ADBPG Knowledge Base Management

Build enterprise knowledge bases in three steps: Create Knowledge Base → Upload Documents → Search & Q&A

The system automatically handles document parsing, chunking, vectorization, and index building. Users only need to focus on business logic.

Architecture: ADBPG Instance + Namespace + DocumentCollection + Vector Index + LLM Service

Core Concepts

• Knowledge Base: Container for documents, automatically manages vector indexes (corresponds to DocumentCollection in API)
• Document: Files uploaded to the knowledge base, supports PDF/Word/Markdown/HTML/JSON/CSV/images, etc.
• Q&A: Intelligent conversation based on knowledge base + large language model

Environment Setup