mirror of
https://github.com/getzep/graphiti.git
synced 2025-07-25 01:49:57 +00:00
64 lines
2.1 KiB
Python
64 lines
2.1 KiB
Python
|
"""
|
||
|
|
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 groq import AsyncGroq
|
||
|
|
from groq.types.chat import ChatCompletionMessageParam
|
||
|
|
from openai import AsyncOpenAI
|
||
|
|
|
||
|
|
from ..prompts.models import Message
|
||
|
|
from .client import LLMClient
|
||
|
|
from .config import LLMConfig
|
||
|
|
|
||
|
|
logger = logging.getLogger(__name__)
|
||
|
|
|
||
|
|
|
||
|
|
class GroqClient(LLMClient):
|
||
|
|
def __init__(self, config: LLMConfig | None = None):
|
||
|
|
if config is None:
|
||
|
|
config = LLMConfig()
|
||
|
|
self.client = AsyncGroq(api_key=config.api_key)
|
||
|
|
self.model = config.model
|
||
|
|
|
||
|
|
def get_embedder(self) -> typing.Any:
|
||
|
|
openai_client = AsyncOpenAI()
|
||
|
|
return openai_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='llama-3.1-70b-versatile',
|
||
|
|
messages=openai_messages,
|
||
|
|
temperature=0.0,
|
||
|
|
max_tokens=4096,
|
||
|
|
response_format={'type': 'json_object'},
|
||
|
|
)
|
||
|
|
result = response.choices[0].message.content or ''
|
||
|
|
return json.loads(result)
|
||
|
|
except Exception as e:
|
||
|
|
print(openai_messages)
|
||
|
|
logger.error(f'Error in generating LLM response: {e}')
|
||
|
|
raise
|