Knowledgebase RAG System - Intelligent Chatbot Integration
RAG-based Question-Answering with Document, FAQ and News Integration
Project Description
Key Features
RAG-based Answer Generation
OpenAI models with structured JSON responses
Vector Search
Embedding-based document similarity search
Document Integration
Automatic indexing and vectorization of documents
FAQ Integration
Keyword-based FAQ search with scoring
News Integration
News article search as fallback information source
Question Management
Automatic storage and management of unanswered questions
Agentic Orchestrator
Multi-step chat agent that plans retrieval and tool use
Hybrid Retrieval
Combine keyword and vector signals for better grounding
Vector Store & MCP Tools
Persistent vector index with MCP-accessible retrieval tools
Technology Stack
Backend Framework
AI & ML
Frontend
Data Management
Workflow
- User Query: User asks a question in the chatbot
- FAQ Search: System searches in FAQ files with keyword matching and scoring
- Knowledgebase Search: If FAQ score is low, system searches in vectorized documents
- Context Formatting: Search results are formatted as TOON (Token-Oriented Object Notation)
- Answer Generation: OpenAI GPT-4o-mini generates answer based on context with JSON schema
- Source Display: Relevant document sources are displayed with chunk information
- Question Storage: If no answer found, question is automatically stored for review
- News Fallback: If no document match, system searches in news articles
- Agentic Path: Orchestrator selects tools, hybrid retrieval, and vector store lookups