This article explores techniques for optimizing Retrieval-Augmented Generation (RAG) systems by implementing hybrid search and re-ranking mechanisms. It details how to combine dense vector embeddings with sparse keyword matching, such as BM25, to improve retrieval accuracy, followed by the use of a cross-encoder reranker to ensure only the most relevant context is passed to a Large Language Model in production environments.
Claude-Mem is a persistent memory compression system designed specifically for Claude Code and Gemini CLI. It automatically captures tool usage observations, generates semantic summaries via AI, and injects relevant context into future sessions to ensure continuity of knowledge across coding projects.
Key features include:
* Persistent memory that survives session restarts
* Progressive disclosure architecture for token-efficient retrieval
* Skill-based search using MCP tools (search, timeline, get_observations)
* Hybrid semantic and keyword search powered by Chroma vector database and SQLite
* Privacy controls via specific tags to exclude sensitive data
* A web viewer UI for real-time memory stream monitoring
Key features include:
* Persistent memory that survives session restarts
* Progressive disclosure architecture for token-efficient retrieval
* Skill-based search using MCP tools (search, timeline, get_observations)
* Hybrid semantic and keyword search powered by Chroma vector database and SQLite
* Privacy controls via specific tags to exclude sensitive data
* A web viewer UI for real-time memory stream monitoring
RAG combines language models with external knowledge. This article explores context & retrieval in RAG, covering search methods (keywords, TF-IDF, embeddings/FAISS/Chroma), context length challenges (compression, re-ranking), and contextual retrieval (query & conversation history).
LocalAI is a free and open-source AI stack that allows you to run language models, autonomous agents, and document intelligence locally on your hardware. It's an OpenAI API-compatible alternative focused on privacy, ease of use, and extensibility.
The article explores whether combining a command-line agent (like Claude Code or Gemini CLI) with Unix-like file system tools and SemTools is sufficient for complex tasks, particularly document search. It details a benchmark testing the limits of coding agents with and without SemTools, focusing on search, cross-referencing, and temporal analysis. The conclusion is that CLI access is powerful and SemTools enhances agent capabilities for document search and RAG.
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.
This Space demonstrates a simple method for embedding text using a LLM (Large Language Model) via the Hugging Face Inference API. It showcases how to convert text into numerical vector representations, useful for semantic search and similarity comparisons.
Foundational concepts, practical implementation of semantic search, and the workflow of RAG, highlighting its advantages and versatile applications.
The article provides a step-by-step guide to implementing a basic semantic search using TF-IDF and cosine similarity. This includes preprocessing steps, converting text to embeddings, and searching for relevant documents based on query similarity.
The article provides a step-by-step guide to implementing a basic semantic search using TF-IDF and cosine similarity. This includes preprocessing steps, converting text to embeddings, and searching for relevant documents based on query similarity.
An article discussing the use of embeddings in natural language processing, focusing on comparing open source and closed source embedding models for semantic search, including techniques like clustering and re-ranking.
The author explores semantic search using embeddings on U.S. Presidents, comparing four models: BGE, ST, Ada, and Large. The findings show that while embeddings capture interesting data, their limitations and inability to understand subtext and perform certain semantic tasks highlight their shallowness compared to full language models.
