mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
6d863bed51
**Description** This PR sets the "caller identity" of the Astra DB clients used by the integration plugins (`AstraDBChatMessageHistory`, `AstraDBStore`, `AstraDBByteStore` and, pending #17767 , `AstraDBVectorStore`). In this way, the requests to the Astra DB Data API coming from within LangChain are identified as such (the purpose is anonymous usage stats to best improve the Astra DB service). |
||
---|---|---|
.. | ||
langchain_astradb | ||
scripts | ||
tests | ||
.gitignore | ||
LICENSE | ||
Makefile | ||
poetry.lock | ||
pyproject.toml | ||
README.md |
langchain-astradb
This package contains the LangChain integrations for using DataStax Astra DB.
DataStax Astra DB is a serverless vector-capable database built on Apache Cassandra® and made conveniently available through an easy-to-use JSON API.
Note. For a short transitional period, only some of the Astra DB integration classes are contained in this package (the remaining ones being still in langchain-community
). In a short while, and surely by version 0.2 of LangChain, all of the Astra DB support will be removed from langchain-community
and included in this package.
Installation and Setup
Installation of this partner package:
pip install langchain-astradb
Integrations overview
Vector Store
from langchain_astradb import AstraDBVectorStore
my_store = AstraDBVectorStore(
embedding=my_embeddings,
collection_name="my_store",
api_endpoint="https://...",
token="AstraCS:...",
)
Chat message history
from langchain_astradb import AstraDBChatMessageHistory
message_history = AstraDBChatMessageHistory(
session_id="test-session",
api_endpoint="...",
token="...",
)
Store
from langchain_astradb import AstraDBStore
store = AstraDBStore(
collection_name="my_kv_store",
api_endpoint="...",
token="..."
)
Byte Store
from langchain_astradb import AstraDBByteStore
store = AstraDBByteStore(
collection_name="my_kv_store",
api_endpoint="...",
token="..."
)
Reference
See the LangChain docs page for a more detailed listing.