Skip to content

Releases: infiniflow/ragflow

nightly

25 Feb 04:43
@yuzhichang yuzhichang
nightly
98ee3de
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
nightly Pre-release
Pre-release

Release nightly created from 98ee3de at 2025-09-01 21:13:46+08:00

Loading

v0.20.4

27 Aug 10:56
@yuzhichang yuzhichang
v0.20.4
2d89863
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.20.4 Latest
Latest

Summary

Improvements

  • Agent component: Completes Chinese localization for the Agent component.
  • Introduces the ENABLE_TIMEOUT_ASSERTION environment variable to enable or disable timeout assertions for file parsing tasks.
  • Dataset:
    • Improves Markdown file parsing, with AST support to avoid unintended chunking.
    • Enhances HTML parsing, supporting bs4-based HTML tag traversal.

Added models

ZHIPU GLM-4.5

New Agent templates

Ecommerce Customer Service Workflow: A template designed to handle enquiries about product features and multi-product comparisons using the internal knowledge base, as well as to manage installation appointment bookings.

Fixed issues

  • Dataset:
    • Unable to share resources with the team.
    • Inappropriate restrictions on the number and size of uploaded files.
  • Chat:
    • Unable to preview referenced files in responses.
    • Unable to send out messages after file uploads.
  • An OAuth2 authentication failure.
  • A logical error in multi-conditioned metadata searches within a dataset.
  • Citations infinitely increased in multi-turn conversations.

What's Changed

New Contributors

Full Changelog: v0.20.3...v0.20.4

Contributors

ycz87, asiroliu, and 15 other contributors
Assets 2
Loading

v0.20.3

20 Aug 03:08
@yuzhichang yuzhichang
v0.20.3
d55f446
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.20.3

Summary

Improvements

  • Revamps the user interface for the Datasets, Chat, and Search pages.
  • Search and Chat: Introduces document-level metadata filtering, allowing automatic or manual filtering during chats or searches.
  • Search: Supports creating search apps tailored to various business scenarios
  • Chat: Supports comparing answer performance of up to three chat model settings on a single Chat page.
  • Agent:
    • Implements a toggle in the Agent component to enable or disable citation.
    • Introduces a drag-and-drop method for creating components.
  • Documentation: Corrects inaccuracies in the API reference.

New Agent templates

  • Report Agent: A template for generating summary reports in internal question-answering scenarios, supporting the display of tables and formulae. #9427 (The template is now in active use at a research institution.)

Fixed issues

  • The timeout mechanism introduced in v0.20.0 caused tasks like GraphRAG to halt.
  • Predefined opening greeting in the Agent component was missing during conversations.
  • An automatic line break issue in the prompt editor.
  • A memory leak issue caused by PyPDF. #9469

What's Changed

Read more

Contributors

yingfeng, mustangxu, and 23 other contributors
Loading

v0.20.2

19 Aug 11:33
@yuzhichang yuzhichang
v0.20.2
e6cb74b
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.20.2 Pre-release
Pre-release 
Fix (next search): Optimize the search problem interface and related …
Loading

v0.20.1

08 Aug 10:51
@yuzhichang yuzhichang
v0.20.1
9b026fc
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.20.1

Release v0.20.1 created from 9b026fc at 2025-08-08 18:51:10+08:00

Summary

New Features

  • The Retrieval components now support the dynamic specification of knowledge base names using variables.
  • The user interface now includes a French language option.

Added Models

  • GPT 5
  • Claude 4.1

New agent Templates (both workflow and agentic)

  • SQL Assistant Workflow: Empowers non-technical teams (e.g., operations, product) to independently query business data.
  • Choose Your Knowledge Base Workflow: Lets users select a knowledge base to query during conversations. #9325
  • Choose Your Knowledge Base Agent: Delivers higher-quality responses with extended reasoning time, suited for complex queries. #9325

Fixed Issues

  • The Agent component was unable to invoke models installed via vLLM.
  • Agents could not be shared with the team.
  • Embedding an Agent into a webpage was not functioning properly.

What's Changed

Read more

Contributors

mustangxu, sinopec, and 19 other contributors
Loading

v0.20.0

01 Aug 13:59
@yuzhichang yuzhichang
v0.20.0
47ba683
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.20.0

Released on August 1, 2025.

Features and improvements

  • Unified orchestration of both Agents and Workflows.
  • A comprehensive refactor of the Agent, greatly enhancing its capabilities and usability, with support for Multi-Agent configurations, planning and reflection, and visual functionalities.
  • Fully realized MCP functionality, allowing for MCP Server import, Agents functioning as MCP Clients, and RAGFlow itself operating as an MCP Server.
  • Access to runtime logs for Agents.
  • Chat histories with Agents available through the management panel.
  • Integration of a new, more robust version of Infinity, enabling the auto-tagging functionality with Infinity as the underlying document engine.
  • An OpenAI-compatible API that supports file reference information.
  • Support for new models, including Kimi K2, Grok 4, and Voyage.

10 new Agent templates are now available:

  • Multi-Agent based Deep Research: Collaborative Agent teamwork led by a Lead Agent with multiple Subagents, distinct from traditional workflow orchestration.
  • An intelligent Q&A chatbot leveraging internal knowledge bases, designed for customer service and training scenarios.
  • A resume analysis template used by the RAGFlow team to screen, analyze, and record candidate information.
  • A blog generation workflow that transforms raw ideas into SEO-friendly blog content.
  • An intelligent customer service workflow.
  • A user feedback analysis template that directs user feedback to appropriate teams through semantic analysis.
  • Trip Planner: Uses web search and MCP maps to assist with travel planning.
  • Image Lingo: Translates content from uploaded photos.
  • An information search assistant that retrieves answers from both internal knowledge bases and the web.

Breaking changes

From v0.20.0 onwards, Agents are no longer compatible with earlier versions, and all existing Agents from previous versions must be rebuilt following the upgrade.

What's Changed

Read more

Contributors

yuzhichang, huansinho, and 48 other contributors
Loading

v0.19.1

20 Jun 10:00
@yuzhichang yuzhichang
v0.19.1
887651e
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.19.1

v0.19.1

Released on June 23, 2025.

Fixed issues

  • A memory leak issue during high-concurrency requests.
  • Fixed a freezing issue when parsing large files with GraphRAG entity resolution enabled. #8223
  • A context error occurring when using Sandbox in standalone mode. #8340
  • An excessive CPU usage issue caused by Ollama. #8216
  • A bug in the Code Component. #7949

Improvements

  • Added support for Qwen 3 Embedding. #8184
  • Added support for Voyage Multimodal 3. #7987
  • Enabled role-based authentication for S3 bucket access. #8149
  • Added support for models installed via Ollama or VLLM when creating a knowledge base through the API. #8069

What's Changed

Read more

Contributors

panzi, yuzhichang, and 42 other contributors
Loading

v0.19.0

23 May 12:17
@yuzhichang yuzhichang
v0.19.0
6ca1aef
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.19.0

Released on May 26, 2025.

New features

  • Cross-language search is supported in the Knowledge and Chat modules, enhancing search accuracy and user experience in multilingual environments, such as in Chinese-English knowledge bases.
  • Agent component: A new Code component supports Python and JavaScript scripts, enabling developers to handle more complex tasks like dynamic data processing.
  • Enhanced image display: Images in Chat and Search now render directly within responses, rather than as external references. Knowledge retrieval testing can retrieve images directly, instead of texts extracted from images.
  • Claude 4 and ChatGPT o3: Developers can now use the newly released, most advanced Claude model alongside OpenAI’s latest ChatGPT o3 inference model.

The following features are contributed by our community contributors:

  • Agent component: Enables tool calling within the Generate Component. Kudos to notsyncing.
  • Markdown rendering: Image references in a markdown file can be displayed after chunking. Kudos to Woody-Hu.
  • Document engine support: OpenSearch can now be used as RAGFlow's document engine. Kudos to pyyuhao.

What's Changed

Read more

Contributors

benni82, notsyncing, and 37 other contributors
Loading

v0.18.0

23 Apr 06:12
@KevinHuSh KevinHuSh
v0.18.0
94181a9
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.18.0

Release v0.18.0 created from 94181a9 at 2025-04-23 14:11:59+08:00

New features

  • MCP server: enables access to RAGFlow's knowledge bases via MCP.
  • DeepDoc supports adopting VLM model as a processing pipeline during document layout recognition, enabling in-depth analysis of images in PDFs.
  • Agent version control: all updates are continuously logged and can be rolled back to a previous version via export.
  • Team collaboration: Agents can be shared with team members.
  • OpenAI-compatible APIs: Agents can be called via OpenAI-compatible APIs.
  • User registration control: administrators can enable or disable user registration through an environment variable.

Improvements

  • Enhanced answer referencing: Citation accuracy in generated responses is improved.
  • Enhanced question-answering experience: users can now manually stop streaming output during a conversation.

Compatibility changes

  • From this release on wards, built-in re-rank models have been removed because they have minimal impact on retrieval rates but significantly increase retrieval time.

What's Changed

Read more

Contributors

yingfeng, yuzhichang, and 58 other contributors
Loading

v0.17.2

13 Mar 08:12
@yuzhichang yuzhichang
v0.17.2
baf3b9b
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v0.17.2

Improvements

  • Adds OpenAI-compatible APIs.
  • Introduces a German user interface.
  • Accelerates knowledge graph extraction.
  • Enables Tavily-based web search in the Retrieval agent component.
  • Adds Tongyi-Qianwen QwQ models (OpenAI-compatible).
  • Supports CSV files in the General chunk method.

Fixed issues

  • Unable to add models via Ollama/Xinference, an issue introduced in v0.17.1.

Related APIs

HTTP APIs

Create chat completion

Python APIs

Create chat completion

What's Changed

New Contributors

Full Changelog: v0.17.1...v0.17.2

Contributors

yuzhichang, asiroliu, and 11 other contributors
Loading