Search the knowledge base for relevant documents.

This tool uses hybrid search (semantic + keyword) to find the most relevant documents matching your query. Results include source citations for reference.

Parameters:

• query: Your search question or keywords

• top_k: Maximum number of results (default: 5)

• collection: Limit search to a specific document collection

List all available document collections in the knowledge base.

Returns information about each collection including:

• Collection name

• Document count (if include_stats=true)

• Collection metadata

Use this tool to discover available collections before querying.

Get summary and metadata for a specific document.

Returns structured information about a document including:

• Title (extracted or inferred from content)

• Summary (first chunk preview or metadata summary)

• Tags (document-level tags/categories)

• Source path

• Chunk count

Use this tool after list_collections to get details about specific documents.

Delete a document and its associated data from the RAG knowledge base.

First call without confirm_delete_data (or with confirm_delete_data=false) to preview what will be deleted (chunk count, image count). Then call again with confirm_delete_data=true to execute the deletion.

This removes all associated data: vector embeddings, BM25 index entries, extracted images, and the ingestion history record.

Ingest a document file into the knowledge hub.

Supports PDF, Markdown (.md/.markdown), and source code (.py, .c, .cpp, etc.). The document is parsed, chunked, embedded, and stored for later retrieval.

Parameters:

• file_path: Absolute or relative path to the file to ingest

• collection: Target collection name (default: "default")