mirror of
https://github.com/hwchase17/langchain
synced 2024-10-31 15:20:26 +00:00
fa5d49f2c1
ran ```bash g grep -l "langchain.vectorstores" | xargs -L 1 sed -i '' "s/langchain\.vectorstores/langchain_community.vectorstores/g" g grep -l "langchain.document_loaders" | xargs -L 1 sed -i '' "s/langchain\.document_loaders/langchain_community.document_loaders/g" g grep -l "langchain.chat_loaders" | xargs -L 1 sed -i '' "s/langchain\.chat_loaders/langchain_community.chat_loaders/g" g grep -l "langchain.document_transformers" | xargs -L 1 sed -i '' "s/langchain\.document_transformers/langchain_community.document_transformers/g" g grep -l "langchain\.graphs" | xargs -L 1 sed -i '' "s/langchain\.graphs/langchain_community.graphs/g" g grep -l "langchain\.memory\.chat_message_histories" | xargs -L 1 sed -i '' "s/langchain\.memory\.chat_message_histories/langchain_community.chat_message_histories/g" gco master libs/langchain/tests/unit_tests/*/test_imports.py gco master libs/langchain/tests/unit_tests/**/test_public_api.py ```
38 lines
1.2 KiB
Python
38 lines
1.2 KiB
Python
# Ingest Documents into a Zep Collection
|
|
import os
|
|
|
|
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
|
from langchain_community.document_loaders import WebBaseLoader
|
|
from langchain_community.embeddings import FakeEmbeddings
|
|
from langchain_community.vectorstores.zep import CollectionConfig, ZepVectorStore
|
|
|
|
ZEP_API_URL = os.environ.get("ZEP_API_URL", "http://localhost:8000")
|
|
ZEP_API_KEY = os.environ.get("ZEP_API_KEY", None)
|
|
ZEP_COLLECTION_NAME = os.environ.get("ZEP_COLLECTION", "langchaintest")
|
|
|
|
collection_config = CollectionConfig(
|
|
name=ZEP_COLLECTION_NAME,
|
|
description="Zep collection for LangChain",
|
|
metadata={},
|
|
embedding_dimensions=1536,
|
|
is_auto_embedded=True,
|
|
)
|
|
|
|
# Load
|
|
loader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")
|
|
data = loader.load()
|
|
|
|
# Split
|
|
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)
|
|
all_splits = text_splitter.split_documents(data)
|
|
|
|
# Add to vectorDB
|
|
vectorstore = ZepVectorStore.from_documents(
|
|
documents=all_splits,
|
|
collection_name=ZEP_COLLECTION_NAME,
|
|
config=collection_config,
|
|
api_url=ZEP_API_URL,
|
|
api_key=ZEP_API_KEY,
|
|
embedding=FakeEmbeddings(size=1),
|
|
)
|