# sciphi-ai/r2r

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/sciphi-ai-r2r).**

7,891 stars · 635 forks · Python · MIT

## Links

- GitHub: https://github.com/SciPhi-AI/R2R
- awesome-repositories: https://awesome-repositories.com/repository/sciphi-ai-r2r.md

## Description

R2R is an agentic retrieval-augmented generation platform that uses reasoning agents to perform multi-step data fetching for context-aware answering. It functions as a multimodal vector database manager and knowledge graph engine designed to ground artificial intelligence responses in verified factual knowledge.

The platform distinguishes itself by combining reasoning agents for complex research automation with a knowledge graph that maps entity relationships. This allows the system to perform structured data traversal alongside unstructured vector search to resolve complex questions from internal knowledge bases and the web.

The system covers multimodal content ingestion for various file types, hybrid semantic-keyword search, and collection-based data isolation for multi-tenant access control. These capabilities are exposed through a programmable REST API gateway.

## Tags

### Artificial Intelligence & ML

- [Agentic RAG Platforms](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-rag-platforms.md) — Operates as a comprehensive platform using LLMs and reasoning agents for multi-step retrieval-augmented generation.
- [Agentic RAG Development](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-rag-development.md) — Provides a framework for building intelligent, self-correcting retrieval systems using agentic reasoning.
- [Agentic Retrieval Frameworks](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-retrieval-frameworks.md) — Employs reasoning agents to decompose complex queries into multiple retrieval steps and synthesize the results.
- [Knowledge Graph Construction](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/knowledge-graph-engineering/knowledge-graph-construction.md) — Implements automated extraction of entities and relationships from ingested data to build connected knowledge bases. ([source](https://github.com/sciphi-ai/r2r#readme))
- [Retrieval Augmented Generation](https://awesome-repositories.com/f/artificial-intelligence-ml/language-model-orchestration/retrieval-augmented-generation.md) — Implements a system that grounds AI responses in verified factual knowledge through a retrieval-augmented generation pipeline. ([source](https://github.com/sciphi-ai/r2r#readme))
- [Retrieval-Augmented Agents](https://awesome-repositories.com/f/artificial-intelligence-ml/retrieval-augmented-agents.md) — Combines reasoning agents with retrieval tools to perform multi-step data fetching for context-aware responses. ([source](https://github.com/sciphi-ai/r2r#readme))
- [Deep Research Execution](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-task-execution/deep-research-execution.md) — Uses multi-step reasoning and collaborative agents to fetch information and resolve complex research questions. ([source](https://github.com/sciphi-ai/r2r#readme))
- [AI Knowledge Management](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-knowledge-management.md) — Organizes internal multimodal content into searchable databases to support AI-driven factual grounding.
- [Automated Research Platforms](https://awesome-repositories.com/f/artificial-intelligence-ml/automated-research-platforms.md) — Coordinates AI agents to conduct research across internal bases and the web to resolve complex questions.
- [Multimodal Normalization](https://awesome-repositories.com/f/artificial-intelligence-ml/data-ingestion-pipelines/multimodal-normalization.md) — Parses diverse file formats into a normalized text representation for consistent indexing and retrieval.

### Data & Databases

- [Knowledge Graphs](https://awesome-repositories.com/f/data-databases/entity-relationships/knowledge-graphs.md) — Builds a knowledge graph that maps entity relationships to enable structured data traversal alongside vector search.
- [Hybrid Search Engines](https://awesome-repositories.com/f/data-databases/hybrid-search-engines.md) — Integrates vector-based semantic retrieval with traditional keyword-based indexing for high-accuracy data discovery. ([source](https://github.com/sciphi-ai/r2r#readme))
- [Hybrid Vector-Keyword Indexing](https://awesome-repositories.com/f/data-databases/hybrid-vector-keyword-indexing.md) — Combines dense vector embeddings with traditional keyword matching to improve document retrieval accuracy.
- [Knowledge Graph Indexing Engines](https://awesome-repositories.com/f/data-databases/knowledge-graph-indexing-engines.md) — Extracts entities and relationships from unstructured data to build connected knowledge graph representations.
- [Multimodal Search](https://awesome-repositories.com/f/data-databases/semantic-search/multimodal-search.md) — Manages the ingestion and retrieval of multimodal content like text and images via hybrid search.
- [Multimodal Document Ingestion](https://awesome-repositories.com/f/data-databases/data-engineering-infrastructure/data-extraction-ingestion/data-ingestion/multimodal-document-ingestion.md) — Parses various file types, including PDFs and images, to prepare multimodal data for indexing. ([source](https://github.com/sciphi-ai/r2r#readme))
- [Hybrid Retrieval](https://awesome-repositories.com/f/data-databases/search-indexing-technologies/search-indexing/search-information-retrieval/hybrid-retrieval.md) — Combines vector similarity and full-text keyword matching to enhance retrieval accuracy within large datasets.

### Development Tools & Productivity

- [REST APIs](https://awesome-repositories.com/f/development-tools-productivity/rest-apis.md) — Provides a programmable REST API to integrate agentic retrieval and factual grounding into external applications.

### DevOps & Infrastructure

- [RESTful](https://awesome-repositories.com/f/devops-infrastructure/api-gateways/restful.md) — Exposes retrieval and ingestion logic through a standardized RESTful API gateway for external integration.

### Security & Cryptography

- [Application Data Isolation](https://awesome-repositories.com/f/security-cryptography/multi-tenant-isolation-layers/application-data-isolation.md) — Provides collection-based namespaces to enforce strict data separation and access control for multi-tenant environments.
- [User Access Management](https://awesome-repositories.com/f/security-cryptography/user-access-management.md) — Provides administrative control of user identities and implements collection-based data isolation for multi-tenant access. ([source](https://github.com/sciphi-ai/r2r#readme))

### Part of an Awesome List

- [Application Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/application-frameworks.md) — Framework for rapid development of production-ready RAG systems.
- [Retrieval Augmented Generation](https://awesome-repositories.com/f/awesome-lists/ai/retrieval-augmented-generation.md) — Platform for building and deploying RAG applications.