R2R
Search engine
An RAG system built on top of Elasticsearch that enables multimodal search and generation capabilities with a RESTful API and containerized architecture.
The most advanced Retrieval-Augmented Generation (RAG) system, containerized and RESTful
4k stars
27 watching
270 forks
Language: Python
last commit: 4 days ago
Linked from 1 awesome list
artificial-intelligencelarge-language-modelspythonquestion-answeringragretrieval-augmented-generationretrieval-systemssearch
kyrolabs/awesome-langchainRelated projects:
| Repository | Description | Stars |
|---|---|---|
 infiniflow/ragflow | An RAG (Retrieval-Augmented Generation) engine based on deep document understanding for generating truthful question-answering capabilities from complex data. | 22,999 |
 whyhow-ai/rule-based-retrieval | A Python package for creating and managing RAG applications with advanced filtering capabilities | 222 |
 truefoundry/cognita | A modular framework for building production-ready AI applications with integrated data management and model deployment capabilities | 3,305 |
 pathwaycom/llm-app | Pre-built templates for integrating large language models into enterprise applications with real-time data APIs and various data sources. | 4,642 |
 deepset-ai/haystack | An AI orchestration framework to build customizable LLM applications with advanced retrieval methods. | 17,691 |
 miurla/morphic | An AI-powered search engine with a generative UI | 6,299 |
 activerecord-hackery/ransack | A Ruby gem that adds object-based searching to Rails applications. | 5,679 |
 devflowinc/trieve | An all-in-one infrastructure for integrating search, recommendations, RAG, and analytics via API | 1,575 |
 rstudio/shiny | An R package for building interactive web applications with reactive programming and a prebuilt set of widgets. | 5,370 |
 weaviate/verba | A chatbot application utilizing Retrieval Augmented Generation (RAG) and a context-aware database for querying and interacting with data. | 6,328 |
 llmware-ai/llmware | A framework for building enterprise LLM-based applications using small, specialized models | 6,651 |
 quivrhq/quivr | An AI-powered personal assistant framework that integrates various natural language models and databases to provide fast and efficient answers. | 36,681 |
 marker-inc-korea/autorag | An autoML tool to optimize RAG pipelines for data | 2,704 |
 future-house/paper-qa | A package for high-accuracy question answering from scientific documents with citations using retrieval augmented generation (RAG) techniques. | 6,414 |
 root-project/root | A software package for analyzing and visualizing large scientific data sets | 2,707 |