GitHub topics: hybrid-search | Ecosyste.ms: Repos

bhupencoD3/PerfectPick

PerfectPick is an AI-powered smartphone recommendation system built with Flask and Postgres for session management, AstraDB for vector storage, and hybrid retrieval using BM25 and BGE embeddings. Deployed on GCP with Docker and Kubernetes, integrated with Prometheus and Grafana for scalable, production-grade performance and MLOps observability.

Language: Python - Size: 7.51 MB - Last synced at: about 8 hours ago - Pushed at: about 8 hours ago - Stars: 0 - Forks: 0

hamzaideators/cinerag

🎬 Discover movies effortlessly with CineRAG, a RAG system that combines natural language queries and intelligent retrieval for personalized recommendations.

Language: Python - Size: 12.1 MB - Last synced at: about 14 hours ago - Pushed at: about 16 hours ago - Stars: 0 - Forks: 0

Extensivenesswoodpulp484/weaviate_ex

🚀 Streamline your interactions with Weaviate using this idiomatic Elixir client for easy access to vector database features and robust functionality.

Language: Elixir - Size: 1.55 MB - Last synced at: 1 day ago - Pushed at: 1 day ago - Stars: 0 - Forks: 0

sivenz/hybrid-agent-framework

🤖 Build AI agents that combine OpenAI's orchestration and Claude's execution for effective production solutions.

Language: Python - Size: 47.9 KB - Last synced at: 2 days ago - Pushed at: 2 days ago - Stars: 0 - Forks: 0

meilisearch/meilisearch

A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.

Language: Rust - Size: 80.9 MB - Last synced at: 2 days ago - Pushed at: 2 days ago - Stars: 54,272 - Forks: 2,236

treygrainger/ai-powered-search

The codebase for the book "AI-Powered Search" (Manning Publications, 2025)

Language: Jupyter Notebook - Size: 69.5 MB - Last synced at: about 20 hours ago - Pushed at: about 21 hours ago - Stars: 329 - Forks: 85

SAHIXXX12/AI-Search-Engine

🔍 Build an AI-powered search engine with React, TypeScript, and Vite for fast, responsive querying and efficient development.

Language: TypeScript - Size: 1.35 MB - Last synced at: 3 days ago - Pushed at: 3 days ago - Stars: 0 - Forks: 0

duynguyensh/AI-Powered

🤖 Employ AI to autonomously perform penetration testing, enhancing attack strategies and improving cybersecurity defenses with advanced automated techniques.

Size: 1.48 MB - Last synced at: 3 days ago - Pushed at: 3 days ago - Stars: 0 - Forks: 0

Hyperkorn/qdrant-neo4j-crawl4ai-mcp

🧠 Enhance AI coordination with the Qdrant Neo4j Crawl4AI MCP server, combining vector search, knowledge graphs, and web intelligence for optimal performance.

Language: Python - Size: 702 KB - Last synced at: 3 days ago - Pushed at: 4 days ago - Stars: 1 - Forks: 0

paswell-chiks/Optimizing-RAG-with-Hybrid-Search

🔍 Optimize RAG systems by exploring Lexical, Semantic, and Hybrid Search methods for better context retrieval and improved LLM responses.

Language: Jupyter Notebook - Size: 3.67 MB - Last synced at: 3 days ago - Pushed at: 4 days ago - Stars: 0 - Forks: 0

GauravvvGoyal/congress-bill-search

🔍 Search and discover Congressional bills efficiently with a powerful system that combines authoritative data, advanced storage, and hybrid search techniques.

Language: Python - Size: 1.3 MB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 0 - Forks: 0

PDewangan/neo4j-agentframework

📊 Transform documents into a smart knowledge base using Neo4j and Azure AI for efficient, intelligent searching and answer generation.

Language: Python - Size: 38.3 MB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 1 - Forks: 0

paradedb/paradedb

The transactional Elasticsearch alternative built on Postgres

Language: Rust - Size: 32.6 MB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 7,881 - Forks: 283

crate/cratedb-django

CrateDB backend for Django

Language: Python - Size: 185 KB - Last synced at: 5 days ago - Pushed at: 5 days ago - Stars: 3 - Forks: 1

Milesdexter/docschat-rag

📚 Enhance technical documentation queries with DocsChat RAG, a robust Retrieval-Augmented Generation system featuring hybrid search and precise citations.

Size: 10.7 KB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 0 - Forks: 0

infiniflow/infinity

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

Language: C++ - Size: 73.2 MB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 4,154 - Forks: 392

HendrikReh/deepresearch-rs

AI Research Assistant that proves every conclusion it delivers. The system showcases how to operationalise Explainable AI (XAI) end-to-end: autonomous research, transparent reasoning, traceable evidence, and governance-ready artefacts.

Language: Rust - Size: 455 KB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 0 - Forks: 1

dingodb/dingo

A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.

Language: Java - Size: 30.2 MB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 1,683 - Forks: 265

ChrisGVE/workspace-qdrant-mcp

Project-scoped Qdrant MCP server for workspace collections with scratchbook functionality. Python port of claude-qdrant-mcp with FastEmbed and project-aware collection management.

Language: Python - Size: 319 MB - Last synced at: 7 days ago - Pushed at: 7 days ago - Stars: 0 - Forks: 0

weaviate/weaviate

Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.

Language: Go - Size: 980 MB - Last synced at: 7 days ago - Pushed at: 9 days ago - Stars: 14,848 - Forks: 1,116

microsoft/rag-time

RAG Time: A 5-week Learning Journey to Mastering RAG

Language: Jupyter Notebook - Size: 71.4 MB - Last synced at: 7 days ago - Pushed at: 5 months ago - Stars: 719 - Forks: 269

weaviate/weaviate-io

Website for the Weaviate vector database

Language: MDX - Size: 1.26 GB - Last synced at: 6 days ago - Pushed at: 6 days ago - Stars: 87 - Forks: 142

capybara-brain346/capybaradb

capybaradb - a toy Vector DB implementation from scratch in Python. Explore Vector DB internals.

Language: Python - Size: 346 KB - Last synced at: 9 days ago - Pushed at: 10 days ago - Stars: 0 - Forks: 0

PrithivirajDamodaran/FlashRank

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.

Language: Python - Size: 2.48 MB - Last synced at: 9 days ago - Pushed at: about 2 months ago - Stars: 874 - Forks: 61

Restream/reindexer

Embeddable, in-memory, document-oriented database with a high-level Query builder interface.

Language: C++ - Size: 19.7 MB - Last synced at: 10 days ago - Pushed at: 10 days ago - Stars: 794 - Forks: 62

ukushu/Ifrit

Swfit library for fuzzy search. No dependencies lib.

Language: Swift - Size: 3.06 MB - Last synced at: 10 days ago - Pushed at: 10 days ago - Stars: 71 - Forks: 8

vearch/vearch

Distributed vector search for AI-native applications

Language: Go - Size: 36.1 MB - Last synced at: 10 days ago - Pushed at: 10 days ago - Stars: 2,234 - Forks: 350

PrithivirajDamodaran/SPLADERunner

Lite weight wrapper for the independent implementation of SPLADE++ models for search & retrieval pipelines. Models and Library created by Prithivi Da, For PRs and Collaboration checkout the readme.

Language: Python - Size: 185 KB - Last synced at: 9 days ago - Pushed at: about 1 year ago - Stars: 33 - Forks: 2

torleifg/bookquest

Hybrid search engine for books that combines semantic and full-text search.

Language: Java - Size: 884 KB - Last synced at: 11 days ago - Pushed at: 11 days ago - Stars: 2 - Forks: 0

nshkrdotcom/weaviate_ex

Modern Elixir client for Weaviate vector database with health checks and friendly error messages

Language: Elixir - Size: 314 KB - Last synced at: 9 days ago - Pushed at: 13 days ago - Stars: 0 - Forks: 0

ma3u/neo4j-agentframework

🚀 Hybrid RAG: Local Neo4j + BitNet.cpp RAG System and Azure SaaS deployment. Fast vector search, instant Docker deployment via GitHub Container Registry. Complete RAG pipeline with ultra-efficient LLMs for enterprise knowledge management.

Language: Python - Size: 35.1 MB - Last synced at: 14 days ago - Pushed at: 14 days ago - Stars: 1 - Forks: 0

rapidsai/cuvs-lucene

A Lucene codec for vector search and clustering on the GPU

Language: Java - Size: 127 KB - Last synced at: 16 days ago - Pushed at: 16 days ago - Stars: 5 - Forks: 4

rbatllet/private-blockchain-cli

A command-line interface for managing a private blockchain system built with Java 21, Maven, and PicoCLI.

Language: Java - Size: 832 KB - Last synced at: 10 days ago - Pushed at: 10 days ago - Stars: 0 - Forks: 0

pingcap/pytidb

TiDB AI SDK: Unified Multi-Modal Data Platform for AI Apps & Agents - https://pingcap.github.io/ai/

Language: Python - Size: 2.06 MB - Last synced at: 5 days ago - Pushed at: 17 days ago - Stars: 27 - Forks: 15

mongodb-industry-solutions/retail-unified-commerce

This demo showcases a store associate application built on MongoDB Atlas, created to streamline product discovery and inventory visibility as part of a unified commerce strategy.

Language: JavaScript - Size: 9.19 MB - Last synced at: 18 days ago - Pushed at: 18 days ago - Stars: 1 - Forks: 1

AstraBert/Pokemon-Bot

Discord bot that knows a lot about Pokemons :)

Language: Python - Size: 7.63 MB - Last synced at: 8 days ago - Pushed at: 10 months ago - Stars: 14 - Forks: 1

hassenhamdi/HyDRA

 HyDRA: Hybrid Dynamic RAG Agents, An advanced, agentic AI framework that transforms Retrieval-Augmented Generation from a static pipeline into a dynamic, learning reasoning system.

Language: Python - Size: 23.6 MB - Last synced at: 26 days ago - Pushed at: 26 days ago - Stars: 9 - Forks: 1

Tiledesk/tiledesk-chatbot

The Tiledesk Automation Engine: Your open-source solution for multichannel workflow automation. An alternative to Voiceflow, Botpress, Stack AI, Flowise, Gumloop, VectorShift, Lyzr AI

Language: JavaScript - Size: 5.73 MB - Last synced at: 10 days ago - Pushed at: 10 days ago - Stars: 64 - Forks: 38

bielacki/cinerag

🎬 Movie discovery RAG system using natural language queries. Features hybrid search (BM25+Vector), reranking, LLM integration, and Grafana monitoring.

Language: Python - Size: 10.8 MB - Last synced at: 28 days ago - Pushed at: 28 days ago - Stars: 0 - Forks: 0

paulo-b-vale/hybrid-search-engine

An implementation of a hybrid search engine using dense-sparse fusion on the MS MARCO dataset. Built with Python, FAISS, and Transformers.

Language: Python - Size: 205 KB - Last synced at: 29 days ago - Pushed at: 29 days ago - Stars: 0 - Forks: 0

Ntropy86/review-recommender

A Hybrid Semantic Search Algorithm using Low Dimensional multiple Amazon Reviews Dataset.

Language: Python - Size: 107 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 1 - Forks: 0

wzdavid/ThinkRAG

A LLM RAG system runs on your laptop. 大模型检索增强生成系统，可以轻松部署在笔记本电脑上，实现本地知识库智能问答。

Language: Python - Size: 7.98 MB - Last synced at: 28 days ago - Pushed at: 3 months ago - Stars: 275 - Forks: 40

MUHAMMAD-FARMAN/SIMS-AI-receptionist

An intelligent healthcare receptionist application powered by Retrieval-Augmented Generation (RAG) technology with hybrid search.

Language: JavaScript - Size: 189 KB - Last synced at: 28 days ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

juhokoskela/rag_service

FastAPI-based RAG backend with hybrid search and reranking

Language: Python - Size: 96.7 KB - Last synced at: about 1 month ago - Pushed at: about 1 month ago - Stars: 0 - Forks: 0

iamarunbrahma/rag-api

RAG-API: A production-ready Retrieval Augmented Generation API leveraging LLMs, vector databases, and hybrid search for accurate, context-aware responses with citation support.

Language: Python - Size: 33.2 KB - Last synced at: 28 days ago - Pushed at: 11 months ago - Stars: 6 - Forks: 2

BjornMelin/docmind-ai-llm

DocMind AI is a powerful, open-source Streamlit application leveraging LlamaIndex, LangGraph, and local Large Language Models (LLMs) via Ollama, LMStudio, llama.cpp, or vLLM for advanced document analysis. Analyze, summarize, and extract insights from a wide array of file formats—securely and privately, all offline.

Language: Python - Size: 7.45 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 29 - Forks: 4

ImadSaddik/ElasticSearch_Python_Course

This repository is part of a course on Elasticsearch in Python. It includes notebooks that demonstrate its usage, along with a YouTube series to guide you through the material.

Language: Jupyter Notebook - Size: 27.8 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 68 - Forks: 55

evalops/congress-bill-search

High-quality congressional bill search with hybrid BM25+vector similarity using DuckDB, TEI embeddings, and GovInfo API. Local deployment with Docker.

Language: Python - Size: 15.6 KB - Last synced at: 26 days ago - Pushed at: about 2 months ago - Stars: 2 - Forks: 0

graphgeeks-lab/odsc-agentic-ai-summit-2025

Code from the ODSC Agentic Graph RAG workshop combining vector, FTS & graph retrieval for RAG. Includes observability and guardrails for evaluating outputs.

Language: Python - Size: 17.3 MB - Last synced at: 25 days ago - Pushed at: 3 months ago - Stars: 14 - Forks: 3

nabeelshan78/Optimizing-RAG-with-Hybrid-Search

Hybrid RAG with three retrievers—Lexical (BM25), Semantic (embeddings), and Hybrid (Reciprocal Rank Fusion) — parallel retrieval, Llama 3 generation, and side-by-side evaluation with reproducible notebooks.

Language: Jupyter Notebook - Size: 2.39 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 1 - Forks: 0

Nexer8/simple-rag

Playground environment for experimenting with RAG techniques.

Language: Jupyter Notebook - Size: 131 KB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

AlwaysSany/hybrid-search

A product search platform where users can browse, search, and filter products using a hybrid search mechanism that combines lexical and semantic techniques

Language: Jupyter Notebook - Size: 1.66 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

e1washere/production-rag-service

Production-grade RAG service demonstrating enterprise MLOps practices with hybrid search, comprehensive observability, and automated deployment pipelines.

Language: Python - Size: 93.8 KB - Last synced at: 19 days ago - Pushed at: 2 months ago - Stars: 0 - Forks: 0

typesense/showcase-hn-comments-semantic-search

Semantic Search + Keyword Search + Hybrid Search + Filtering + Faceting on 300K HN Comments

Language: JavaScript - Size: 433 KB - Last synced at: 2 months ago - Pushed at: 11 months ago - Stars: 53 - Forks: 11

YeonwooSung/postgresql-books

Playground for learning various techniques about PostgreSQL

Language: PLpgSQL - Size: 416 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 2 - Forks: 1

PeerlessMonster/JoyRead_backend

一个十分简单的资讯阅读应用的后端 Backend of a Very Simple Information Reading App

Language: Kotlin - Size: 105 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 1 - Forks: 0

tmoesl/rag-pipeline

An implementation of PostgreSQL and pgvector built to power RAG solutions in Python, featuring Docling-based document processing and OpenAI embeddings.

Language: Python - Size: 5.07 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 1 - Forks: 0

machinelearningZH/deep-research

Powerful, automated research and analysis across your own document collections.

Language: Python - Size: 17.3 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 10 - Forks: 2

pureinsights/discovery-sandbox

Discovery Sandbox SDK

Language: Python - Size: 241 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

Syed007Hassan/Investment-Search

This application implements an advanced company search and ranking system using a hybrid search approach that combines vector similarity search (using PgVector) and traditional full-text search in PostgreSQL.

Language: Python - Size: 1.45 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 4 - Forks: 0

fenilsonani/rag-document-qa

Enterprise-grade RAG system featuring dual online/offline operation, multi-modal document processing, and advanced AI capabilities including knowledge graph construction and hybrid search for intelligent document analysis.

Language: Python - Size: 298 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 1 - Forks: 0

agoodway/vecto 📦

Hybrid Search with Postgres and Ecto

Language: Elixir - Size: 27.3 KB - Last synced at: 12 days ago - Pushed at: 3 months ago - Stars: 59 - Forks: 3

beter2004/Vector.AI

Create content effortlessly with Vector.AI, an AI-powered platform for writing articles, generating images, and enhancing digital assets. 🌟🚀

Language: JavaScript - Size: 3.24 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0

AstraBert/llamaindex-docs-agent

A simple ReAct agent that has access to LlamaIndex docs and to the internet to provide you with insights on LlamaIndex itself.

Language: Python - Size: 1.61 MB - Last synced at: 8 days ago - Pushed at: 8 months ago - Stars: 11 - Forks: 1

aninghidalgo/Enterprise-RAG-Framework

Language: Python - Size: 154 KB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

iamarunbrahma/rag-ingest

RAG-Ingest: A tool for converting PDFs to markdown and indexing them for enhanced Retrieval Augmented Generation (RAG) capabilities.

Language: Python - Size: 40 KB - Last synced at: 28 days ago - Pushed at: 11 months ago - Stars: 4 - Forks: 0

isfnr1/qdrant-neo4j-crawl4ai-mcp

Discover the Qdrant Neo4j Crawl4AI MCP Server, a powerful tool for intelligent AI coordination using vector and graph intelligence. 🌐🚀

Language: Python - Size: 704 KB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 0

sonesuke/oboyu

Self-hosted MCP Japanese text indexing & search—chunking+embeddings with BM25×vector rerank

Language: Python - Size: 5.77 MB - Last synced at: about 1 month ago - Pushed at: 4 months ago - Stars: 1 - Forks: 1

BjornMelin/qdrant-neo4j-crawl4ai-mcp

MCP server combining Qdrant vector search, Neo4j knowledge graphs, and Crawl4AI web intelligence with agentic RAG capabilities. FastMCP 2.0 architecture with enterprise security, monitoring, and Kubernetes deployment. AI/ML engineering powerhouse.

Language: Python - Size: 706 KB - Last synced at: 3 months ago - Pushed at: 4 months ago - Stars: 0 - Forks: 1

razamehar/Advanced-RAG

Language: Jupyter Notebook - Size: 11.6 MB - Last synced at: 4 months ago - Pushed at: 5 months ago - Stars: 0 - Forks: 0

JackLeeJM/rag-medication-ner

An LLM-powered RAG application for medication Named Entity Recognition (NER)

Language: Python - Size: 361 KB - Last synced at: about 2 months ago - Pushed at: 9 months ago - Stars: 2 - Forks: 0

kjaymiller/multi_service_ai_request

AI Personal Assistant using content created by @kjaymiller

Language: Python - Size: 13.7 KB - Last synced at: about 2 months ago - Pushed at: 5 months ago - Stars: 2 - Forks: 0

thangchung/sk-hybrid-search

[Experiment] Vibe coding with vscode - agent mode with Claude Sonnet 4 (just for fun to learn the concept of hybrid search by implementing it from scratch)

Language: C# - Size: 121 KB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 3 - Forks: 1

ksm26/vector-databases-embeddings-applications

Unlock the power of vector databases with the "Vector Databases: from Embeddings to Applications" course! A journey that will equip you with essential skills to leverage vector databases for various applications.

Language: Jupyter Notebook - Size: 5.74 MB - Last synced at: 8 days ago - Pushed at: almost 2 years ago - Stars: 6 - Forks: 9

ismailbokri/Combot

This project, Contract Compliance, was developed as part of a project for the Contract Lifecycle Management module in the Management Information Systems program at ESPRIT University. It focuses on automating the monitoring and enforcement of contractual obligations to ensure regulatory compliance and minimize operational risks.

Language: Python - Size: 6.17 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 2 - Forks: 0

TaimoorKhan10/Enterprise-RAG-Framework

Production-ready Retrieval Augmented Generation (RAG) system with hybrid retrieval, advanced evaluation metrics, and monitoring. Build enterprise LLM applications with reduced hallucinations, better context management, and comprehensive observability.

Language: Python - Size: 0 Bytes - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 0 - Forks: 0

RheagalFire/LLM-gym

All things Essential For my Learning Curve in LLM

Language: Python - Size: 2.23 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 4 - Forks: 0

yuniko-software/bge-m3-qdrant-sample

A demonstration of hybrid search with reranking using Qdrant and BGE-M3 model. A showcase of dense and sparse retrieval combined with ColBERT reranking for optimal search results

Language: Jupyter Notebook - Size: 200 KB - Last synced at: 5 months ago - Pushed at: 7 months ago - Stars: 7 - Forks: 0

gedankrayze/training-data-generator

Training Data Generator for SPLADE Model Fine-tuning

Language: Python - Size: 37.1 KB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 0 - Forks: 0

salman-aziz-4425/FlowThink-Backend

A React-based visual interface that allows users to connect YouTube videos to chat nodes and interact with video content through a conversational interface.

Language: Python - Size: 45.9 KB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 0 - Forks: 0

liamca/sqlite-hybrid-search

Hybrid Search (BM25 & Vector) with SQLite

Language: Jupyter Notebook - Size: 23.4 KB - Last synced at: 7 months ago - Pushed at: about 1 year ago - Stars: 14 - Forks: 1

machinelearningZH/ogd_ai-search

Semantic, lexical, multilingual search in your OGD metadata catalog.

Language: Jupyter Notebook - Size: 6.21 MB - Last synced at: 5 months ago - Pushed at: 7 months ago - Stars: 2 - Forks: 0

AlbeneZiv/HFSIA

A hybrid Artificial Immune optimization for high-dimensional feature selection

Language: MATLAB - Size: 10.2 MB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 0 - Forks: 0

JacobSKN/pubmed_semantic_search

Enhanced biomedical literature search combining semantic understanding with traditional keyword search for PubMed articles

Size: 0 Bytes - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 1 - Forks: 0

zilliz-bootcamp/milvus_hybrid_search_based_postgres

This project provides an example of consolidating Milvus (vector search engine) and PostgreSQL (relational database) to carry out the hybrid search of vectors and structured data.

Language: Python - Size: 13.7 KB - Last synced at: 5 months ago - Pushed at: about 4 years ago - Stars: 10 - Forks: 1

sjy-dv/coltt

Coltt is a vector database that supports Multi-Vector Search, high-performance HNSW, FLAT and quantization, and enables fast searches through sophisticated internal data shard design.

Language: Go - Size: 55.2 MB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 184 - Forks: 1

askaitools/askaitools-community-edition

A cutting-edge search engine project tailored specifically for the AI product

Language: TypeScript - Size: 742 KB - Last synced at: 7 months ago - Pushed at: over 1 year ago - Stars: 347 - Forks: 29

balaragavesh/RAG-assistant

A RAG model using Phi-2 and ChromaDB to generate precise, context-aware answers from user guide documentation, enhancing AI-driven assistance.

Language: Jupyter Notebook - Size: 0 Bytes - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 0 - Forks: 0

ashwantmanikoth/IntellilSearch

This is a AI powered crawler that can search the web for information based on your input.

Language: Python - Size: 28.3 KB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 0 - Forks: 0

waitingsong/paradedb

ParadeDb JavaScript Client Library

Language: TypeScript - Size: 271 KB - Last synced at: 14 days ago - Pushed at: 8 months ago - Stars: 0 - Forks: 0

ctrlb-hq/diskannrs

Pure Rust Port of DiskANN

Language: Rust - Size: 3.87 MB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 4 - Forks: 0

v-ade-r/Chatbot-based-on-Contextual-RAG-full-OpenSource

Chatbot based on Contextual RAG with Hybrid Search and Reranking with short conversation history awareness, fully OpenSource.

Language: Python - Size: 666 KB - Last synced at: 7 months ago - Pushed at: 9 months ago - Stars: 1 - Forks: 0

yarikama/Agentic-Advanced-RAG

Building a multi-agent RAG system with advanced RAG methods

Language: Jupyter Notebook - Size: 22.8 MB - Last synced at: 10 months ago - Pushed at: 10 months ago - Stars: 6 - Forks: 2

extrawest/pinecone_hybrid_search

Hybrid Search of full text and vector queries that execute against a search index containing both searchable plain text content and generated embeddings

Language: Python - Size: 7.81 KB - Last synced at: 7 months ago - Pushed at: 11 months ago - Stars: 2 - Forks: 0

jesse-c/notes-app-hybrid-search

Make your notes from Notes.app searchable via hybrid search.

Language: Python - Size: 113 KB - Last synced at: 14 days ago - Pushed at: 10 months ago - Stars: 1 - Forks: 0

Shakshi3104/cobalt-hybrid-search

Demo app for hybrid search with vector and surface search

Language: Python - Size: 362 KB - Last synced at: 8 days ago - Pushed at: 12 months ago - Stars: 0 - Forks: 0

shaadclt/Hybrid-Search-RAG-LangChain-Pinecone

This repository contains a Google Colab notebook that demonstrates how to set up and use a hybrid search Retrieval-Augmented Generation (RAG) system using LangChain and Pinecone. The hybrid search combines vector embeddings and sparse (BM25) encodings to provide efficient and accurate information retrieval.

Language: Jupyter Notebook - Size: 26.4 KB - Last synced at: 7 months ago - Pushed at: about 1 year ago - Stars: 5 - Forks: 0