Skip to content

ragflow

v0.26.1 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo RAG & Retrieval
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-harness agentic-ai agentic-retrieval agentic-search ai ai-agents
+8 more
context-engine context-engineering context-management harness-engineering knowledge-compilation llm-apps llm retrieval-augmented-generation

Summary

AI summary

Broad release touches Bug fixes, fix, Go, and Fix.

Full changelog

Summary

New features

  • Model provider: Allows users to modify the model type of existing model configurations. #16029
  • Chat channel: Enables users to deploy RAGFlow assistants as chatbots within external messaging platforms like Discord and Feishu. #15850
  • Observability: Groups multi-turn chat traces by session within Langfuse to facilitate conversation debugging and replay. #15679

i18n

  • Adds ~70 missing translation keys for the French UI. #15983

Bug fixes

  • Model provider: Fixes inaccurate token billing, corrects embedding truncation limits to prevent indexing failures, and refactors error handling to surface root error causes. #15424
  • API: Adds a legacy mode to the /chat/completions endpoint to restore the v0.23.0 style <think> output for backward compatibility. #16014 See also Converse with chat assistant.

What's Changed

  • Go: add dimensions for list models and fix some embed-bug in providers by @Haruko386 in https://github.com/infiniflow/ragflow/pull/15940
  • feat(models): add shared HTTP client, SSE parser, and stub helpers for Go model drivers by @JPette1783 in https://github.com/infiniflow/ragflow/pull/15821
  • fix(user-settings): collapse sidebar to icon-only rail on mobile by @carlh7777 in https://github.com/infiniflow/ragflow/pull/15678
  • fix(llm): correct error handling, token accounting, and truncation in embedding providers by @Dexterity104 in https://github.com/infiniflow/ragflow/pull/15424
  • Improve docx preview by @yingfeng in https://github.com/infiniflow/ragflow/pull/15907
  • fix: keep max pagerank for repeated n-hop edges by @he-yufeng in https://github.com/infiniflow/ragflow/pull/15696
  • feat: Langfuse session grouping for multi-turn chat traces by @jonathanchang31 in https://github.com/infiniflow/ragflow/pull/15679
  • fix(profile): enforce profile name validation and input constraints by @carlh7777 in https://github.com/infiniflow/ragflow/pull/15694
  • Json: add some models by @Haruko386 in https://github.com/infiniflow/ragflow/pull/15947
  • feat(go): Add Z.ai model entries to all_models.json Add missing Qwen commercial models and provider aliases by @Hz-186 in https://github.com/infiniflow/ragflow/pull/15929
  • Go: use NATS as the message queue by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/15327
  • fix(go): redact internal handler errors by @bitloi in https://github.com/infiniflow/ragflow/pull/15746
  • Fix: chat/agent -- Default avatar is not displaying correctly. by @cike8899 in https://github.com/infiniflow/ragflow/pull/15948
  • Go: parse ingestion DSL by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/15938
  • Decouple skill space from Python API by @yingfeng in https://github.com/infiniflow/ragflow/pull/15971
  • Feat: chat channels — connect assistants to external messaging bots by @KevinHuSh in https://github.com/infiniflow/ragflow/pull/15850
  • fix(Go-models): preserve model name lookup when aliases exist by @Haruko386 in https://github.com/infiniflow/ragflow/pull/15969
  • Json[model-provider] add nvidia, moonshot, minimax, claude, GPT models by @Haruko386 in https://github.com/infiniflow/ragflow/pull/15970
  • Go: add office_oxide and parse docx file. by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/15976
  • fix: SSE write timeout by @bitloi in https://github.com/infiniflow/ragflow/pull/15852
  • feat(agent): Go port — canvas engine, 22 components, DSL v2, 13 endpoints by @yuzhichang in https://github.com/infiniflow/ragflow/pull/15952
  • Go: add more file parser by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/15979
  • i18n(fr): add ~70 missing French translation keys by @vincentlambert in https://github.com/infiniflow/ragflow/pull/15983
  • Go: file parser config by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/15989
  • Fix last login time by @wangq8 in https://github.com/infiniflow/ragflow/pull/16004
  • Go: refactor model API to accept model id by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/15999
  • fix: use /api/tags endpoint for Ollama model listing (#16000) by @zaviermeekz-cpu in https://github.com/infiniflow/ragflow/pull/16003
  • Add git-like file commit API by @yingfeng in https://github.com/infiniflow/ragflow/pull/15978
  • feat(go-models): Add google models to all_models.json by @Hz-186 in https://github.com/infiniflow/ragflow/pull/16007
  • feat: add custom value support for s3 region by @buua436 in https://github.com/infiniflow/ragflow/pull/15968
  • refactor(go): replace GenerateUUID1 with GenerateToken for entity IDs by @Hz-186 in https://github.com/infiniflow/ragflow/pull/16010
  • Move REDIS to engine dir by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/16006
  • Go: add Markdown parser by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/16016
  • Json: add many models to all_models.json by @Haruko386 in https://github.com/infiniflow/ragflow/pull/16013
  • fix: output 2 lines when list-supported models by @Haruko386 in https://github.com/infiniflow/ragflow/pull/16015
  • fix(api): return 4xx not 500 when attachment blob is missing by @dripsmvcp in https://github.com/infiniflow/ragflow/pull/15509
  • Go: parse HTML file by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/16018
  • Go: add API mode check in file system command by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/16022
  • Fix: Adjust chat line height. by @cike8899 in https://github.com/infiniflow/ragflow/pull/16021
  • Fix one data source can be synced to multiple dataset by @wangq8 in https://github.com/infiniflow/ragflow/pull/16023
  • Feat: Move less important chat settings into a collapsible panel. by @cike8899 in https://github.com/infiniflow/ragflow/pull/16024
  • Feat: model provider by @Lynn-Inf in https://github.com/infiniflow/ragflow/pull/16028
  • Feat: Add edit model type function by @dcc123456 in https://github.com/infiniflow/ragflow/pull/16029
  • Feat: add harness-go framework —— graph engine by @yingfeng in https://github.com/infiniflow/ragflow/pull/16039
  • feat[Go] add max_dimension and dimensions for ModelRequest by @Haruko386 in https://github.com/infiniflow/ragflow/pull/16019
  • fix: add legacy chat/completions mode by @buua436 in https://github.com/infiniflow/ragflow/pull/16014
  • fix: sandbox config api method mismatch by @buua436 in https://github.com/infiniflow/ragflow/pull/16031
  • Feat: add harness-go framework —— agent core by @yingfeng in https://github.com/infiniflow/ragflow/pull/16045
  • Dev: consoldiate dev script by @wangq8 in https://github.com/infiniflow/ragflow/pull/16066
  • Refactor: Change table chat_channel status data type. by @KevinHuSh in https://github.com/infiniflow/ragflow/pull/16061
  • feat(go-api): support setting tenant default models by model_id by @Hz-186 in https://github.com/infiniflow/ragflow/pull/16030
  • feat(go-cli): support add models with embedding type by @Hz-186 in https://github.com/infiniflow/ragflow/pull/16020
  • feat(go-models): add more providers by @Hz-186 in https://github.com/infiniflow/ragflow/pull/16017
  • fix: improve remember me checkbox UX in login form by @BasilFoubert in https://github.com/infiniflow/ragflow/pull/16051
  • Fix: filter unsupported model_type by @Lynn-Inf in https://github.com/infiniflow/ragflow/pull/16062
  • fix: add toc field to extractor output by @buua436 in https://github.com/infiniflow/ragflow/pull/16059
  • Go: fix register user by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/16058
  • Document: github release for RAGFlow Go CLI by @Haruko386 in https://github.com/infiniflow/ragflow/pull/16036
  • fix(go): all_models.json by @Hz-186 in https://github.com/infiniflow/ragflow/pull/16075
  • Fix: v0.26.1 model provider by @Lynn-Inf in https://github.com/infiniflow/ragflow/pull/16073
  • fix: resolve the error caused by office_oxide by @Haruko386 in https://github.com/infiniflow/ragflow/pull/16078
  • Fix auto migration issue by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/16081
  • fix: update localization keys for image2text and add ocr option by @dcc123456 in https://github.com/infiniflow/ragflow/pull/16076
  • fix: update channelTemplates to filter for Discord and Lark only by @dcc123456 in https://github.com/infiniflow/ragflow/pull/16065
  • fix: remove unnecessary div in profile page layout by @dcc123456 in https://github.com/infiniflow/ragflow/pull/16091
  • fix workflow ss not found by @myf-bee in https://github.com/infiniflow/ragflow/pull/16085
  • fix: remove unnecessary 'asChild' prop from FilterButton component by @dcc123456 in https://github.com/infiniflow/ragflow/pull/16094
  • Docs: Added v0.26.1 release notes by @writinwaters in https://github.com/infiniflow/ragflow/pull/16087
  • Fix: SSRF in markdown parser remote image fetch by @galuis116 in https://github.com/infiniflow/ragflow/pull/15438
  • fix: rename dialog_id to chat_id in chat_channel (backend + frontend) by @KevinHuSh in https://github.com/infiniflow/ragflow/pull/16096
  • Refactor: rename /chat_channels to /chat-channels by @wangq8 in https://github.com/infiniflow/ragflow/pull/16099
  • build(deps): bump starlette from 0.51.0 to 1.3.1 by @dependabot[bot] in https://github.com/infiniflow/ragflow/pull/16089
  • Go refactor: merge similar functions by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/16098
  • refactor(paddleocr): migrate from sync API to async Job API by @Rander7 in https://github.com/infiniflow/ragflow/pull/15967
  • feat(paddleocr): add image parsing support with async Job API by @Rander7 in https://github.com/infiniflow/ragflow/pull/16086
  • fix: paginate non-DeepDOC PDF parsing tasks to prevent OOM by @euvre in https://github.com/infiniflow/ragflow/pull/15951
  • build(deps): bump aiohttp from 3.13.3 to 3.14.1 by @dependabot[bot] in https://github.com/infiniflow/ragflow/pull/16090
  • Docs: update chat completions docs by @buua436 in https://github.com/infiniflow/ragflow/pull/16100
  • Revert "fix: paginate non-DeepDOC PDF parsing tasks to prevent OOM" by @wangq8 in https://github.com/infiniflow/ragflow/pull/16104
  • Go: add more start server parameters by @JinHai-CN in https://github.com/infiniflow/ragflow/pull/16093
  • fix: paginate non-DeepDOC PDF parsing tasks to prevent OOM by @euvre in https://github.com/infiniflow/ragflow/pull/16106
  • Fix: Importing the MCP dialog causes duplicate submissions. by @cike8899 in https://github.com/infiniflow/ragflow/pull/16037
  • feat(go/dao): migrate chat channel database entity and DAO to Go by @Hz-186 in https://github.com/infiniflow/ragflow/pull/16055
  • Fix RAGFlow cannot start by @wangq8 in https://github.com/infiniflow/ragflow/pull/16116
  • Docs: Updated Converse with chat assistant by @writinwaters in https://github.com/infiniflow/ragflow/pull/16117
  • feat(go-models): harden ListModels for FishAudio (#15853) by @hunnyboy1217 in https://github.com/infiniflow/ragflow/pull/15957
  • fix: return full record in get_ingestion_log by @euvre in https://github.com/infiniflow/ragflow/pull/16120
  • Fix MinerU table option sanitization by @wangq8 in https://github.com/infiniflow/ragflow/pull/16118
  • feat(agent): ship the Go agent canvas port — eino interrupt/resume + Redis check-pointing by @yuzhichang in https://github.com/infiniflow/ragflow/pull/16035
  • fix: tighten embedding truncation threshold by @buua436 in https://github.com/infiniflow/ragflow/pull/16123
  • fix: show telegram chat channel by @buua436 in https://github.com/infiniflow/ragflow/pull/16125
  • Set default Paddle OCR URL by @wangq8 in https://github.com/infiniflow/ragflow/pull/16128
  • Enhancement: optimize ci by @6ba3i in https://github.com/infiniflow/ragflow/pull/16130
  • fix: chat channel runtime by @buua436 in https://github.com/infiniflow/ragflow/pull/16129
  • Update doc rerank_id from int to string by @wangq8 in https://github.com/infiniflow/ragflow/pull/16142
  • Dev: add go starter by @wangq8 in https://github.com/infiniflow/ragflow/pull/16138
  • Fix: The .docx file is not displaying fully; the hierarchy of the pipeline created from the template is missing. by @cike8899 in https://github.com/infiniflow/ragflow/pull/16134
  • fix: misc frontend fixes for agent log, login, search settings by @dcc123456 in https://github.com/infiniflow/ragflow/pull/16137
  • Fix: The pipeline created from the template fails immediately upon execution. by @cike8899 in https://github.com/infiniflow/ragflow/pull/16149
  • refactor(go-models): harden Ollama ListModels and route through ParseListModel (#15853) by @hunnyboy1217 in https://github.com/infiniflow/ragflow/pull/15955
  • feat: add qqbot chat channel by @buua436 in https://github.com/infiniflow/ragflow/pull/16140
  • Docs: Updated v0.26.1 release date. by @writinwaters in https://github.com/infiniflow/ragflow/pull/16154
  • Fix: add mimo by @Lynn-Inf in https://github.com/infiniflow/ragflow/pull/16136
  • Fix: A pipeline created from a template fails immediately upon execution with a "hierarchy does not exist" error. by @cike8899 in https://github.com/infiniflow/ragflow/pull/16151
  • fix(go): correct OpenRouter streaming URL routing and reasoning parameter by @bittoby in https://github.com/infiniflow/ragflow/pull/16111
  • Enhancement: update ci for parallel test execution by @6ba3i in https://github.com/infiniflow/ragflow/pull/16133
  • Docs: Update version references to v0.26.1 in READMEs and docs by @asiroliu in https://github.com/infiniflow/ragflow/pull/16158
  • build(deps): bump python-multipart from 0.0.21 to 0.0.31 by @dependabot[bot] in https://github.com/infiniflow/ragflow/pull/16088
  • fix back release.yml to old version by @Haruko386 in https://github.com/infiniflow/ragflow/pull/16160

New Contributors

  • @carlh7777 made their first contribution in https://github.com/infiniflow/ragflow/pull/15678
  • @BasilFoubert made their first contribution in https://github.com/infiniflow/ragflow/pull/16051
  • @myf-bee made their first contribution in https://github.com/infiniflow/ragflow/pull/16085
  • @Rander7 made their first contribution in https://github.com/infiniflow/ragflow/pull/15967

Full Changelog: https://github.com/infiniflow/ragflow/compare/v0.26.0...v0.26.1

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track ragflow

Get notified when new releases ship.

Sign up free

About ragflow

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

All releases →

Related context

Beta — feedback welcome: [email protected]