graphiti/graphiti_core/llm_client/openai_client.py

59 lines
2.0 KiB
Python
Raw Normal View History

"""
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
from openai import AsyncOpenAI
from openai.types.chat import ChatCompletionMessageParam
from ..prompts.models import Message
from .client import LLMClient
from .config import LLMConfig
logger = logging.getLogger(__name__)
class OpenAIClient(LLMClient):
def __init__(self, config: LLMConfig):
self.client = AsyncOpenAI(api_key=config.api_key, base_url=config.base_url)
self.model = config.model
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,
messages=openai_messages,
2024-08-23 18:06:42 -04:00
temperature=0,
max_tokens=3000,
response_format={'type': 'json_object'},
)
result = response.choices[0].message.content or ''
return json.loads(result)
except Exception as e:
logger.error(f'Error in generating LLM response: {e}')
raise