Search Results for "document search engine"
Sort By:
Showing 1175 open source projects for "document search engine"
View related business solutions-
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
Search-Index
A persistent, network resilient, full text search library
Search-Index is a lightweight and fast JavaScript-based search engine that enables full-text search indexing and retrieval for web applications. -
2
RATS Search
BitTorrent P2P multi-platform search engine for Desktop
Rats Search is a cross-platform search tool for torrent indexing across multiple BitTorrent DHT networks. It provides a GUI for searching decentralized torrent metadata in real time without relying on centralized indexes. Built with Electron and Vue.js, Rats Search emphasizes decentralization and anonymity, allowing users to explore content from distributed sources such as the BitTorrent Mainline DHT and WebTorrent. It supports filtering, magnet link generation, and acts as a... -
3
Text Search Engine
A text search engine that supports mixed Chinese and English search
Text-Search-Engine is a JavaScript-based lightweight search engine that enables full-text search functionality. It allows developers to implement fast search indexing and retrieval in web applications. -
4
Search with Lepton
Lightweight demo to build a conversational AI search engine quickly
Search with Lepton is an open source demonstration project that shows how to build a conversational search engine using the Lepton AI framework. It combines traditional web search with large language models to provide natural language answers to user queries. It retrieves information from supported search engines and uses that context to generate responses through a retrieval-augmented generation approach. -
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
5
Open Semantic Search
Open source semantic search and text analytics for large document sets
Open Semantic Search is an open source research and analytics platform designed for searching, analyzing, and exploring large collections of documents using semantic search technologies. It provides an integrated search server combined with a document processing pipeline that supports crawling, text extraction, and automated analysis of content from many different sources. -
6
Whoogle Search
A self-hosted, ad-free, privacy-respecting metasearch engine
Get Google search results, but without any ads, javascript, AMP links, cookies, or IP address tracking. Easily deployable in one click as a Docker app, and customizable with a single config file. Quick and simple to implement as a primary search engine replacement on both desktop and mobile. Autocomplete/search suggestions. POST request search and suggestion queries (when possible). -
7
GitHub search with Manticore Search
Demo: GitHub search with Manticore Search
GitHub search with Manticore Search. The Manticore GitHub Issue Search tool allows users to search through GitHub issues using Manticore Search, a powerful full-text search engine designed for large datasets and real-time processing. It integrates Manticore's capabilities with GitHub to offer fast and efficient searches within repositories. -
8
SemTools
Semantic search and document parsing tools for the command line
SemTools is an open-source command-line toolkit designed for document parsing, semantic indexing, and semantic search workflows. The project focuses on enabling developers and AI agents to process large document collections and extract meaningful semantic representations that can be searched efficiently. Built with Rust for performance and reliability, the toolchain provides fast processing of text and structured documents while maintaining low system overhead. ... -
9
Wicked Engine
3D engine with modern graphics
...There are other example projects that you can build as well within the solution. If you want to develop a C++ application that uses Wicked Engine, you can build the WickedEngine static library project for the appropriate platform, such as WickedEngine_Windows, and link against it. Including the "WickedEngine.h" header will attempt to link the binaries for the appropriate platform, but search directories should be set up beforehand. -
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
10
HelixDB
Graph-vector database for building unified AI backends fast
...HelixDB includes built-in capabilities for embeddings, vector search, keyword search, and graph traversal, which are particularly useful for retrieval-augmented generation and agent-based systems. -
11
fess
Open source enterprise search server for websites, files, and data
Fess is an open source enterprise search server designed to provide powerful full-text search capabilities across multiple data sources. It enables organizations to quickly deploy a scalable search environment without requiring deep knowledge of underlying search technologies. Fess is built on top of OpenSearch and offers an integrated solution for crawling, indexing, and searching documents from websites, file systems, and various data stores. -
12
Summa
Full-text IPFS-friendly and WASM-compatible Search in Rust
Summa is a full-text IPFS-friendly search engine that may be launched on both large servers and inside your browser. Thanks to the embedded IPFS daemon, your data can be replicated and published through P2P, allowing for a truly distributed and uncensorable search experience. And, thanks to compatibility with WASM, Summa can be launched entirely inside your browser, enabling you to search in network-published indices without ever having to execute search queries on remote servers. -
13
SAG
SQL-Driven RAG Engine
...These vectors allow the system to identify relationships between concepts and construct a graph representation of knowledge at runtime. The architecture also includes a three-stage retrieval pipeline consisting of recall, expansion, and reranking steps to improve search accuracy. The engine integrates semantic vector similarity with traditional full-text search to improve both recall and precision. Because the knowledge graph is generated dynamically, the system can adapt to new information without requiring manual graph maintenance. -
14
OceanBase seekdb
The AI-Native Search Database
seekdb is an AI-native search database from OceanBase that unifies vector, full-text, relational, JSON, and GIS data into a single query engine. The system is designed to support hybrid search workloads and in-database AI workflows without requiring multiple specialized databases. It enables developers to perform semantic search, keyword search, and structured SQL queries within the same platform, simplifying modern AI application stacks. seekdb also embeds AI capabilities directly in the database layer, including embedding generation, reranking, and LLM inference for end-to-end RAG pipelines. ... -
15
theHarvester
E-mails, subdomains and names
theHarvester is a very simple to use, yet powerful and effective tool designed to be used in the early stages of a penetration test or red team engagement. Use it for open source intelligence (OSINT) gathering to help determine a company's external threat landscape on the internet. The tool gathers emails, names, subdomains, IPs and URLs using multiple public data sources. -
16
WeKnora
LLM framework for document understanding and semantic retrieval
...This approach enables the system to provide more reliable answers by grounding model reasoning in the content of uploaded documents. WeKnora is designed with a modular architecture that separates components for document processing, search strategies, and model inference, allowing developers to customize or extend different parts of the pipeline. It supports knowledge base management and conversational question answering built on top of structured and unstructured documents. -
17
MongoDB
The MongoDB Database
MongoDB refers to the core MongoDB server, a modern, document-oriented NoSQL database offering flexible schema, rich queries, horizontal scalability, and integrated support for transactions and search. Packages are created dynamically by the buildscripts/packager.py script. This will generate RPM and Debian packages. Client drivers for most programming languages are available. You can install compass using the install_compass script packaged with MongoDB. -
18
Paperless-AI
AI-powered document analysis and tagging for Paperless-ngx
...A key capability is its use of retrieval-augmented generation, which enables semantic search and natural language interaction across an entire document archive. Users can ask contextual questions about their files and receive precise answers based on full document understanding rather than simple keyword matching. Paperless-AI also includes a web interface for manual review and tagging, allowing greater control when handling sensitive or complex documents. -
19
marqo
Tensor search for humans
A tensor-based search and analytics engine that seamlessly integrates with your applications, websites, and workflows. Marqo is a versatile and robust search and analytics engine that can be integrated into any website or application. Due to horizontal scalability, Marqo provides lightning-fast query times, even with millions of documents. Marqo helps you configure deep-learning models like CLIP to pull semantic meaning from images. -
20
Meilisearch
An open-source, lightning-fast, and hyper-relevant search engine
An open-source, lightning-fast, and hyper-relevant search engine that fits effortlessly into your apps, websites, and workflow. Meilisearch is a flexible and powerful user-focused search engine that can be added to any website or application. Search-as-you-type returns answers in less than 50 milliseconds. That's faster than the blink of an eye! Deploy in a matter of minutes. Smart presets let you start searching through your data with zero configuration. ... -
21
ParadeDB
ParadeDB is a modern Elasticsearch alternative built on Postgres
ParadeDB is an open-source search and analytics engine built on top of PostgreSQL. It serves as a modern alternative to Elasticsearch, offering real-time search capabilities for update-heavy workloads. By leveraging PostgreSQL's robustness, ParadeDB provides a scalable and efficient solution for full-text search and analytics. -
22
RAG API
ID-based RAG FastAPI: Integration with Langchain and PostgreSQL
rag_api is an open-source REST API for building Retrieval-Augmented Generation (RAG) systems using LLMs like GPT. It lets users index documents, search semantically, and retrieve relevant content for use in generative AI workflows. Designed for rapid prototyping, it is ideal for chatbot development, document assistants, and knowledge-based LLM apps. -
23
Marten
.NET Transactional Document DB and Event Store on PostgreSQL
The Marten library provides .NET developers with the ability to use the proven PostgreSQL database engine and its fantastic JSON support as a fully-fledged document database. The Marten team believes that a document database has far-reaching benefits for developer productivity over relational databases with or without an ORM tool. Marten also provides .NET developers with an ACID-compliant event store with user-defined projections against event streams. -
24
qBittorrent RuTracker plugin
qBittorrent search engine plugin for rutracker
qBittorrent RuTracker plugin is a lightweight search engine extension designed to integrate the RuTracker torrent index directly into the qBittorrent client, allowing users to search for torrents without leaving the application interface. The plugin follows qBittorrent’s official search plugin architecture and is implemented as a Python script that communicates with the RuTracker website to retrieve and display search results. -
25
ZhParser
PostgreSQL extension for full-text search of Chinese language
zhparser is a PostgreSQL extension for full-text search of Chinese text. It integrates with PostgreSQL's text search engine to tokenize Chinese characters using a dictionary-based segmentation algorithm. zhparser is a valuable tool for improving search accuracy and performance in Chinese-language applications.
