCompletionChunk]:
+
         # This method requires an inference_key to be set via client argument or environment variable
         if not hasattr(self._client, "inference_key") or not self._client.inference_key:
             raise TypeError(
@@ -358,12 +881,16 @@ class AsyncCompletionsResource(AsyncAPIResource):
                     "top_p": top_p,
                     "user": user,
                 },
-                completion_create_params.CompletionCreateParams,
+                completion_create_params.CompletionCreateParamsStreaming
+                if stream
+                else completion_create_params.CompletionCreateParamsNonStreaming,
             ),
             options=make_request_options(
                 extra_headers=headers, extra_query=extra_query, extra_body=extra_body, timeout=timeout
             ),
             cast_to=CompletionCreateResponse,
+            stream=stream or False,
+            stream_cls=AsyncStream[ChatCompletionChunk],
         )
 
 

gradientai/types/agents/chat/__init__.py

@@ -4,3 +4,4 @@ from __future__ import annotations
 
 from .completion_create_params import CompletionCreateParams as CompletionCreateParams
 from .completion_create_response import CompletionCreateResponse as CompletionCreateResponse
+from .agent_chat_completion_chunk import AgentChatCompletionChunk as AgentChatCompletionChunk