DataStax Astra DB is a serverless
AI-ready database built on Apache Cassandra® and made conveniently available
through an easy-to-use JSON API.
Overview
The Astra DB Document Loader returns a list of LangChainDocument objects read from an Astra DB collection.
The loader takes the following parameters:
- api_endpoint: Astra DB API endpoint. Looks like- https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com
- token: Astra DB token. Looks like- AstraCS:aBcD0123...
- collection_name: AstraDB collection name
- namespace: (Optional) AstraDB namespace (called keyspace in Astra DB)
- filter_criteria: (Optional) Filter used in the find query
- projection: (Optional) Projection used in the find query
- limit: (Optional) Maximum number of documents to retrieve
- extraction_function: (Optional) A function to convert the AstraDB document to the LangChain- page_contentstring. Defaults to- json.dumps
Setup
Load documents with the Document Loader
AstraDBLoader
Connect these docs programmatically to Claude, VSCode, and more via MCP for    real-time answers.