Section 13
Retrieval Augmented Generation (RAG)
Architecting systems that ground LLMs in private data using Vector Databases (Pinecone, FAISS).
Projects in this section: 0
Retrieval Augmented Generation (RAG)GitHub
DocSearchAI
CPU-optimized semantic search with FAISS and BART summarization.
Retrieval Augmented Generation (RAG)GitHub
Pinecone Serverless Reranking
Optimization of retrieval precision.
Retrieval Augmented Generation (RAG)GitHub
RAG Pipeline (LangChain/Hugging Face)
Implementation of a retrieval system.
Retrieval Augmented Generation (RAG)GitHub
Search System
RAG system with FAISS semantic search and automatic summarization.
Retrieval Augmented Generation (RAG)GitHub
Tellow RAG
Universal document RAG system with LanceDB and Docling.
Retrieval Augmented Generation (RAG)GitHub
Vector DB Benchmark
FAISS vs ChromaDB comparison.
Retrieval Augmented Generation (RAG)GitHub
VEV RAG
High-performance agentic RAG with hybrid search running 100% locally on CPU.