datavector index search

Vector Index Search

vector_index_search

Builds and searches a local vector index using an explicitly configured localhost embedding endpoint such as Ollama. Use when TF-IDF semantic_search is insufficient and an agent needs embedding-based relevance. Indexing writes a local JSON index only after confirm_write=true; embedding requests are rejected unless the endpoint is localhost. Not for remote embedding APIs or automatic background indexing.

How to use vector_index_search

Provide only the required inputs below. Start with the smallest scope that answers the task, then review the risk properties before an agent executes the call.

Risk and execution properties

Read only: yes

Destructive: no

Idempotent: yes

Open world: no — operates locally or through configured services

Inputs

actionstringrequired

Use index to build a local index or search to query an existing one.

Allowed: "index""search"

pathstring

Directory to index. Required for action=index.

index_pathstringrequired

Explicit local path for the JSON vector index.

querystring

Search query. Required for action=search.

modelstring

Embedding model served by the local endpoint.

Default: "nomic-embed-text"

endpointstring

Localhost embedding API endpoint only.

Default: "http://127.0.0.1:11434/api/embed"

file_extensionsarray

Optional source file extension filter when indexing.

confirm_writeboolean

Must be true to create or overwrite the index file.

Default: false

max_resultsinteger

Maximum search results. Max: 100.

Default: 10

Example input

{
  "action": "index",
  "path": "<string>",
  "index_path": "<string>",
  "query": "<string>",
  "model": "nomic-embed-text",
  "endpoint": "http://127.0.0.1:11434/api/embed",
  "file_extensions": "<array>",
  "confirm_write": false,
  "max_results": 10
}

Browse or search the full 74-tool reference to choose the smallest suitable capability.

Browse all tools →