Skip to main content
Open on GitHub

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.

See a tutorial provided by DataStax.

Installation and Setup​

Install the following Python package:

pip install "langchain-astradb>=0.1.0"

Get the connection secrets. Set up the following environment variables:

ASTRA_DB_APPLICATION_TOKEN="TOKEN"
ASTRA_DB_API_ENDPOINT="API_ENDPOINT"

Vector Store​

from langchain_astradb import AstraDBVectorStore

vector_store = AstraDBVectorStore(
    embedding=my_embedding,
    collection_name="my_store",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)
API Reference:AstraDBVectorStore

Learn more in the example notebook.

See the example provided by DataStax.

Chat message history​

from langchain_astradb import AstraDBChatMessageHistory

message_history = AstraDBChatMessageHistory(
    session_id="test-session",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)

See the usage example.

LLM Cache​

from langchain.globals import set_llm_cache
from langchain_astradb import AstraDBCache

set_llm_cache(AstraDBCache(
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
))
API Reference:set_llm_cache | AstraDBCache

Learn more in the example notebook (scroll to the Astra DB section).

Semantic LLM Cache​

from langchain.globals import set_llm_cache
from langchain_astradb import AstraDBSemanticCache

set_llm_cache(AstraDBSemanticCache(
    embedding=my_embedding,
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
))

Learn more in the example notebook (scroll to the appropriate section).

Learn more in the example notebook.

Document loader​

from langchain_astradb import AstraDBLoader

loader = AstraDBLoader(
    collection_name="my_collection",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)
API Reference:AstraDBLoader

Learn more in the example notebook.

Self-querying retriever​

from langchain_astradb import AstraDBVectorStore
from langchain.retrievers.self_query.base import SelfQueryRetriever

vector_store = AstraDBVectorStore(
    embedding=my_embedding,
    collection_name="my_store",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)

retriever = SelfQueryRetriever.from_llm(
    my_llm,
    vector_store,
    document_content_description,
    metadata_field_info
)

Learn more in the example notebook.

Store​

from langchain_astradb import AstraDBStore

store = AstraDBStore(
    collection_name="my_kv_store",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)
API Reference:AstraDBStore

See the API Reference for the AstraDBStore.

Byte Store​

from langchain_astradb import AstraDBByteStore

store = AstraDBByteStore(
    collection_name="my_kv_store",
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    token=ASTRA_DB_APPLICATION_TOKEN,
)
API Reference:AstraDBByteStore

See the API reference for the AstraDBByteStore.

Was this page helpful?