Can I add metadata to my documents in Doc Lib?

Yes, Doc Lib allows you to add tags and update metadata for individual chunks or entire sources. This helps with categorization and filtering during semantic search.

What file types does Doc Lib support for ingestion?

Doc Lib ingests and chunks Markdown, Python, OpenAPI JSON, and HTML files. It also supports ingesting from URLs and raw text/code strings.

What is the purpose of the note management feature?

Doc Lib includes a simple note storage system with a custom URI scheme, allowing you to create, store, and summarize notes alongside your documentation.

How does semantic search work in Doc Lib?

Doc Lib performs vector-based semantic search over ingested content, allowing you to find relevant chunks based on meaning, even without exact keyword matches. You can filter by chunk type and tags.

How can I debug Doc Lib when using it as an MCP server?

For the best debugging experience, use the MCP Inspector. It provides a URL that you can access in your browser to inspect and debug the server.

Doc Lib

Name: Doc Lib
Author: shifusen329

0•

Manages document ingestion, chunking, semantic search, and note management.

Doc Lib is a Model Context Protocol (MCP) server that facilitates document processing for AI applications. It allows users to ingest various file types (Markdown, Python, OpenAPI, HTML) and URLs, chunk them into manageable segments, perform semantic searches, and manage notes. The server offers tools for adding notes, ingesting content, searching chunks, deleting sources or chunks, updating chunk metadata, and retrieving context for AI models. It also supports batch ingestion and tagging for enhanced organization and retrieval of information.

主な機能

01Ingests and chunks Markdown, Python, OpenAPI, and HTML files.

020 GitHub stars

03Provides tools to add, delete, and update chunks and their metadata.

04Performs semantic search over ingested content with filtering options.

05Supports batch ingestion and tagging of documentation files.

06Manages notes with a custom URI scheme.

ユースケース

01Providing context to AI models by retrieving relevant document chunks.

02Building knowledge bases from various document formats.

03Implementing semantic search in documentation or code repositories.