Couchbase

Couchbase is a distributed, JSON document database, with all the desired capabilities of a relational DBMS.

Categories: Artificial Intelligence

Type: couchbase/v1

Connections

Version: 1

custom

Properties

Name	Label	Type	Description	Required
connectionString	Connection String	STRING	A couchbase connection string	true
username	Username	STRING	Username for authentication with Couchbase.	true
password	Password	STRING	Password for authentication with Couchbase.	true
indexName	Index Name	STRING	The name of the index to store the vectors.	false
bucketName	Bucket Name	STRING	The name of the Couchbase Bucket, parent of the scope.	false
scopeName	Scope Name	STRING	The name of the Couchbase scope, parent of the collection. Search queries will be executed in the scope context.	false
collectionName	Collection Name	STRING	The name of the Couchbase collection to store the Documents.	false
dimensions	Dimensions	INTEGER	The number of dimensions in the vector.	false
similarity	Similarity	STRING Options l2_norm, dot_product	The similarity function to use.	true
optimization	Optimization	STRING Options latency, recall	The index optimization strategy to use.	false
initializeSchema	Initialize Schema	BOOLEAN Options true, false	Whether to initialize the schema.	false

Connection Setup

Official documentation

Step-by-step guide:

Create a Cluster, click on it
Go to Buckets, Create a Bucket
Go to Settings → Networking → Allow IP Addresses, Allow your current IP address
Go to Settings → Security, Create Access (username and password)
Go to Data Tools → Search, Create a Search Index
Go to Connect, Copy Public Connection String

Now you have Public Connection String, Username, Password, Index Name and can create a connection

Actions

Load Data

Name: load

Loads data into the vector store using LLM embeddings.

Example JSON Structure

{
  "label" : "Load Data",
  "name" : "load",
  "type" : "couchbase/v1/load"
}

Output

This action does not produce any output.

Search Data

Name: search

Query data from the vector store using LLM embeddings.

Properties

Name	Label	Type	Description	Required
query	Query	STRING	The query to be executed.	true

Example JSON Structure

{
  "label" : "Search Data",
  "name" : "search",
  "parameters" : {
    "query" : ""
  },
  "type" : "couchbase/v1/search"
}

Output

The output for this action is dynamic and may vary depending on the input parameters. To determine the exact structure of the output, you need to execute the action.

On this page