Skip to content
Nappai Documentation

Cassandra

Cassandra stores documents in an Apache Cassandra table, or an Astra DB database, and searches it by meaning.

A vector database stores texts so they can be searched by meaning, not just by exact words. That way an agent can find the paragraph of a manual that answers a question even if it uses different words.

When to use it

  • Your company already works with Cassandra and wants to use it as a knowledge base.
  • You want stored texts to expire after some time.
  • You need to combine search by meaning with words that must appear in the text.

Configuration

The Operation field decides what the component does, and the fields and outputs change with your choice:

  • Add (default): stores in the database the documents it receives in Ingest Data.
  • Search: finds the documents closest to the text in Search Query.
  • Retriever: offers the database as a search engine for another component to use, for example an agent or a question-answering chain.

You need a Cassandra DB credential with your Cassandra database connection details. See Credentials.

FieldWhat it does
Credential (required)The Cassandra DB credential with the connection details.
OperationWhat the component does: Add, Search or Retriever.
Ingest Data (required)With Add. The documents to store, usually those coming out of a text splitter or a file loader.
Search QueryWith Search. The text to search for. If left empty, nothing is returned.
EmbeddingThe connector where you plug the component that turns texts into numbers to compare them by meaning, such as OpenAI Embeddings. Always use the same one to store and to search.
Keyspace (required)The table’s keyspace, or the namespace if it is Astra DB.
Table Name (required)The table where documents are stored.

Advanced options

FieldWhat it does
Number Of ResultsHow many documents each search returns. Default: 4.
TTL SecondsIf set, stored texts are deleted automatically after that time, in seconds.
Batch SizeHow many documents are stored in each batch. Default: 16.
Setup ModeHow the table is set up: Sync (default), Async or Off.
Cluster ArgumentsExtra cluster connection settings, if whoever runs it gives you any.
Enable Body SearchAllows also searching by words in the text with Search Body. It must be on before the table is created.
Search BodyWords that must appear in the text of the documents found.
Search TypeHow to search: Similarity, Similarity with score threshold, MMR (Max Marginal Relevance). Similarity returns the closest; with a threshold, only those above Search Score Threshold; MMR looks for close but varied results.
Search Score ThresholdMinimum similarity score, only with the threshold search. Default: 0.0.
Search Metadata FilterField and value pairs to search only among the documents that match them.

Output

The outputs depend on Operation:

  • Results: with Add and Search. With Search, the list of documents found, which you can pass to a prompt or an agent.
  • Vector Store: with Add. The database, to connect it to components that work with a vector database.
  • Retriever: with Retriever. The search engine, to connect it to components that ask for one.

In tool mode, an agent can use the component to search by itself. See Tool Mode.

Example

A telecom company keeps solved incidents in Cassandra so support can find similar cases.

  1. Add Cassandra with Operation set to Search, the keyspace and the table.
  2. Connect the same embeddings component they were stored with.
  3. Type the new incident’s description in Search Query.