a7f2c92bb4
- Introduced CHUTES_API_TOKEN in .env.example files for configuration. - Updated README.md in quickstart example to include Chutes API setup. - Created quickstart_chutes.py example for demonstrating Chutes integration. - Added ChutesEmbedder and ChutesClient classes for embedding and LLM functionalities. - Updated LLM and embedder provider configurations to support Chutes. - Enhanced factories to include Chutes client and embedder. - Modified schema.py to define Chutes provider configuration. - Updated mcp_server configuration files to integrate Chutes API. - Added necessary dependencies in pyproject.toml for Chutes support.
90 lines
2.8 KiB
Python
90 lines
2.8 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,
|
|
WITHOUTHOUT 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 os
|
|
import typing
|
|
|
|
from openai import AsyncOpenAI
|
|
from openai.types.chat import ChatCompletionMessageParam
|
|
from pydantic import BaseModel
|
|
|
|
from .config import DEFAULT_MAX_TOKENS, LLMConfig
|
|
from .openai_base_client import DEFAULT_REASONING, DEFAULT_VERBOSITY, BaseOpenAIClient
|
|
|
|
|
|
class ChutesClient(BaseOpenAIClient):
|
|
"""
|
|
ChutesClient is a client class for interacting with Chutes's language models.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
config: LLMConfig | None = None,
|
|
cache: bool = False,
|
|
client: typing.Any = None,
|
|
max_tokens: int = DEFAULT_MAX_TOKENS,
|
|
reasoning: str = DEFAULT_REASONING,
|
|
verbosity: str = DEFAULT_VERBOSITY,
|
|
):
|
|
"""
|
|
Initialize the ChutesClient with the provided configuration, cache setting, and client.
|
|
"""
|
|
super().__init__(config, cache, max_tokens, reasoning, verbosity)
|
|
|
|
if config is None:
|
|
config = LLMConfig()
|
|
|
|
if client is None:
|
|
self.client = AsyncOpenAI(
|
|
api_key=config.api_key,
|
|
base_url="https://llm.chutes.ai/v1",
|
|
)
|
|
else:
|
|
self.client = client
|
|
|
|
async def _create_structured_completion(
|
|
self,
|
|
model: str,
|
|
messages: list[ChatCompletionMessageParam],
|
|
temperature: float | None,
|
|
max_tokens: int,
|
|
response_model: type[BaseModel],
|
|
reasoning: str | None = None,
|
|
verbosity: str | None = None,
|
|
):
|
|
"""Create a structured completion using Chutes's API."""
|
|
return await self._create_completion(
|
|
model, messages, temperature, max_tokens, response_model
|
|
)
|
|
|
|
async def _create_completion(
|
|
self,
|
|
model: str,
|
|
messages: list[ChatCompletionMessageParam],
|
|
temperature: float | None,
|
|
max_tokens: int,
|
|
response_model: type[BaseModel] | None = None,
|
|
reasoning: str | None = None,
|
|
verbosity: str | None = None,
|
|
):
|
|
"""Create a regular completion with JSON format."""
|
|
return await self.client.chat.completions.create(
|
|
model=model,
|
|
messages=messages,
|
|
temperature=temperature,
|
|
max_tokens=max_tokens,
|
|
response_format={"type": "json_object"} if response_model else None,
|
|
)
|