9e78890f2e
* first cut * Update dependencies and enhance README for optional LLM providers - Bump aiohttp version from 3.11.14 to 3.11.16 - Update yarl version from 1.18.3 to 1.19.0 - Modify pyproject.toml to include optional extras for Anthropic, Groq, and Google Gemini - Revise README.md to reflect new optional LLM provider installation instructions and clarify API key requirements * Remove deprecated packages from poetry.lock and update content hash - Removed cachetools, google-auth, google-genai, pyasn1, pyasn1-modules, rsa, and websockets from the lock file. - Added new extras for anthropic, google-genai, and groq. - Updated content hash to reflect changes. * Refactor import paths for GeminiClient in README and __init__.py - Updated import statement in README.md to reflect the new module structure for GeminiClient. - Removed GeminiClient from the __all__ list in __init__.py as it is no longer directly imported. * Refactor import paths for GeminiEmbedder in README and __init__.py - Updated import statement in README.md to reflect the new module structure for GeminiEmbedder. - Removed GeminiEmbedder and GeminiEmbedderConfig from the __all__ list in __init__.py as they are no longer directly imported.
68 lines
2.1 KiB
Python
68 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.
|
|
"""
|
|
|
|
from collections.abc import Iterable
|
|
|
|
from google import genai # type: ignore
|
|
from google.genai import types # type: ignore
|
|
from pydantic import Field
|
|
|
|
from .client import EmbedderClient, EmbedderConfig
|
|
|
|
DEFAULT_EMBEDDING_MODEL = 'embedding-001'
|
|
|
|
|
|
class GeminiEmbedderConfig(EmbedderConfig):
|
|
embedding_model: str = Field(default=DEFAULT_EMBEDDING_MODEL)
|
|
api_key: str | None = None
|
|
|
|
|
|
class GeminiEmbedder(EmbedderClient):
|
|
"""
|
|
Google Gemini Embedder Client
|
|
"""
|
|
|
|
def __init__(self, config: GeminiEmbedderConfig | None = None):
|
|
if config is None:
|
|
config = GeminiEmbedderConfig()
|
|
self.config = config
|
|
|
|
# Configure the Gemini API
|
|
self.client = genai.Client(
|
|
api_key=config.api_key,
|
|
)
|
|
|
|
async def create(
|
|
self, input_data: str | list[str] | Iterable[int] | Iterable[Iterable[int]]
|
|
) -> list[float]:
|
|
"""
|
|
Create embeddings for the given input data using Google's Gemini embedding model.
|
|
|
|
Args:
|
|
input_data: The input data to create embeddings for. Can be a string, list of strings,
|
|
or an iterable of integers or iterables of integers.
|
|
|
|
Returns:
|
|
A list of floats representing the embedding vector.
|
|
"""
|
|
# Generate embeddings
|
|
result = await self.client.aio.models.embed_content(
|
|
model=self.config.embedding_model or DEFAULT_EMBEDDING_MODEL,
|
|
contents=[input_data],
|
|
config=types.EmbedContentConfig(output_dimensionality=self.config.embedding_dim),
|
|
)
|
|
|
|
return result.embeddings[0].values
|