langchain/libs/community/langchain_community/retrievers/embedchain.py

72 lines
2.0 KiB
Python
Raw Normal View History

community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463) Moved the following modules to new package langchain-community in a backwards compatible fashion: ``` mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community mv langchain/langchain/adapters community/langchain_community mv langchain/langchain/callbacks community/langchain_community/callbacks mv langchain/langchain/chat_loaders community/langchain_community mv langchain/langchain/chat_models community/langchain_community mv langchain/langchain/document_loaders community/langchain_community mv langchain/langchain/docstore community/langchain_community mv langchain/langchain/document_transformers community/langchain_community mv langchain/langchain/embeddings community/langchain_community mv langchain/langchain/graphs community/langchain_community mv langchain/langchain/llms community/langchain_community mv langchain/langchain/memory/chat_message_histories community/langchain_community mv langchain/langchain/retrievers community/langchain_community mv langchain/langchain/storage community/langchain_community mv langchain/langchain/tools community/langchain_community mv langchain/langchain/utilities community/langchain_community mv langchain/langchain/vectorstores community/langchain_community mv langchain/langchain/agents/agent_toolkits community/langchain_community mv langchain/langchain/cache.py community/langchain_community ``` Moved the following to core ``` mv langchain/langchain/utils/json_schema.py core/langchain_core/utils mv langchain/langchain/utils/html.py core/langchain_core/utils mv langchain/langchain/utils/strings.py core/langchain_core/utils cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py rm langchain/langchain/utils/env.py ``` See .scripts/community_split/script_integrations.sh for all changes
2023-12-11 21:53:30 +00:00
"""Wrapper around Embedchain Retriever."""
from __future__ import annotations
from typing import Any, Iterable, List, Optional
from langchain_core.callbacks import CallbackManagerForRetrieverRun
from langchain_core.documents import Document
from langchain_core.retrievers import BaseRetriever
class EmbedchainRetriever(BaseRetriever):
"""`Embedchain` retriever."""
client: Any
"""Embedchain Pipeline."""
@classmethod
def create(cls, yaml_path: Optional[str] = None) -> EmbedchainRetriever:
"""
Create a EmbedchainRetriever from a YAML configuration file.
Args:
yaml_path: Path to the YAML configuration file. If not provided,
a default configuration is used.
Returns:
An instance of EmbedchainRetriever.
"""
from embedchain import Pipeline
# Create an Embedchain Pipeline instance
if yaml_path:
client = Pipeline.from_config(yaml_path=yaml_path)
else:
client = Pipeline()
return cls(client=client)
def add_texts(
self,
texts: Iterable[str],
) -> List[str]:
"""Run more texts through the embeddings and add to the retriever.
Args:
texts: Iterable of strings/URLs to add to the retriever.
Returns:
List of ids from adding the texts into the retriever.
"""
ids = []
for text in texts:
_id = self.client.add(text)
ids.append(_id)
return ids
def _get_relevant_documents(
self, query: str, *, run_manager: CallbackManagerForRetrieverRun
) -> List[Document]:
res = self.client.search(query)
docs = []
for r in res:
docs.append(
Document(
page_content=r["context"],
metadata={"source": r["source"], "document_id": r["document_id"]},
)
)
return docs