View as Markdown
Databricks (Service Principal) icon

Databricks (Service Principal) ACTION

Query Vector Search Index

Query a specific vector search index in Databricks. See the documentation
  • Action
  • Read only
  • OAuth
  • SDK
  • MCP

IMPLEMENTATION

Call this tool

Connect a user's Databricks (Service Principal) account once, then configure and run Query Vector Search Index from your backend or agent.

import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "databricks_oauth-query-vector-search-index",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    databricks_oauth: { authProvisionId: "apn_xxxxxxx" },
    endpointName: "Endpoint Name",
    indexName: "Index Name",
  },
})

console.log(result)

SCHEMA

Inputs

Pipedream supplies the connected account. Your application provides the operation-specific values below. Dynamic inputs are resolved against that user's account.

Query Vector Search Index inputs
Property Type Description
endpointName Endpoint Name string
The name of the vector search endpoint
Required Dynamic
indexName Index Name string
The name of the vector search index
Required Dynamic
columns Columns string[]
List of column names to include in the response. Example: ["id"]
Required
queryText Query Text string
Free-text query for semantic search.
Optional
queryVector Query Vector string
JSON array of floats representing the embedding vector for the query.
Optional
filtersJson Filters JSON string
JSON string representing query filters. Example: { "id <": 5 }
Optional
numResults Number of Results integer
Number of results to return. Defaults to 10.
Optional
includeEmbeddings Include Embeddings boolean
Whether to include the embedding vectors in the results.
Optional

REFERENCE

Tool details

Behavior hints are published with the component in the Pipedream registry and surface as MCP tool annotations, so an agent can reason about a tool before it calls it.

Registry key
databricks_oauth-query-vector-search-index
Version
0.0.1
App
Databricks (Service Principal)
Authentication
OAuth
Read-only
Yes
Destructive
No
Open world
Yes