mirascope 2.0.0a1__py3-none-any.whl → 2.0.0a3__py3-none-any.whl

mirascope/llm/providers/openai/completions/provider.py

@@ -0,0 +1,456 @@
+"""OpenAI client implementation."""
+
+from collections.abc import Sequence
+from typing import Literal
+from typing_extensions import Unpack
+
+from openai import AsyncOpenAI, OpenAI
+
+from ....context import Context, DepsT
+from ....formatting import Format, FormattableT
+from ....messages import Message
+from ....responses import (
+    AsyncContextResponse,
+    AsyncContextStreamResponse,
+    AsyncResponse,
+    AsyncStreamResponse,
+    ContextResponse,
+    ContextStreamResponse,
+    Response,
+    StreamResponse,
+)
+from ....tools import (
+    AsyncContextTool,
+    AsyncContextToolkit,
+    AsyncTool,
+    AsyncToolkit,
+    ContextTool,
+    ContextToolkit,
+    Tool,
+    Toolkit,
+)
+from ...base import BaseProvider, Params
+from ..model_id import OpenAIModelId, model_name
+from . import _utils
+
+
+class OpenAICompletionsProvider(BaseProvider[OpenAI]):
+    """The client for the OpenAI LLM model."""
+
+    id = "openai:completions"
+    default_scope = "openai/"
+
+    def __init__(
+        self,
+        *,
+        api_key: str | None = None,
+        base_url: str | None = None,
+        wrapped_by_openai_provider: bool = False,
+    ) -> None:
+        """Initialize the OpenAI client."""
+        self.client = OpenAI(api_key=api_key, base_url=base_url)
+        self.async_client = AsyncOpenAI(api_key=api_key, base_url=base_url)
+        self.active_provider_id: Literal["openai", "openai:completions"] = (
+            "openai" if wrapped_by_openai_provider else "openai:completions"
+        )
+
+    def _call(
+        self,
+        *,
+        model_id: OpenAIModelId,
+        messages: Sequence[Message],
+        tools: Sequence[Tool] | Toolkit | None = None,
+        format: type[FormattableT] | Format[FormattableT] | None = None,
+        **params: Unpack[Params],
+    ) -> Response | Response[FormattableT]:
+        """Generate an `llm.Response` by synchronously calling the OpenAI ChatCompletions API.
+
+        Args:
+            model_id: Model identifier to use.
+            messages: Messages to send to the LLM.
+            tools: Optional tools that the model may invoke.
+            format: Optional response format specifier.
+            **params: Additional parameters to configure output (e.g. temperature). See `llm.Params`.
+
+        Returns:
+            An `llm.Response` object containing the LLM-generated content.
+        """
+        input_messages, format, kwargs = _utils.encode_request(
+            model_id=model_id,
+            messages=messages,
+            tools=tools,
+            format=format,
+            params=params,
+        )
+
+        openai_response = self.client.chat.completions.create(**kwargs)
+
+        assistant_message, finish_reason = _utils.decode_response(
+            openai_response, model_id, self.active_provider_id
+        )
+
+        return Response(
+            raw=openai_response,
+            provider_id=self.active_provider_id,
+            model_id=model_id,
+            provider_model_name=model_name(model_id, "completions"),
+            params=params,
+            tools=tools,
+            input_messages=input_messages,
+            assistant_message=assistant_message,
+            finish_reason=finish_reason,
+            format=format,
+        )
+
+    def _context_call(
+        self,
+        *,
+        ctx: Context[DepsT],
+        model_id: OpenAIModelId,
+        messages: Sequence[Message],
+        tools: Sequence[Tool | ContextTool[DepsT]]
+        | ContextToolkit[DepsT]
+        | None = None,
+        format: type[FormattableT] | Format[FormattableT] | None = None,
+        **params: Unpack[Params],
+    ) -> ContextResponse[DepsT, None] | ContextResponse[DepsT, FormattableT]:
+        """Generate an `llm.ContextResponse` by synchronously calling the OpenAI ChatCompletions API.
+
+        Args:
+            ctx: Context object with dependencies for tools.
+            model_id: Model identifier to use.
+            messages: Messages to send to the LLM.
+            tools: Optional tools that the model may invoke.
+            format: Optional response format specifier.
+            **params: Additional parameters to configure output (e.g. temperature). See `llm.Params`.
+
+        Returns:
+            An `llm.ContextResponse` object containing the LLM-generated content.
+        """
+        input_messages, format, kwargs = _utils.encode_request(
+            model_id=model_id,
+            messages=messages,
+            tools=tools,
+            format=format,
+            params=params,
+        )
+
+        openai_response = self.client.chat.completions.create(**kwargs)
+
+        assistant_message, finish_reason = _utils.decode_response(
+            openai_response, model_id, self.active_provider_id
+        )
+
+        return ContextResponse(
+            raw=openai_response,
+            provider_id=self.active_provider_id,
+            model_id=model_id,
+            provider_model_name=model_name(model_id, "completions"),
+            params=params,
+            tools=tools,
+            input_messages=input_messages,
+            assistant_message=assistant_message,
+            finish_reason=finish_reason,
+            format=format,
+        )
+
+    async def _call_async(
+        self,
+        *,
+        model_id: OpenAIModelId,
+        messages: Sequence[Message],
+        tools: Sequence[AsyncTool] | AsyncToolkit | None = None,
+        format: type[FormattableT] | Format[FormattableT] | None = None,
+        **params: Unpack[Params],
+    ) -> AsyncResponse | AsyncResponse[FormattableT]:
+        """Generate an `llm.AsyncResponse` by asynchronously calling the OpenAI ChatCompletions API.
+
+        Args:
+            model_id: Model identifier to use.
+            messages: Messages to send to the LLM.
+            tools: Optional tools that the model may invoke.
+            format: Optional response format specifier.
+            **params: Additional parameters to configure output (e.g. temperature). See `llm.Params`.
+
+        Returns:
+            An `llm.AsyncResponse` object containing the LLM-generated content.
+        """
+
+        input_messages, format, kwargs = _utils.encode_request(
+            model_id=model_id,
+            params=params,
+            messages=messages,
+            tools=tools,
+            format=format,
+        )
+
+        openai_response = await self.async_client.chat.completions.create(**kwargs)
+
+        assistant_message, finish_reason = _utils.decode_response(
+            openai_response, model_id, self.active_provider_id
+        )
+
+        return AsyncResponse(
+            raw=openai_response,
+            provider_id=self.active_provider_id,
+            model_id=model_id,
+            provider_model_name=model_name(model_id, "completions"),
+            params=params,
+            tools=tools,
+            input_messages=input_messages,
+            assistant_message=assistant_message,
+            finish_reason=finish_reason,
+            format=format,
+        )
+
+    async def _context_call_async(
+        self,
+        *,
+        ctx: Context[DepsT],
+        model_id: OpenAIModelId,
+        messages: Sequence[Message],
+        tools: Sequence[AsyncTool | AsyncContextTool[DepsT]]
+        | AsyncContextToolkit[DepsT]
+        | None = None,
+        format: type[FormattableT] | Format[FormattableT] | None = None,
+        **params: Unpack[Params],
+    ) -> AsyncContextResponse[DepsT, None] | AsyncContextResponse[DepsT, FormattableT]:
+        """Generate an `llm.AsyncContextResponse` by asynchronously calling the OpenAI ChatCompletions API.
+
+        Args:
+            ctx: Context object with dependencies for tools.
+            model_id: Model identifier to use.
+            messages: Messages to send to the LLM.
+            tools: Optional tools that the model may invoke.
+            format: Optional response format specifier.
+            **params: Additional parameters to configure output (e.g. temperature). See `llm.Params`.
+
+        Returns:
+            An `llm.AsyncContextResponse` object containing the LLM-generated content.
+        """
+        input_messages, format, kwargs = _utils.encode_request(
+            model_id=model_id,
+            params=params,
+            messages=messages,
+            tools=tools,
+            format=format,
+        )
+
+        openai_response = await self.async_client.chat.completions.create(**kwargs)
+
+        assistant_message, finish_reason = _utils.decode_response(
+            openai_response, model_id, self.active_provider_id
+        )
+
+        return AsyncContextResponse(
+            raw=openai_response,
+            provider_id=self.active_provider_id,
+            model_id=model_id,
+            provider_model_name=model_name(model_id, "completions"),
+            params=params,
+            tools=tools,
+            input_messages=input_messages,
+            assistant_message=assistant_message,
+            finish_reason=finish_reason,
+            format=format,
+        )
+
+    def _stream(
+        self,
+        *,
+        model_id: OpenAIModelId,
+        messages: Sequence[Message],
+        tools: Sequence[Tool] | Toolkit | None = None,
+        format: type[FormattableT] | Format[FormattableT] | None = None,
+        **params: Unpack[Params],
+    ) -> StreamResponse | StreamResponse[FormattableT]:
+        """Generate an `llm.StreamResponse` by synchronously streaming from the OpenAI ChatCompletions API.
+
+        Args:
+            model_id: Model identifier to use.
+            messages: Messages to send to the LLM.
+            tools: Optional tools that the model may invoke.
+            format: Optional response format specifier.
+            **params: Additional parameters to configure output (e.g. temperature). See `llm.Params`.
+
+        Returns:
+            An `llm.StreamResponse` object for iterating over the LLM-generated content.
+        """
+        input_messages, format, kwargs = _utils.encode_request(
+            model_id=model_id,
+            messages=messages,
+            tools=tools,
+            format=format,
+            params=params,
+        )
+
+        openai_stream = self.client.chat.completions.create(
+            **kwargs,
+            stream=True,
+        )
+
+        chunk_iterator = _utils.decode_stream(openai_stream)
+
+        return StreamResponse(
+            provider_id=self.active_provider_id,
+            model_id=model_id,
+            provider_model_name=model_name(model_id, "completions"),
+            params=params,
+            tools=tools,
+            input_messages=input_messages,
+            chunk_iterator=chunk_iterator,
+            format=format,
+        )
+
+    def _context_stream(
+        self,
+        *,
+        ctx: Context[DepsT],
+        model_id: OpenAIModelId,
+        messages: Sequence[Message],
+        tools: Sequence[Tool | ContextTool[DepsT]]
+        | ContextToolkit[DepsT]
+        | None = None,
+        format: type[FormattableT] | Format[FormattableT] | None = None,
+        **params: Unpack[Params],
+    ) -> ContextStreamResponse[DepsT] | ContextStreamResponse[DepsT, FormattableT]:
+        """Generate an `llm.ContextStreamResponse` by synchronously streaming from the OpenAI ChatCompletions API.
+
+        Args:
+            ctx: Context object with dependencies for tools.
+            model_id: Model identifier to use.
+            messages: Messages to send to the LLM.
+            tools: Optional tools that the model may invoke.
+            format: Optional response format specifier.
+            **params: Additional parameters to configure output (e.g. temperature). See `llm.Params`.
+
+        Returns:
+            An `llm.ContextStreamResponse` object for iterating over the LLM-generated content.
+        """
+        input_messages, format, kwargs = _utils.encode_request(
+            model_id=model_id,
+            messages=messages,
+            tools=tools,
+            format=format,
+            params=params,
+        )
+
+        openai_stream = self.client.chat.completions.create(
+            **kwargs,
+            stream=True,
+        )
+
+        chunk_iterator = _utils.decode_stream(openai_stream)
+
+        return ContextStreamResponse(
+            provider_id=self.active_provider_id,
+            model_id=model_id,
+            provider_model_name=model_name(model_id, "completions"),
+            params=params,
+            tools=tools,
+            input_messages=input_messages,
+            chunk_iterator=chunk_iterator,
+            format=format,
+        )
+
+    async def _stream_async(
+        self,
+        *,
+        model_id: OpenAIModelId,
+        messages: Sequence[Message],
+        tools: Sequence[AsyncTool] | AsyncToolkit | None = None,
+        format: type[FormattableT] | Format[FormattableT] | None = None,
+        **params: Unpack[Params],
+    ) -> AsyncStreamResponse | AsyncStreamResponse[FormattableT]:
+        """Generate an `llm.AsyncStreamResponse` by asynchronously streaming from the OpenAI ChatCompletions API.
+
+        Args:
+            model_id: Model identifier to use.
+            messages: Messages to send to the LLM.
+            tools: Optional tools that the model may invoke.
+            format: Optional response format specifier.
+            **params: Additional parameters to configure output (e.g. temperature). See `llm.Params`.
+
+        Returns:
+            An `llm.AsyncStreamResponse` object for asynchronously iterating over the LLM-generated content.
+        """
+
+        input_messages, format, kwargs = _utils.encode_request(
+            model_id=model_id,
+            messages=messages,
+            tools=tools,
+            format=format,
+            params=params,
+        )
+
+        openai_stream = await self.async_client.chat.completions.create(
+            **kwargs,
+            stream=True,
+        )
+
+        chunk_iterator = _utils.decode_async_stream(openai_stream)
+
+        return AsyncStreamResponse(
+            provider_id=self.active_provider_id,
+            model_id=model_id,
+            provider_model_name=model_name(model_id, "completions"),
+            params=params,
+            tools=tools,
+            input_messages=input_messages,
+            chunk_iterator=chunk_iterator,
+            format=format,
+        )
+
+    async def _context_stream_async(
+        self,
+        *,
+        ctx: Context[DepsT],
+        model_id: OpenAIModelId,
+        messages: Sequence[Message],
+        tools: Sequence[AsyncTool | AsyncContextTool[DepsT]]
+        | AsyncContextToolkit[DepsT]
+        | None = None,
+        format: type[FormattableT] | Format[FormattableT] | None = None,
+        **params: Unpack[Params],
+    ) -> (
+        AsyncContextStreamResponse[DepsT]
+        | AsyncContextStreamResponse[DepsT, FormattableT]
+    ):
+        """Generate an `llm.AsyncContextStreamResponse` by asynchronously streaming from the OpenAI ChatCompletions API.
+
+        Args:
+            ctx: Context object with dependencies for tools.
+            model_id: Model identifier to use.
+            messages: Messages to send to the LLM.
+            tools: Optional tools that the model may invoke.
+            format: Optional response format specifier.
+            **params: Additional parameters to configure output (e.g. temperature). See `llm.Params`.
+
+        Returns:
+            An `llm.AsyncContextStreamResponse` object for asynchronously iterating over the LLM-generated content.
+        """
+        input_messages, format, kwargs = _utils.encode_request(
+            model_id=model_id,
+            messages=messages,
+            tools=tools,
+            format=format,
+            params=params,
+        )
+
+        openai_stream = await self.async_client.chat.completions.create(
+            **kwargs,
+            stream=True,
+        )
+
+        chunk_iterator = _utils.decode_async_stream(openai_stream)
+
+        return AsyncContextStreamResponse(
+            provider_id=self.active_provider_id,
+            model_id=model_id,
+            provider_model_name=model_name(model_id, "completions"),
+            params=params,
+            tools=tools,
+            input_messages=input_messages,
+            chunk_iterator=chunk_iterator,
+            format=format,
+        )

mirascope/llm/providers/openai/model_id.py

@@ -0,0 +1,31 @@
+"""OpenAI model ids, and related utilities."""
+
+from typing import Literal, TypeAlias, get_args
+
+from .model_info import OpenAIKnownModels
+
+OpenAIModelId = OpenAIKnownModels | str
+"""Valid OpenAI model IDs including API-specific variants."""
+
+OPENAI_KNOWN_MODELS: set[str] = set(get_args(OpenAIKnownModels))
+
+ApiMode: TypeAlias = Literal["responses", "completions"]
+
+
+def model_name(model_id: OpenAIModelId, api_mode: ApiMode | None) -> str:
+    """Extract the openai model name from the ModelId
+
+    Args:
+        model_id: Full model ID (e.g. "openai/gpt-4o")
+        api_mode: API mode to append as suffix ("responses" or "completions").
+          If None, no suffix will be added (just the base model name).
+
+    Returns:
+        Provider-specific model ID with API suffix (e.g. "gpt-4o:responses")
+    """
+    base_name = (
+        model_id.split("/")[1].removesuffix(":responses").removesuffix(":completions")
+    )
+    if api_mode is None:
+        return base_name
+    return f"{base_name}:{api_mode}"