Amazon S3 Vectors is now generally available with increased scale and production-grade performance capabilities. It offers native support to store and query vector data, potentially reducing costs by up to 90% compared to specialized vector databases.
A tutorial on building a private, offline Retrieval Augmented Generation (RAG) system using Ollama for embeddings and language generation, and FAISS for vector storage, ensuring data privacy and control.
1. **Document Loader:** Extracts text from various file formats (PDF, Markdown, HTML) while preserving metadata like source and page numbers for accurate citations.
2. **Text Chunker:** Splits documents into smaller text segments (chunks) to manage token limits and improve retrieval accuracy. It uses overlapping and sentence boundary detection to maintain context.
3. **Embedder:** Converts text chunks into numerical vectors (embeddings) using the `nomic-embed-text` model via Ollama, which runs locally without internet access.
4. **Vector Database:** Stores the embeddings using FAISS (Facebook AI Similarity Search) for fast similarity search. It uses cosine similarity for accurate retrieval and saves the database to disk for quick loading in future sessions.
5. **Large Language Model (LLM):** Generates answers using the `llama3.2` model via Ollama, also running locally. It takes the retrieved context and the user's question to produce a response with citations.
6. **RAG System Orchestrator:** Coordinates the entire workflow, managing the ingestion of documents (loading, chunking, embedding, storing) and the querying process (retrieving relevant chunks, generating answers).
1. **Document Loader:** Extracts text from various file formats (PDF, Markdown, HTML) while preserving metadata like source and page numbers for accurate citations.
2. **Text Chunker:** Splits documents into smaller text segments (chunks) to manage token limits and improve retrieval accuracy. It uses overlapping and sentence boundary detection to maintain context.
3. **Embedder:** Converts text chunks into numerical vectors (embeddings) using the `nomic-embed-text` model via Ollama, which runs locally without internet access.
4. **Vector Database:** Stores the embeddings using FAISS (Facebook AI Similarity Search) for fast similarity search. It uses cosine similarity for accurate retrieval and saves the database to disk for quick loading in future sessions.
5. **Large Language Model (LLM):** Generates answers using the `llama3.2` model via Ollama, also running locally. It takes the retrieved context and the user's question to produce a response with citations.
6. **RAG System Orchestrator:** Coordinates the entire workflow, managing the ingestion of documents (loading, chunking, embedding, storing) and the querying process (retrieving relevant chunks, generating answers).
This article details the process of building a fast vector search system for a large legal dataset (Australian High Court decisions). It covers choosing embedding providers, performance benchmarks, using USearch and Isaacus embeddings, and the importance of API terms of service. It focuses on achieving speed and scalability while maintaining reasonable accuracy.
This article explains the internal workings of vector databases, highlighting that they don't perform a brute-force search as commonly described. It details algorithms like HNSW, IVF, and PQ, the tradeoffs between recall, speed, and memory, and how different RAG patterns impact vector database usage. It also discusses production challenges like filtering, updates, and sharding.
Google DeepMind research reveals a fundamental architectural limitation in Retrieval-Augmented Generation (RAG) systems related to fixed-size embeddings. The research demonstrates that retrieval performance degrades as database size increases, with theoretical limits based on embedding dimensionality. They introduce the LIMIT benchmark to empirically test these limitations and suggest alternatives like cross-encoders, multi-vector models, and sparse models.
Semantic search and document parsing tools for the command line. A collection of high-performance CLI tools for document processing and semantic search, built with Rust for speed and reliability.
The article discusses using Large Language Model (LLM) embeddings as features in traditional machine learning models built with scikit-learn. It covers the process of generating embeddings from text data using models like Sentence Transformers, and how these embeddings can be combined with existing features to improve model performance. It details practical steps including loading data, creating embeddings, and integrating them into a scikit-learn pipeline for tasks like classification.
A summary of a workshop presented at PyCon US on building software with LLMs, covering setup, prompting, building tools (text-to-SQL, structured data extraction, semantic search/RAG), tool usage, and security considerations like prompt injection. It also discusses the current LLM landscape, including models from OpenAI, Gemini, Anthropic, and open-weight alternatives.
This article details how to automate embedding generation and updates in Postgres using Supabase Vector, Queues, Cron, and pg_net extension with Edge Functions, addressing the issues of drift, latency, and complexity found in traditional external embedding pipelines.
A simple project demonstrating Retrieval Augmented Generation (RAG) using SQLite, sqlite-vec, and OpenAI. It embeds text files, stores them in a SQLite database, and retrieves relevant documents using vector search. The project features lightweight single-file SQLite databases, vector search capabilities, and OpenAI integration for embeddings and chat responses.
