Skip to content

Releases: SciPhi-AI/R2R

R2R v3.3.30

23 Jan 20:17
@emrgnt-cmplxty emrgnt-cmplxty
v3.3.30
7d494d4
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
R2R v3.3.30 Latest
Latest

Released on January 23, 2025

We’re excited to announce the newest release of R2R: v3.3.30! This version contains major enhancements to the agent’s capabilities, new Docker Swarm support, additional configuration options for security and extended model support, and numerous other improvements and fixes. Below is an overview of the most noteworthy changes.

🚀 Major Agent Upgrades

Date & Knowledge Base Awareness

  • Date awareness: Agents now have improved context about current dates and times, enabling more precise and contextually correct responses.
  • Knowledge base insights: Agents can query all available documents, their summaries, collections, and sizes. This means more intelligent retrieval and referencing of ingested data, paving the way for advanced summarization and context understanding.

Enhanced Tooling

  • New content tool: Fetch the raw content of any document directly, enabling single-document summarizations and specialized analysis without a broad search.
  • web_search tool enabled by default: Agents can call the web search tool to gather external information. This is configured out-of-the-box for the Rowland environment and can be toggled as needed.
  • local_search improvements: Continues to be available for local knowledge retrieval, now with refined logic to ensure faster and more accurate searches.

Improved Agent Configuration

  • Refactored agent settings: agent_config replaces the older self.config.agent usage, streamlining how agent behavior is controlled and removing extraneous parameters.
  • Cleaner messaging flows: Internally, message-handling logic was overhauled for greater consistency, resulting in fewer edge cases and a more robust conversation flow.

🛠 New Features & Enhancements

Docker Swarm Support

  • Horizontal scaling: R2R can now be deployed via Docker Swarm for easier clustering in distributed environments.
  • Updated Compose files: compose.full.swarm.yaml, compose.full.yaml, and compose.yaml include references for seamless Docker Swarm service orchestration.

XAI / GROK Integration

  • New XAI_API_KEY environment variable: Allows use of advanced XAI/GROK models.
  • Example Compose updates: XAI_API_KEY is now present in .env.example and Docker Compose configurations, so you can pass authentication for these models automatically.

JWT Auth Provider

  • JWT-based authentication: Added as a new auth provider, enabling a more secure and standardized authentication flow across R2R setups.
  • Integration: Configure your JWT settings in the R2R config files to protect endpoints with token-based security.

Knowledge Graph & Document Processing

  • kg_clustering & kg_community_summary fixes: Corrected indexing and num_communities handling, and improved the functions’ return structures for better downstream usage.
  • Hatchet fallback ingestion: Introduced a fallback ingestion path to ensure documents are successfully processed even if the primary method encounters errors.
  • Empty page allowance: The PDF parser no longer raises an error for empty pages, making ingestion more robust across diverse document formats.
  • Automatic total_tokens column: R2R now automatically adds a total_tokens column to the documents table if missing, avoiding migration blockers and reducing friction for existing installations.

Configuration Examples & Cleanup

  • Combined Example TOML: All possible configuration parameters are now grouped into a single example r2r.toml, making it simpler to discover and enable new features.
  • Refactored agent & retrieval logic: Extraction of common RAG agent patterns into a dedicated RAGAgentMixin. Simplifies how local/web searches and content lookups are handled in agent code.
  • Pre-commit linting: Ensures consistent code style and quality, lowering the bar for new contributors to keep the repository clean.

🐛 Bug Fixes & Stability

  • Agent runtime spec corrections: Addressed edge cases where the agent would misinterpret or fail to execute runtime specifications.
  • Graph extraction patches: Improved how graph data is extracted and utilized, reducing errors in advanced knowledge graph operations.
  • RAG streaming resilience: Re-introduced and enhanced streaming capabilities for RAG-based queries, fixing stability issues in streaming responses.
  • Build cluster logic: Patched a bug in the cluster-building logic to ensure robust knowledge graph creation even in complex document sets.

⚙️ Developer Experience

  • Dockerfile for Unstructured: Updated with the latest NLTK data changes. Streamlines building and running the unstructured text processing environment by removing outdated Dockerfiles and consolidating dependencies.
  • Code refactoring & cleaning: Removal of deprecated pipelines, improved logging messages, and better error handling throughout the codebase.
  • Testing improvements: Extended and refactored tests, including coverage for new agent tools, collection ID filters, and database migrations.

👥 New Contributors

Thank you for helping make R2R even better!

Getting Started & Upgrading

  1. Pull the latest docker images or update your code from the [R2R GitHub repository](https://github.com/SciPhi-AI/R2R).
  2. Set up new environment variables (XAI_API_KEY) if you intend to use XAI/GROK model features.
  3. Run migrations to ensure the new total_tokens column is present in the documents table. R2R automatically attempts to add this column if it’s missing, with no downtime or data loss.
  4. Review your r2r.toml (or equivalent config) for updated agent and RAG entries, especially if you want to enable or disable new search tools at runtime.

Full Changelog

For a comprehensive list of changes, including commits and pull requests, see the official [GitHub comparison between v3.3.29 and v3.3.30](v3.3.29...v3.3.30).

We appreciate your support and feedback. If you have questions or run into any issues, please open an issue on [GitHub](https://github.com/SciPhi-AI/R2R/issues) or reach out on our community forum. Happy building!

Assets 2
Loading

v3.3.29

16 Jan 18:15
@NolanTrem NolanTrem
v3.3.29
1c5938f
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v3.3.29

Adds in contextual enrichment, which you can learn more about here: https://r2r-docs.sciphi.ai/documentation/contextual-enrichment

What's Changed

Full Changelog: v3.3.28...v3.3.29

Contributors

NolanTrem and emrgnt-cmplxty
Assets 2
Loading

v3.3.28

15 Jan 19:33
@NolanTrem NolanTrem
v3.3.28
7ba5105
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v3.3.28

Introduces deduplication, automatic extraction and deduplication, as well as a number of bug fixes.

What's Changed

Full Changelog: 3.3.27...v3.3.28

Contributors

NolanTrem and emrgnt-cmplxty
Assets 2
Loading

3.3.27

11 Jan 03:59
@NolanTrem NolanTrem
3.3.27
9ec211f
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
3.3.27

A number of bug fixes, introduction of more user management configurations, and refined graph processes to better support local LLMs.

What's Changed

Read more

Contributors

yigitkonur, NolanTrem, and 2 other contributors
Assets 2
Loading

v3.3.0

05 Dec 00:56
@NolanTrem NolanTrem
v3.3.0
e407e87
Compare
Choose a tag to compare
v3.3.0

With the release of v3.3.0, R2R offers a completely RESTful API that covers everything you need for production RAG applications. The biggest change is our Git-like knowledge graph architecture, but we've also unified all the core objects you need to build real applications.

📚 Complete API Coverage:

1️⃣ Content & Knowledge
• Documents: Upload files, manage content, and track extraction status
• Chunks: Access and search vectorized text segments
• Graphs: Git-like knowledge graphs with:
↳ Entities & Relationships
↳ Automatic community detection
↳ Independent graphs per collection

2️⃣ Infrastructure
• Indices: Manage vector indices for search optimization
• Collections: Organize documents and share access
• Users: Built-in auth and permission management
• Conversations: Track chat history and manage branches

3️⃣ Retrieval & Generation
• RAG: Configurable retrieval pipeline with hybrid search
• Agents: Conversational interfaces with knowledge graph integration
• Search: Vector, keyword, and knowledge graph search

💻 Quick Example:

from r2r import R2RClient
client = R2RClient("http://localhost:7272")

# Document level extraction
client.documents.extract(document_id)

# Collection level graph management
client.graphs.pull(collection_id)

# Advanced RAG with everything enabled
response = client.retrieval.rag(
    "Your question here",
    search_settings={
        "use_hybrid_search": True,
        "graph_settings": {"enabled": True}
    }
)

All these components work together seamlessly - just configure what you need and R2R handles the rest. Perfect for teams building serious RAG applications.

🔗 Check the API: https://r2r-docs.sciphi.ai/api-and-sdks/introduction

We'd love feedback from folks building in production!

Assets 2
Loading

R2R V3.2.30

23 Oct 22:15
@NolanTrem NolanTrem
v3.2.30
edf8220
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
R2R V3.2.30

Among a number of bug fixes, scaling, and performance improvements, there are a few notable features and considerations.

Migrations
With this release, we introduce a number of changes that require migrations. To run migrations, you can update to the latest version of R2R with r2r update, upon serving R2R (e.g. r2r serve --docker) the schema will be checked, and you will be prompted to upgrade your database with r2r db upgrade.

Advanced GraphRAG
We're rolling out prompt tuning and contextual embeddings, which both offer significant improvements.

Assets 2
Loading

R2R V3.2.0

02 Oct 14:18
@emrgnt-cmplxty emrgnt-cmplxty
v3.2.0
3721fcb
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
R2R V3.2.0

Key Features and Improvements:

  • Introduced light and full installation modes to facilitate faster setup / prototyping
  • Removed Neo4j dependency - GraphRAG is now done entirely in Postgres, we will be writing a blog post around our motivations for this change.
  • Commitment to stable releases and migration - R2R is moving towards serious use cases and is committed to providing working migration scripts with each major change following 3.2.0. This will be the last painful migration.

Optimizations:

  • Improved knowledge graph configuration and construction process
  • Added new prompt endpoints and management features
  • Renamed groups to collections for improved clarity
  • Integrated Supabase authentication
  • Simplified hybrid search functionality
  • Improved error messaging and handling
  • Enhanced Docker configuration and build process

Documentation:

  • Updated and fixed documentation, including broken links in Mintlify
  • Improved configuration documentation for various components

Bug Fixes:

  • Resolved issues with Docker commands and configurations
  • Fixed parsing config docs
  • Addressed problems with app settings and prompt management
  • Corrected various minor bugs and typos

Developer Experience:

  • Updated dependencies and package versions
  • Improved typing and pagination
  • Enhanced JS SDK with auto-refresh capability

Full Changelog: V3.1.0...v3.2.0

Assets 2
Loading

R2R V3.1.0

06 Sep 19:08
@NolanTrem NolanTrem
V3.1.0
16786e8
Compare
Choose a tag to compare
R2R V3.1.0

New Features
Orchestration with Hatchet
Default ingestion provider set to Unstructured
Improved knowledge graph construction process

Bug Fixes
Minor bug fixes around config logic and other.

Full Changelog: v0.3.0...V3.1.0

Assets 2
Loading

R2R V3

23 Aug 23:33
@emrgnt-cmplxty emrgnt-cmplxty
v0.3.0
00d6c19
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
R2R V3

We are very excited to introduce R2R V3. We have been working very intensely as a team over this past month to comprehensively address all the feedback we received after recent explosive growth in R2R usage.

In addition to modifying 420 files and tens of thousands of LOC in the core repository, we have refactored the documentation here - https://r2r-docs.sciphi.ai/introduction.

NOTE - This release has many breaking changes w.r.t to R2R v2 and so we are working on a bespoke migration script to help those already in production.

Highlights

  • We've added full GraphRAG support as per the Microsoft GraphRAG paper. This implementation is built alongside our integration with Neo4j inside R2R so that you can build a non-ephemeral user-facing system. The system supports dynamic tuning of a number of query parameters so that you can optimize it for your given application, you can read more here!
  • Added full group permissions over vector search, meaning you can create unique dynamic groupings of documents which are permissioned at the user level. Support is included for granular actions like create_group, update_group, add_user_to_group, add_document_to_group, add_user_to_group, and more. Get started with the cookbook here.
  • We've doubled down on hybrid search by improving the full-text search component and its integration with vector search. The new system employs advanced techniques including text stemming, synonym expansion, phrase matching, and partial matching, all combined with a sophisticated ranking algorithm. Additionally, we've implemented runtime configurability through the VectorSearchSettings object. You can read more here.
  • We've implemented a powerful RAG Agent that enables developers to add custom tools and behaviors tailored to specific use cases. This allows R2R developers to trivially go from RAG to Agentic RAG, allowing 1-click construction of full chat intelligence. You can read more here.
  • Bug fixes and new focus on production R2R has matured significantly over the last quarter and has now answered over 1 million questions in production. As the system matures we are focusing more on supporting developers in production and carrying out our active development in a way that is minimally disruptive. This new release polishes a number of features that were rough / experimental in V2, while removing some features that were not seeing enough use, such as continuous evaluation.
  • Slim CLI and Python SDK to reduce bloat required to launch / interact with R2R through docker.

What's Changed

New Contributors

Full Changelog: v0.2.85...v3.0.0*

Contributors

manuelciosici, tkellogg, and 5 other contributors
Assets 2
Loading

v0.2.85

13 Aug 18:20
@NolanTrem NolanTrem
v0.2.85
9fe50bf
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.2.85

A few important bug fixes in 0.2.85!

What's Changed

  • Fix parsing config in example config files by @hvoecking in #864
  • Allow BASE_URL and TRAEFIK_DASHBOARD_PORT (added) to be passed in from environment vars by @smig23 in #862
  • Add agent entry to set local ollama/llama3.1 model by @smig23 in #866

New Features

  • Environment variable support for BASE_URL and TRAEFIK_DASHBOARD_PORT

Bug Fixes

  • Fixed parsing config in example config files
  • Added agent entry in config for local ollama/llama3.1 model

New Contributors

We'd like to extend a warm welcome to our new contributor and thank all those who made this release possible!

Full Changelog

For a detailed list of all changes, please see: v2.0.84...v0.2.85

To update to this version, run r2r update from your CLI. If you encounter any issues or have any questions, please don't hesitate to open an issue on Github!

Contributors

hvoecking and smig23
Assets 2
Loading