Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: FAISS
Four Memory Strategies for AI Agents: Rolling Windows, FAISS and GraphRAG
Compare ways to give an LLM agent memory, from full history and rolling windows to inverted indexes, FAISS semantic search and a GraphRAG knowledge graph.
7 min readBenchmarking Five Embedded Vector Stores: FAISS, Chroma, LanceDB, VectLite
Five embedded vector databases benchmarked for local RAG: FAISS, Chroma, LanceDB, VectLite and NumPy compared on recall, latency, filters and cold start.
8 min readFine-Tuning a 7B Medical Model for Free: QLoRA, FAISS and Safety Guardrails
A zero-cost Kaggle T4 pipeline: synthetic data, QLoRA, RAG over classical texts, a verified layer, hard-coded emergency guardrails, GGUF release and the bugs hit.
5 min readOne Retriever, Three Backends: Porting NumPy Search to Chroma, FAISS, Pinecone
Port a hand-rolled NumPy cosine retriever to Chroma, FAISS and Pinecone, and learn what indexes, metadata filters and persistence add, plus the mistakes that break relevance.
11 min readLetting Gemini Pick the Source: FAISS, Tavily and Direct Answers in LangGraph
Build a small LangGraph workflow in which Gemini routes each question to a FAISS knowledge base, Tavily web search or a direct answer, with structured-output routing.
16 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.