https://github.com/nirantk/rag-to-riches
https://github.com/nirantk/rag-to-riches
evals rag search
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/nirantk/rag-to-riches
- Owner: NirantK
- License: mit
- Created: 2024-09-13T12:10:47.000Z (9 months ago)
- Default Branch: main
- Last Pushed: 2025-04-10T12:16:00.000Z (about 2 months ago)
- Last Synced: 2025-04-12T06:07:36.800Z (about 2 months ago)
- Topics: evals, rag, search
- Language: Jupyter Notebook
- Homepage: https://maven.com/nirantk/search-for-rag
- Size: 1.23 MB
- Stars: 22
- Watchers: 1
- Forks: 7
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ๐ RAG to Riches
> A comprehensive course on building production-ready RAG (Retrieval Augmented Generation) systems
[](https://maven.com/nirantk/rag-to-riches)
[](https://nirantk.com)This repository contains all the code and datasets used in the [Search for RAG](https://maven.com/nirantk/rag-to-riches) course. Guest speakers are encouraged to contribute their code, notebooks, and datasets by raising a PR to the respective folders.
## ๐ Course Curriculum
### Module 1: Foundations of RAG
- **01 RAG Evals** ๐
- Understanding RAG metrics and evaluation frameworks
- Setting up evaluation pipelines
- Best practices for RAG testing- **02 Query Understanding** ๐ญ
- Query analysis techniques
- Query expansion and reformulation
- Handling different query types and intents- **03 Jerry Liu** ๐๏ธ 
- Hybrid search approaches
- Multi-stage retrieval
- Custom retrievers and rankers### Module 2: Advanced RAG Techniques
- **04 Ofer** โก 
- Performance optimization strategies
- Caching and indexing techniques
- Scaling RAG systems- **05 Automatic Prompting** ๐ค
- Dynamic prompt generation
- Prompt optimization techniques
- Automated prompt testing- **06 Working with Complex Docs** ๐
- Handling structured and unstructured documents
- Document chunking strategies
- Multi-modal document processing### Module 3: Industry Applications
- **07 Aditya Gushwork** ๐ข 
- Enterprise-grade RAG implementations
- Security and compliance considerations
- Integration patterns- **08 John Gilhuly** ๐ 
- Deployment strategies
- Monitoring and observability
- Production best practices### Module 4: Advanced Topics
- **09 Neural IR** ๐ง
- Neural search architectures
- Dense retrievers
- Cross-encoders and bi-encoders- **10 Testset Generation** ๐งช
- Synthetic data generation
- Test set validation
- Quality assurance techniques- **11 Embedding Models** ๐ค
- Understanding embedding spaces
- Model selection and fine-tuning
- Multi-modal embeddings### Module 5: Optimization and Tricks
- **12 Vectorsearch Tricks** ๐ฏ
- Advanced indexing techniques
- Query optimization
- Performance tuning- **13 Shreya Shankar** ๐๏ธ 
- System architecture patterns
- Scalability considerations
- Error handling and recovery### Module 6: Specialized Applications
- **14 Atita Arora** ๐ฏ 
- Industry-specific implementations
- Custom knowledge bases
- Specialized retrieval techniques- **15 Text Profiling** ๐
- Text classification
- Content analysis
- Metadata extraction- **16 Alberto Romero** ๐ฎ 
- Emerging trends
- Research directions
- Future applications### Additional Resources
- **Lab01 Finance Bench** ๐ฐ
- Finance-specific RAG implementations
- **Office Hours** ๐ฅ
- Recordings and materials from office hours---