vector-database

Edge compatible PDF.ai Chat with any PDF document You can ask questions, get summaries, find information, and more. Built with Pinecone, OpenAI, Langchain, Nextjs13, TypeScript, Clerk Auth, Drizzle ORM for edge runtime environment, Shadcn UI.

CLI tool for Weaviate

Bible verse search in meaning theough embedding and vector database.

A project to show howto use SpringAI with Ollama to chat with the documents in a library. Documents are stored in a normal/vector database. The AI is used to create embeddings from documents that are stored in the vector database. The vector database is used to query for the nearest document. That document is used by the AI to generate the answer.

Embedded on-device vector database for AI agent memory and local RAG — disk-based HNSW in an LSM-tree, C++/Python, optimized for low memory footprint

Semantic QA with a markdown database: Query any markdown file using vector embedding, Pinecone vector database and GPT (langchain). A weaker version of privateGPT

Elixir client for Qdrant vector search engine

Question Answering Generative AI application with Large Language Models (LLMs) and Amazon OpenSearch Service

⚡️Lightning fast in-memory VectorDB written in rust🦀

This repository contains hybrid-rag a LLMOPS python package

Comparing LanceDB and Elasticsearch for full-text search and vector search performance

A unified SDK for IronCore encryption operations including vector encryption for AI data

Simple customizable evaluation for text retrieval performance of Sentence Transformers embedders on PDFs

Privacy-first document intelligence engine — parse PDFs, DOCX, PPTX, XLSX & CSV into AI-ready chunks for RAG pipelines. Includes HITL review, 3-layer memory chat, and a production FastAPI server.

Multi-model AI agent runtime. Define agents in YAML, route each role to a model, orchestrate with 7 patterns (ReAct, Plan & Execute, Fan-Out, Pipeline, Supervisor, Swarm, Glyph), and deploy as a REST/WebSocket API with RAG, memory, MCP tools, guardrails and OpenTelemetry observability.

YouTube MCP Server is an AI-powered solution designed to revolutionize your YouTube experience. It empowers users to search for YouTube videos, retrieve detailed transcripts, and perform semantic searches over video content—all without relying on the official API. By integrating with a vector database, this server streamlines content discovery.

Anthropic's Contextual Retrieval implementation with visual chunk comparison. Preview context enrichment before/after embedding.

Versioned, fast and scalable nearest neighbor search.

Knowledge for GPTScript

Using embeddings to create memory.