graphiti/graphiti_core/llm_client/openai_client.py

"""
Copyright 2024, Zep Software, Inc.

Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
"""

import json
import logging
import typing

import openai
from openai import AsyncOpenAI
from openai.types.chat import ChatCompletionMessageParam

from ..prompts.models import Message
from .client import LLMClient
from .config import LLMConfig
from .errors import RateLimitError

logger = logging.getLogger(__name__)

DEFAULT_MODEL = 'gpt-4o-2024-08-06'


class OpenAIClient(LLMClient):
    """
    OpenAIClient is a client class for interacting with OpenAI's language models.

    This class extends the LLMClient and provides methods to initialize the client,
    get an embedder, and generate responses from the language model.

    Attributes:
        client (AsyncOpenAI): The OpenAI client used to interact with the API.
        model (str): The model name to use for generating responses.
        temperature (float): The temperature to use for generating responses.
        max_tokens (int): The maximum number of tokens to generate in a response.

    Methods:
        __init__(config: LLMConfig | None = None, cache: bool = False, client: typing.Any = None):
            Initializes the OpenAIClient with the provided configuration, cache setting, and client.

        get_embedder() -> typing.Any:
            Returns the embedder from the OpenAI client.

        _generate_response(messages: list[Message]) -> dict[str, typing.Any]:
            Generates a response from the language model based on the provided messages.
    """

    def __init__(
        self, config: LLMConfig | None = None, cache: bool = False, client: typing.Any = None
    ):
        """
        Initialize the OpenAIClient with the provided configuration, cache setting, and client.

        Args:
            config (LLMConfig | None): The configuration for the LLM client, including API key, model, base URL, temperature, and max tokens.
            cache (bool): Whether to use caching for responses. Defaults to False.
            client (Any | None): An optional async client instance to use. If not provided, a new AsyncOpenAI client is created.

        """
        if config is None:
            config = LLMConfig()

        super().__init__(config, cache)

        if client is None:
            self.client = AsyncOpenAI(api_key=config.api_key, base_url=config.base_url)
        else:
            self.client = client

    def get_embedder(self) -> typing.Any:
        return self.client.embeddings

    async def _generate_response(self, messages: list[Message]) -> dict[str, typing.Any]:
        openai_messages: list[ChatCompletionMessageParam] = []
        for m in messages:
            if m.role == 'user':
                openai_messages.append({'role': 'user', 'content': m.content})
            elif m.role == 'system':
                openai_messages.append({'role': 'system', 'content': m.content})
        try:
            response = await self.client.chat.completions.create(
                model=self.model or DEFAULT_MODEL,
                messages=openai_messages,
                temperature=self.temperature,
                max_tokens=self.max_tokens,
                response_format={'type': 'json_object'},
            )
            result = response.choices[0].message.content or ''
            return json.loads(result)
        except openai.RateLimitError as e:
            raise RateLimitError from e
        except Exception as e:
            logger.error(f'Error in generating LLM response: {e}')
            raise