ClusteredBytes
Enjoy my writings on various topics including AI, Cloud Native, Kubernetes, Software Architecture, Data structures and Algorithms and anything else that I’m currently exploring.
A guide to build a fully local Chat-with-pdf app using LlamaIndex TS, Ollama, Next.JS
A guide to building a full-fledged discord bot using LlamaIndex, that listens to, remembers and answers questions from your discord server.
A guide to proposition basead retrieval, and how it outperforms traditional passage and sentence retrievers.
A guide to the new LlamaIndex Ingestion pipeline, which is a new and improved way to ingest documents.
A beginner friendly introduction to multi-modal RAG using LlamaIndex
A guide on how to finetune an adapter on top of existing embedding models to improve retrieval
A guide on how to finetune sentence transformer embedding models to improve retrieval
LLMs get lost in the middle of long context and we try to address this using LangChain LongContextReorder
Looking at LangChain ParentDocumentRetriever to strike a balance between large vs small document chunks while retrieving related documents.
Looking at LangChain MultiQueryRetriever to cover various perspectives and get better results while finding relevant documents.