Results for rag-engine

Agentic RAG framework for Node.js — zero dependencies, auto-retries, full decision trace

Retrivora AI is a plug-and-play AI engine for RAG chat experiences — generic vector DB + LLM provider, embeddable or standalone.

Production-grade RAG engine for conversational bots — hybrid retrieval (pgvector + BM25), pluggable LLM providers, sales-style prompt composition, hallucination guard, query rewriting.

RAG Engine — document ingestion, vector search, and knowledge base MCP server

RAG engine for Najm framework — embeddings, vector search, and semantic tool routing

CLI for RagClaw - local-first RAG engine

Core RAG engine for RagClaw - extractors, chunkers, embedder, store

A powerful, multimodal RAG engine with contextual retrieval, auto-prompt discovery, and PostgreSQL-native vector search

OpenClaw knowledge base RAG engine — standalone plugin for embedding, vector store, hybrid retrieval, and multi-type chunking (document/FAQ/conversation)

RAG engine combining js-doc-store (structured documents) and js-vector-store (semantic search with Ollama embeddings). Hybrid search + structured filtering for Retrieval-Augmented Generation.

Dynamic RAG Engine for AI Reliability. We provide mathematically scored context & sanitized data to prevent hallucinations in both static & volatile domains (starting with Korean Finance).

Local-first RAG engine for documents: semantic segmentation, embeddings, salience-aware retrieval, and citation-grounded Q&A

ContextAI RAG Engine - Document loading, chunking, and retrieval

A lightweight, production-ready Retrieval-Augmented Generation (RAG) engine for Node.js

Library-first realtime RAG engine with pgvector and streaming generation.

A a collection of languages stemmers and stopwords for Lunr Javascript library

Dynamic RAG Engine for AI Reliability. We provide mathematically scored context & sanitized data to prevent hallucinations in both static & volatile domains (starting with Korean Finance).

<p align="left"> <a href="https://r2r-docs.sciphi.ai"><img src="https://img.shields.io/badge/docs.sciphi.ai-3F16E4" alt="Docs"></a> <a href="https://discord.gg/p6KqD2kjtB"><img src="https://img.shields.io/discord/1120774652915105934?style=social&logo=

The Retrieval-Augmented Generation (RAG) module contains document processing and embedding utilities.

A rag component for Convex.

Engine for Shiki using Oniguruma RegExp engine in WebAssembly

styled() API wrapper package for emotion.

This package is intended for Prisma's internal use

Engine for Shiki using JavaScript's native RegExp