SERVICE & TOOLS
PageIndex
PageIndex — web indexing and retrieval service (auth required)
9 available tools
find_
Search documents by query. Uses fast keyword matching against names and descriptions first; automatically falls back to AI semantic ranking when no keyword results are found. Best for specific terms, …
list_
List user's folders. Filter by parent_folder_id to get children of a specific folder, use null for root folders, or omit to get all folders.
get_
Get detailed information about a specific document by name. Requires: doc_name (string). Optional: wait_for_completion (boolean) to automatically wait up to 3 minutes if document is still processing. …
get_
Retrieve an embedded image from a document. Requires image_path from get_page_content() response, format: <docName>/<imagePath> (e.g. MyDoc.pdf/figures/fig1.png). Returns image_base64 and content_type…
get_
Extract the hierarchical structure of a completed document. Optional: wait_for_completion (boolean) to wait up to 3 minutes if still processing. Returns structured outline with headers, sections, and …
get_
Extract specific page content from processed documents. Flexible page selection: single page ('5'), ranges ('3-7'), or multiple pages ('1,5,10'). Use tight, targeted ranges and split into multiple cal…
process_
Upload and process PDF documents from public URLs. Only invoke with a valid, accessible PDF URL. If the user hasn't provided one, ask for it instead of guessing. Returns document name for subsequent o…
recent_
Browse your document collection with pagination. Returns documents sorted by upload date (newest first) with processing status. Supports cursor-based pagination for browsing large collections. Use thi…
remove_
Permanently delete documents and all associated data. Only invoke when the user explicitly names the documents AND confirms deletion. Accepts an array of document names for batch deletion (maximum 10 …