Notes on a DEV Community article that wires up FastAPI as an OpenAI-compatible RAG API layer with llama.cpp, Chroma, and Open WebUI, plus where the architecture fits and what to watch for.
A read of arXiv:2604.26622 OCR-Memory. It renders agent execution history into images, uses Set-of-Mark to let a VLM pick relevant segments, then retrieves verbatim text from the original logs.
VecLite is a Rust/WASM+SIMD library that accelerates vector search inside the browser. How far can you get with Transformers.js for embeddings, IndexedDB for storage, and no server at all?
A look at sachitrafa/YourMemory, a local MCP memory server combining Ebbinghaus forgetting curves, BM25, vector search, and graph expansion. LoCoMo-10 Recall@5 currently sits at 59%.
Japan's Digital Agency released parts of Gennai, the generative AI platform it runs for central-government staff, on GitHub under MIT / CC BY 4.0. The web app and cloud-specific AI templates for AWS, Azure, and Google Cloud are bundled together so local governments and private companies can redeploy the same stack.
The NotebookLM clone open-notebook assumes Docker and cloud APIs by default. I installed SurrealDB natively, ran four processes in tmux, and wired everything through Ollama's qwen3.6:35b and bge-m3. I fed it the Qwen3.6 benchmark article I wrote this morning, and it answered with the correct numbers.
Sentence Transformers v5.4 adds multimodal support. Eight embedding models and four rerankers including Qwen3-VL and NVIDIA Nemotron can now be used through a unified API.
From the basics of RAG and vector databases to Mintlify's design and implementation of ChromaFs, a virtual file system that converts UNIX commands into ChromaDB queries.
A self-editing search agent with 20B parameters published by Chroma. It performs multi-hop search while dynamically pruning the context, and shows the same or higher accuracy than the Frontier model at 1/10 the cost and up to 10 times faster latency. Weights are exposed in Apache 2.0.
Agentic pipeline, which combines ReACT loop and searcher, achieved 1st place in ViDoRe v3 and 2nd place in BRIGHT. We established versatility for multiple domains using the same pipeline.
I looked into PageIndex, a RAG system that builds hierarchical document trees using only LLM reasoning, without chunking or vector databases. I also consider how it fits with layout detection and OCR pipelines.
A plan to build an internal help desk RAG system using a Mac mini M4 Pro and Dify. Highlights what's new in Dify circa 2025 and tips for running local LLMs.
