Astra DB in Langflow
The Astra DB component creates a vector store that uses Astra DB as the underlying database to store and retrieve documents.
The Vector Store RAG guide demonstrates how to use the Astra DB component in a template flow, but you can use the Astra components as the vector store in any Langflow application.
For information about non-Astra components, see the Langflow component documentation. |
Add an Astra DB component in Langflow
The Astra DB component initializes an Astra DB vector store with vector indexes to efficiently store and retrieve documents.
To add the Astra DB component to your Langflow canvas:
-
In Langflow’s Basic Components menu, select Vector Stores > Astra DB.
-
Click and drag the component to the Canvas.
-
In the Token field, enter your Astra DB authentication token, or select it from the dropdown list if you’ve created a global variable.
-
In the Database field, select your existing database from the dropdown menu, or select Create new database. For more information, see Create a database.
Astra organizations on the Free plan can create up to five databases. If you reach the limit, the Create new database option becomes inactive.
To re-enable database creation, either terminate an existing database or upgrade your plan.
-
In the Collection field, select your existing collection from the dropdown menu, or select Create new collection. For more information, see Manage collections and tables.
Your component is ready to use in a flow. See Astra component inputs and outputs for information on how to connect the Astra component to other components in a flow.
Astra DB component parameters
To open Advanced Settings for this component, from the Astra DB component’s top menu, select more_horiz > Advanced.
Field | Description |
---|---|
Collection Name |
The name of the collection within Astra DB where the vectors will be stored. |
Astra DB Application Token |
Authentication token for accessing Astra DB. |
API Endpoint |
API endpoint URL for the Astra DB service. |
Search Input |
Input for search queries. |
Ingest Data |
Data to be ingested into the vector store. |
Namespace |
Optional namespace within Astra DB to use for the collection. |
Metric |
Optional distance metric for vector comparisons in the vector store. Options include cosine, dot_product, and euclidean. |
Batch Size |
Optional number of data to process in a single batch. |
Bulk Insert Batch Concurrency |
Optional concurrency level for bulk insert operations. |
Bulk Insert Overwrite Concurrency |
Optional concurrency level for bulk insert operations that overwrite existing data. |
Bulk Delete Concurrency |
Optional concurrency level for bulk delete operations. |
Setup Mode |
Configuration mode for setting up the vector store, with options for "Sync", "Async", or "Off". |
Pre Delete Collection |
Boolean flag to determine whether to delete the collection before creating a new one. |
Metadata Indexing Include |
Optional list of metadata fields to include in the indexing. |
Embedding or Astra Vectorize |
Allows either an embedding model or an Astra Vectorize configuration. |
Metadata Indexing Exclude |
Optional list of metadata fields to exclude from the indexing. |
Collection Indexing Policy |
Optional dictionary defining the indexing policy for the collection. |
Number of Results |
Number of results to return. |
Search Type |
Search type to use. Options include "Similarity", "Similarity with score threshold", and "MMR (Max Marginal Relevance)". |
Search Score Threshold |
Minimum similarity score threshold for search results when using "Similarity with score threshold". |
Search Metadata Filter |
Optional dictionary of filters to apply to the search query. |
Astra component inputs and outputs
To see a component’s acceptable inputs, hover over the blue circles on the left side of the component.
To see a component’s acceptable outputs, hover over the orange circles on the right side of the component.
To see a component’s embeddings model, hover over the green circle on the component.
To connect the Astra DB component to a flow, click and drag inside one of the circles to another component of an acceptable type. For example, drag a line from the Astra DB component’s Embeddings circle to the Embeddings circle of an OpenAI Embeddings component.
For an example of how to wire the Astra component in a RAG application flow, see the Vector Store RAG.