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.
65 lines
2.1 KiB
Python
65 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 os
|
|
from collections.abc import Iterable
|
|
|
|
from openai import AsyncOpenAI
|
|
from openai.types import EmbeddingModel
|
|
|
|
from .client import EmbedderClient, EmbedderConfig
|
|
|
|
DEFAULT_EMBEDDING_MODEL = "qwen-3-8b"
|
|
|
|
|
|
class ChutesEmbedderConfig(EmbedderConfig):
|
|
embedding_model: EmbeddingModel | str = DEFAULT_EMBEDDING_MODEL
|
|
api_key: str | None = os.environ.get("CHUTES_API_TOKEN")
|
|
base_url: str | None = "https://chutes-qwen-qwen3-embedding-8b.chutes.ai/v1"
|
|
|
|
|
|
class ChutesEmbedder(EmbedderClient):
|
|
"""
|
|
Chutes Embedder Client
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
config: ChutesEmbedderConfig | None = None,
|
|
client: AsyncOpenAI | None = None,
|
|
):
|
|
if config is None:
|
|
config = ChutesEmbedderConfig()
|
|
self.config = config
|
|
|
|
if client is not None:
|
|
self.client = client
|
|
else:
|
|
self.client = AsyncOpenAI(api_key=config.api_key, base_url=config.base_url)
|
|
|
|
async def create(
|
|
self, input_data: str | list[str] | Iterable[int] | Iterable[Iterable[int]]
|
|
) -> list[float]:
|
|
result = await self.client.embeddings.create(
|
|
input=input_data, model=None
|
|
)
|
|
return result.data[0].embedding[: self.config.embedding_dim]
|
|
|
|
async def create_batch(self, input_data_list: list[str]) -> list[list[float]]:
|
|
result = await self.client.embeddings.create(
|
|
input=input_data_list, model=None
|
|
)
|
|
return [embedding.embedding[: self.config.embedding_dim] for embedding in result.data]
|