zhizhunbao RAG Learning
Learning Path
Level 1: Minimal RAG
Build working RAG with LangChain + Chroma in 30 minutes.
For step-by-step: See references/level1-minimal.md
Level 2: Core Components
Understand and experiment with each RAG component.
For details: See references/level2-components.md
Level 3: Real Documents
Handle PDF, web pages, tables. Build personal knowledge base.
For details: See references/level3-documents.md
Level 4: Optimization
Implement Hybrid Search, Reranking, better prompts.
For details: See references/level4-optimization.md
Level 5: Production
Compare frameworks, choose vector DB, add caching.
For details: See references/level5-production.md
Quick Reference
Frameworks by Use Case
| Use Case | Framework | Why |
|---|---|---|
| Quick prototype | LangChain | Most examples, easy start |
| Data-heavy apps | LlamaIndex | Best data connectors |
| No prompting | DSPy | Programmatic LLM |
| Production RAG | RAGFlow | End-to-end solution |
Common Issues
| Problem | Solution |
|---|---|
| Chunk too large/small | Adjust chunk_size (500-1000 tokens) |
| Wrong embedding model | Try domain-specific model |
| Retrieved but wrong answer | Check prompt template |
| No results | Lower similarity threshold |
| Slow retrieval | Add caching, use hybrid search |
Resources
- LangChain - 124k stars
- LlamaIndex - 46k stars
- RAGFlow - 71k stars
- DSPy - 31k stars
- Chonkie - Lightweight chunking