langchain/libs/partners/groq/langchain_groq/chat_models.py

"""Groq Chat wrapper."""

from __future__ import annotations

import os
import warnings
from typing import (
    Any,
    AsyncIterator,
    Dict,
    Iterator,
    List,
    Mapping,
    Optional,
    Tuple,
    Type,
    Union,
    cast,
)

from langchain_core.callbacks import (
    AsyncCallbackManagerForLLMRun,
    CallbackManagerForLLMRun,
)
from langchain_core.language_models.chat_models import (
    BaseChatModel,
    agenerate_from_stream,
    generate_from_stream,
)
from langchain_core.messages import (
    AIMessage,
    AIMessageChunk,
    BaseMessage,
    BaseMessageChunk,
    ChatMessage,
    ChatMessageChunk,
    FunctionMessage,
    FunctionMessageChunk,
    HumanMessage,
    HumanMessageChunk,
    SystemMessage,
    SystemMessageChunk,
    ToolMessage,
    ToolMessageChunk,
)
from langchain_core.outputs import ChatGeneration, ChatGenerationChunk, ChatResult
from langchain_core.pydantic_v1 import BaseModel, Field, SecretStr, root_validator
from langchain_core.utils import (
    convert_to_secret_str,
    get_from_dict_or_env,
    get_pydantic_field_names,
)


class ChatGroq(BaseChatModel):
    """`Groq` Chat large language models API.

    To use, you should have the
    environment variable ``GROQ_API_KEY`` set with your API key.

    Any parameters that are valid to be passed to the groq.create call can be passed
    in, even if not explicitly saved on this class.

    Example:
        .. code-block:: python

            from langchain_community.chat_models import ChatGroq
            groq = ChatGroq(model_name="mixtral-8x7b-32768")
    """

    client: Any = Field(default=None, exclude=True)  #: :meta private:
    async_client: Any = Field(default=None, exclude=True)  #: :meta private:
    model_name: str = Field(default="mixtral-8x7b-32768", alias="model")
    """Model name to use."""
    temperature: float = 0.7
    """What sampling temperature to use."""
    model_kwargs: Dict[str, Any] = Field(default_factory=dict)
    """Holds any model parameters valid for `create` call not explicitly specified."""
    groq_api_key: Optional[SecretStr] = Field(default=None, alias="api_key")
    """Automatically inferred from env var `groq_API_KEY` if not provided."""
    groq_api_base: Optional[str] = Field(default=None, alias="base_url")
    """Base URL path for API requests, leave blank if not using a proxy or service
        emulator."""
    # to support explicit proxy for Groq
    groq_proxy: Optional[str] = None
    request_timeout: Union[float, Tuple[float, float], Any, None] = Field(
        default=None, alias="timeout"
    )
    """Timeout for requests to Groq completion API. Can be float, httpx.Timeout or
        None."""
    max_retries: int = 2
    """Maximum number of retries to make when generating."""
    streaming: bool = False
    """Whether to stream the results or not."""
    n: int = 1
    """Number of chat completions to generate for each prompt."""
    max_tokens: Optional[int] = None
    """Maximum number of tokens to generate."""
    default_headers: Union[Mapping[str, str], None] = None
    default_query: Union[Mapping[str, object], None] = None
    # Configure a custom httpx client. See the
    # [httpx documentation](https://www.python-httpx.org/api/#client) for more details.
    http_client: Union[Any, None] = None
    """Optional httpx.Client."""

    class Config:
        """Configuration for this pydantic object."""

        allow_population_by_field_name = True

    @root_validator(pre=True)
    def build_extra(cls, values: Dict[str, Any]) -> Dict[str, Any]:
        """Build extra kwargs from additional params that were passed in."""
        all_required_field_names = get_pydantic_field_names(cls)
        extra = values.get("model_kwargs", {})
        for field_name in list(values):
            if field_name in extra:
                raise ValueError(f"Found {field_name} supplied twice.")
            if field_name not in all_required_field_names:
                warnings.warn(
                    f"""WARNING! {field_name} is not default parameter.
                    {field_name} was transferred to model_kwargs.
                    Please confirm that {field_name} is what you intended."""
                )
                extra[field_name] = values.pop(field_name)

        invalid_model_kwargs = all_required_field_names.intersection(extra.keys())
        if invalid_model_kwargs:
            raise ValueError(
                f"Parameters {invalid_model_kwargs} should be specified explicitly. "
                f"Instead they were passed in as part of `model_kwargs` parameter."
            )

        values["model_kwargs"] = extra
        return values

    @root_validator()
    def validate_environment(cls, values: Dict) -> Dict:
        """Validate that api key and python package exists in environment."""
        if values["n"] < 1:
            raise ValueError("n must be at least 1.")
        if values["n"] > 1 and values["streaming"]:
            raise ValueError("n must be 1 when streaming.")

        if values["temperature"] == 0:
            values["temperature"] = 1e-8

        values["groq_api_key"] = convert_to_secret_str(
            get_from_dict_or_env(values, "groq_api_key", "GROQ_API_KEY")
        )
        values["groq_api_base"] = values["groq_api_base"] or os.getenv("GROQ_API_BASE")
        values["groq_proxy"] = values["groq_proxy"] = os.getenv("GROQ_PROXY")

        client_params = {
            "api_key": values["groq_api_key"].get_secret_value(),
            "base_url": values["groq_api_base"],
            "timeout": values["request_timeout"],
            "max_retries": values["max_retries"],
            "default_headers": values["default_headers"],
            "default_query": values["default_query"],
            "http_client": values["http_client"],
        }

        try:
            import groq

            if not values.get("client"):
                values["client"] = groq.Groq(**client_params).chat.completions
            if not values.get("async_client"):
                values["async_client"] = groq.AsyncGroq(
                    **client_params
                ).chat.completions
        except ImportError:
            raise ImportError(
                "Could not import groq python package. "
                "Please install it with `pip install groq`."
            )
        return values

    #
    # Serializable class method overrides
    #
    @property
    def lc_secrets(self) -> Dict[str, str]:
        return {"groq_api_key": "GROQ_API_KEY"}

    @classmethod
    def is_lc_serializable(cls) -> bool:
        """Return whether this model can be serialized by Langchain."""
        return True

    #
    # BaseChatModel method overrides
    #
    @property
    def _llm_type(self) -> str:
        """Return type of model."""
        return "groq-chat"

    def _generate(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[CallbackManagerForLLMRun] = None,
        stream: Optional[bool] = None,
        **kwargs: Any,
    ) -> ChatResult:
        should_stream = stream if stream is not None else self.streaming
        if should_stream:
            stream_iter = self._stream(
                messages, stop=stop, run_manager=run_manager, **kwargs
            )
            return generate_from_stream(stream_iter)
        message_dicts, params = self._create_message_dicts(messages, stop)
        params = {
            **params,
            **({"stream": stream} if stream is not None else {}),
            **kwargs,
        }
        response = self.client.create(messages=message_dicts, **params)
        return self._create_chat_result(response)

    async def _agenerate(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
        stream: Optional[bool] = None,
        **kwargs: Any,
    ) -> ChatResult:
        should_stream = stream if stream is not None else self.streaming
        if should_stream:
            stream_iter = self._astream(
                messages, stop=stop, run_manager=run_manager, **kwargs
            )
            return await agenerate_from_stream(stream_iter)

        message_dicts, params = self._create_message_dicts(messages, stop)
        params = {
            **params,
            **({"stream": stream} if stream is not None else {}),
            **kwargs,
        }
        response = await self.async_client.create(messages=message_dicts, **params)
        return self._create_chat_result(response)

    def _stream(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[CallbackManagerForLLMRun] = None,
        **kwargs: Any,
    ) -> Iterator[ChatGenerationChunk]:
        message_dicts, params = self._create_message_dicts(messages, stop)
        params = {**params, **kwargs, "stream": True}

        default_chunk_class = AIMessageChunk
        for chunk in self.client.create(messages=message_dicts, **params):
            if not isinstance(chunk, dict):
                chunk = chunk.dict()
            if len(chunk["choices"]) == 0:
                continue
            choice = chunk["choices"][0]
            chunk = _convert_delta_to_message_chunk(
                choice["delta"], default_chunk_class
            )
            generation_info = {}
            if finish_reason := choice.get("finish_reason"):
                generation_info["finish_reason"] = finish_reason
            logprobs = choice.get("logprobs")
            if logprobs:
                generation_info["logprobs"] = logprobs
            default_chunk_class = chunk.__class__
            chunk = ChatGenerationChunk(
                message=chunk, generation_info=generation_info or None
            )

            if run_manager:
                run_manager.on_llm_new_token(chunk.text, chunk=chunk, logprobs=logprobs)
            yield chunk

    async def _astream(
        self,
        messages: List[BaseMessage],
        stop: Optional[List[str]] = None,
        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
        **kwargs: Any,
    ) -> AsyncIterator[ChatGenerationChunk]:
        message_dicts, params = self._create_message_dicts(messages, stop)
        params = {**params, **kwargs, "stream": True}

        default_chunk_class = AIMessageChunk
        async for chunk in await self.async_client.create(
            messages=message_dicts, **params
        ):
            if not isinstance(chunk, dict):
                chunk = chunk.dict()
            if len(chunk["choices"]) == 0:
                continue
            choice = chunk["choices"][0]
            chunk = _convert_delta_to_message_chunk(
                choice["delta"], default_chunk_class
            )
            generation_info = {}
            if finish_reason := choice.get("finish_reason"):
                generation_info["finish_reason"] = finish_reason
            logprobs = choice.get("logprobs")
            if logprobs:
                generation_info["logprobs"] = logprobs
            default_chunk_class = chunk.__class__
            chunk = ChatGenerationChunk(
                message=chunk, generation_info=generation_info or None
            )

            if run_manager:
                await run_manager.on_llm_new_token(
                    token=chunk.text, chunk=chunk, logprobs=logprobs
                )
            yield chunk

    #
    # Internal methods
    #
    @property
    def _default_params(self) -> Dict[str, Any]:
        """Get the default parameters for calling Groq API."""
        params = {
            "model": self.model_name,
            "stream": self.streaming,
            "n": self.n,
            "temperature": self.temperature,
            **self.model_kwargs,
        }
        if self.max_tokens is not None:
            params["max_tokens"] = self.max_tokens
        return params

    def _create_chat_result(self, response: Union[dict, BaseModel]) -> ChatResult:
        generations = []
        if not isinstance(response, dict):
            response = response.dict()
        for res in response["choices"]:
            message = _convert_dict_to_message(res["message"])
            generation_info = dict(finish_reason=res.get("finish_reason"))
            if "logprobs" in res:
                generation_info["logprobs"] = res["logprobs"]
            gen = ChatGeneration(
                message=message,
                generation_info=generation_info,
            )
            generations.append(gen)
        token_usage = response.get("usage", {})
        llm_output = {
            "token_usage": token_usage,
            "model_name": self.model_name,
            "system_fingerprint": response.get("system_fingerprint", ""),
        }
        return ChatResult(generations=generations, llm_output=llm_output)

    def _create_message_dicts(
        self, messages: List[BaseMessage], stop: Optional[List[str]]
    ) -> Tuple[List[Dict[str, Any]], Dict[str, Any]]:
        params = self._default_params
        if stop is not None:
            if "stop" in params:
                raise ValueError("`stop` found in both the input and default params.")
            params["stop"] = stop
        message_dicts = [_convert_message_to_dict(m) for m in messages]
        return message_dicts, params

    def _combine_llm_outputs(self, llm_outputs: List[Optional[dict]]) -> dict:
        overall_token_usage: dict = {}
        system_fingerprint = None
        for output in llm_outputs:
            if output is None:
                # Happens in streaming
                continue
            token_usage = output["token_usage"]
            if token_usage is not None:
                for k, v in token_usage.items():
                    if k in overall_token_usage:
                        overall_token_usage[k] += v
                    else:
                        overall_token_usage[k] = v
            if system_fingerprint is None:
                system_fingerprint = output.get("system_fingerprint")
        combined = {"token_usage": overall_token_usage, "model_name": self.model_name}
        if system_fingerprint:
            combined["system_fingerprint"] = system_fingerprint
        return combined


#
# Type conversion helpers
#
def _convert_message_to_dict(message: BaseMessage) -> dict:
    """Convert a LangChain message to a dictionary.

    Args:
        message: The LangChain message.

    Returns:
        The dictionary.
    """
    message_dict: Dict[str, Any]
    if isinstance(message, ChatMessage):
        message_dict = {"role": message.role, "content": message.content}
    elif isinstance(message, HumanMessage):
        message_dict = {"role": "user", "content": message.content}
    elif isinstance(message, AIMessage):
        message_dict = {"role": "assistant", "content": message.content}
        if "function_call" in message.additional_kwargs:
            message_dict["function_call"] = message.additional_kwargs["function_call"]
            # If function call only, content is None not empty string
            if message_dict["content"] == "":
                message_dict["content"] = None
        if "tool_calls" in message.additional_kwargs:
            message_dict["tool_calls"] = message.additional_kwargs["tool_calls"]
            # If tool calls only, content is None not empty string
            if message_dict["content"] == "":
                message_dict["content"] = None
    elif isinstance(message, SystemMessage):
        message_dict = {"role": "system", "content": message.content}
    elif isinstance(message, FunctionMessage):
        message_dict = {
            "role": "function",
            "content": message.content,
            "name": message.name,
        }
    elif isinstance(message, ToolMessage):
        message_dict = {
            "role": "tool",
            "content": message.content,
            "tool_call_id": message.tool_call_id,
        }
    else:
        raise TypeError(f"Got unknown type {message}")
    if "name" in message.additional_kwargs:
        message_dict["name"] = message.additional_kwargs["name"]
    return message_dict


def _convert_delta_to_message_chunk(
    _dict: Mapping[str, Any], default_class: Type[BaseMessageChunk]
) -> BaseMessageChunk:
    role = cast(str, _dict.get("role"))
    content = cast(str, _dict.get("content") or "")
    additional_kwargs: Dict = {}
    if _dict.get("function_call"):
        function_call = dict(_dict["function_call"])
        if "name" in function_call and function_call["name"] is None:
            function_call["name"] = ""
        additional_kwargs["function_call"] = function_call
    if _dict.get("tool_calls"):
        additional_kwargs["tool_calls"] = _dict["tool_calls"]

    if role == "user" or default_class == HumanMessageChunk:
        return HumanMessageChunk(content=content)
    elif role == "assistant" or default_class == AIMessageChunk:
        return AIMessageChunk(content=content, additional_kwargs=additional_kwargs)
    elif role == "system" or default_class == SystemMessageChunk:
        return SystemMessageChunk(content=content)
    elif role == "function" or default_class == FunctionMessageChunk:
        return FunctionMessageChunk(content=content, name=_dict["name"])
    elif role == "tool" or default_class == ToolMessageChunk:
        return ToolMessageChunk(content=content, tool_call_id=_dict["tool_call_id"])
    elif role or default_class == ChatMessageChunk:
        return ChatMessageChunk(content=content, role=role)
    else:
        return default_class(content=content)  # type: ignore


def _convert_dict_to_message(_dict: Mapping[str, Any]) -> BaseMessage:
    """Convert a dictionary to a LangChain message.

    Args:
        _dict: The dictionary.

    Returns:
        The LangChain message.
    """
    role = _dict.get("role")
    if role == "user":
        return HumanMessage(content=_dict.get("content", ""))
    elif role == "assistant":
        content = _dict.get("content", "")
        additional_kwargs: Dict = {}
        if function_call := _dict.get("function_call"):
            additional_kwargs["function_call"] = dict(function_call)
        if tool_calls := _dict.get("tool_calls"):
            additional_kwargs["tool_calls"] = tool_calls
        return AIMessage(content=content, additional_kwargs=additional_kwargs)
    elif role == "system":
        return SystemMessage(content=_dict.get("content", ""))
    elif role == "function":
        return FunctionMessage(content=_dict.get("content", ""), name=_dict.get("name"))
    elif role == "tool":
        additional_kwargs = {}
        if "name" in _dict:
            additional_kwargs["name"] = _dict["name"]
        return ToolMessage(
            content=_dict.get("content", ""),
            tool_call_id=_dict.get("tool_call_id"),
            additional_kwargs=additional_kwargs,
        )
    else:
        return ChatMessage(content=_dict.get("content", ""), role=role)