How sushantbrpl/awesome-rag-production works
Awesome RAG Production is a curated guide for engineers choosing and operating production RAG systems. The principal workflow is to use its decision guide and reference stacks, then explore resources across the RAG lifecycle and operational concerns. Supporting material adds benchmarks, datasets, case studies, and pitfalls. The README also describes weekly freshness auditing; sampled source confirms the discovery script queries GitHub and checks the README and benchmarks before writing proposed updates. Other resource sections are documented in the README but their individual entries were not sampled.
Main entry points: discovery_engine.py Freshness discovery · README.md Decision guide · benchmarks.md Benchmarks · showcase.md Case studies
Components 31
Selection guidance
- Decision guide
README.md - Reference architectures
README.md - Frameworks
README.md
RAG capabilities
- Data ingestion
README.md - Embedding models
README.md - Vector databases
README.md - Data versioning
README.md - Chunking
README.md - Retrieval and reranking
README.md - Query routing
README.md - Agentic RAG
README.md - Agent memory
README.md - Multimodal RAG
README.md - Structured and SQL RAG
README.md
Production operations
- Evaluation
README.md - Observability
README.md - Deployment
README.md - Caching and performance
README.md - Security and compliance
README.md - LLM gateways
README.md - FinOps
README.md
Evidence and curation
- Case studies
showcase.md - Benchmarks
benchmarks.md - Datasets
datasets.md - RAG pitfalls
rag-pitfalls.md - Books
books.md - Blogs
blogs.md - Freshness discovery
scripts/discovery_engine.py - Proposed updates
.github/PROPOSED_UPDATES.md
Other components
- Engineer
- GitHub API
Connections 31
- Engineer → Decision guide: uses to choose
- Engineer → Reference architectures: consults
- Engineer → Frameworks: explores
- Engineer → Data ingestion: explores
- Engineer → Embedding models: explores
- Engineer → Vector databases: explores
- Engineer → Data versioning: explores
- Engineer → Chunking: explores
- Engineer → Retrieval and reranking: explores
- Engineer → Query routing: explores
- Engineer → Agentic RAG: explores
- Engineer → Agent memory: explores
- Engineer → Multimodal RAG: explores
- Engineer → Structured and SQL RAG: explores
- Engineer → Evaluation: explores
- Engineer → Observability: explores
- Engineer → Deployment: explores
- Engineer → Caching and performance: explores
- Engineer → Security and compliance: explores
- Engineer → LLM gateways: explores
- Engineer → FinOps: explores
- Engineer → Case studies: consults
- Engineer → Benchmarks: consults
- Engineer → Datasets: consults
- Engineer → RAG pitfalls: consults
- Engineer → Books: consults
- Engineer → Blogs: consults
- Freshness discovery → GitHub API: queries
- Freshness discovery → Benchmarks: checks freshness
- Freshness discovery → Decision guide: audits listed tools
- Freshness discovery → Proposed updates: writes report