9ab8abf9b4
* Refactor group_id handling and update dependencies - Changed default behavior for `group_id` to 'default' instead of generating a UUID. - Updated README to reflect the new default behavior for `--group-id`. - Reformatted LLMConfig initialization for better readability. - Bumped versions of several dependencies including `azure-core`, `azure-identity`, `certifi`, `charset-normalizer`, `sse-starlette`, and `typing-inspection`. - Added `python-multipart` as a new dependency. This update improves usability and ensures compatibility with the latest library versions. * Update Graphiti MCP server instructions and refactor method names for clarity - Revised the welcome message to enhance clarity about Graphiti's functionality. - Renamed methods for better understanding: `add_episode` to `add_memory`, `search_nodes` to `search_memory_nodes`, `search_facts` to `search_memory_facts`, and updated related docstrings to reflect these changes. - Updated references to "knowledge graph" to "graph memory" for consistency throughout the codebase. * Update README for Graphiti MCP server configuration and integration with Claude Desktop - Changed server name from "graphiti" to "graphiti-memory" in configuration examples for clarity. - Added instructions for running the Graphiti MCP server using Docker. - Included detailed steps for integrating Claude Desktop with the Graphiti MCP server, including optional installation of `mcp-remote`. - Enhanced overall documentation to improve user experience and understanding of the setup process. * Enhance error handling in GeminiEmbedder and GeminiClient - Added checks to raise exceptions when no embeddings or response text are returned, improving robustness. - Included type ignore comments for mypy compatibility in embed_content calls. * Update graphiti_core/embedder/gemini.py Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> * Update graphiti_core/llm_client/gemini_client.py Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com> --------- Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
84 lines
3 KiB
Python
84 lines
3 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], # type: ignore[arg-type] # mypy fails on broad union type
|
|
config=types.EmbedContentConfig(output_dimensionality=self.config.embedding_dim),
|
|
)
|
|
|
|
if not result.embeddings or len(result.embeddings) == 0 or not result.embeddings[0].values:
|
|
raise ValueError('No embeddings returned from Gemini API in create()')
|
|
|
|
return result.embeddings[0].values
|
|
|
|
async def create_batch(self, input_data_list: list[str]) -> list[list[float]]:
|
|
# Generate embeddings
|
|
result = await self.client.aio.models.embed_content(
|
|
model=self.config.embedding_model or DEFAULT_EMBEDDING_MODEL,
|
|
contents=input_data_list, # type: ignore[arg-type] # mypy fails on broad union type
|
|
config=types.EmbedContentConfig(output_dimensionality=self.config.embedding_dim),
|
|
)
|
|
|
|
if not result.embeddings or len(result.embeddings) == 0:
|
|
raise Exception('No embeddings returned')
|
|
|
|
return [embedding.values if embedding.values else [] for embedding in result.embeddings]
|