mirror of
https://github.com/getzep/graphiti.git
synced 2025-06-27 02:00:02 +00:00
895afc7be1
* chore: Add romeo runner * fix: Linter * wip * wip dump * chore: Update romeo parser * chore: Anthropic model fix * wip * allbirds * allbirds runner * format * wip * wip * mypy updates * update * remove r * update tests * format * wip * chore: Strategically update the message * rebase and fix import issues * Update package imports for graphiti_core in examples and utils * nits * chore: Update OpenAI GPT-4o model to gpt-4o-2024-08-06 * implement groq * improvments & linting * cleanup and nits * Refactor package imports for graphiti_core in examples and utils * Refactor package imports for graphiti_core in examples and utils * implement diskcache * remove debug stuff * log cache hit when debugging only * Improve LLM config. Fix bugs (#41) Refactor LLMConfig class to allow None values for model and base_url * chore: Resolve mc --------- Co-authored-by: paulpaliychuk <pavlo.paliychuk.ca@gmail.com> Co-authored-by: prestonrasmussen <prasmuss15@gmail.com>
66 lines
2.2 KiB
Python
66 lines
2.2 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 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__)
|
|
|
|
DEFAULT_MODEL = 'gpt-4o-2024-08-06'
|
|
|
|
|
|
class OpenAIClient(LLMClient):
|
|
def __init__(self, config: LLMConfig | None = None, cache: bool = False):
|
|
if config is None:
|
|
config = LLMConfig()
|
|
|
|
super().__init__(config, cache)
|
|
|
|
self.client = AsyncOpenAI(api_key=config.api_key, base_url=config.base_url)
|
|
|
|
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 Exception as e:
|
|
print(openai_messages)
|
|
logger.error(f'Error in generating LLM response: {e}')
|
|
raise
|