Grew the Collection from 5 Entries to 741 Real Chunks
Every retrieval test since Entry 05 has run against the same handful of entries — three documents in...
Tag archive
Every retrieval test since Entry 05 has run against the same handful of entries — three documents in...
I Built a Memory System That Actually Helps Me Think After 13 days of autonomous...

By Yaala Labs Most AI agents have a fundamental flaw: they forget everything. Every conversation...
Why Automate Content Creation Creating content manually for 9 channels would take 8+ hours...
Loose end from Entry 14: switching mcp_search_server.py from stdio to SSE broke the Entry 08 Claude...
Why Automate Content Creation Creating content manually for 9 channels would take 8+ hours...
Context: Every prior entry in this arc — building the Chroma index, chunking, querying — was done by...
Why Automate Content Creation Creating content manually for 9 channels would take 8+ hours...
Context: Chunking means splitting a long document into smaller overlapping pieces before embedding...
Context: Building the vector store in the last entry was only half the job — the actual point of...
Context: An embedding model doesn't generate text — it converts text into a list of numbers (a...
Run a complete RAG pipeline on a 15000 rupee Android phone using Termux, Ollama, ChromaDB, and FastEmbed. Build a personal AI assistant that reads your files offline with zero API cost.