8 Pull requests merged by 6 people

• Test: Refactor test concurrency handling and add SDK chunk management tests

  #8112 merged Jun 6, 2025

• Docs: Added auto-keyword auto-question guide

  #8113 merged Jun 6, 2025

• Feat: Reference the output variable of the upstream operator #3221

  #8111 merged Jun 6, 2025

• Fix: QWenCV issue.

  #8106 merged Jun 6, 2025

• Feat: Enables the message operator form to reference the data defined by the begin operator #3221

  #8108 merged Jun 6, 2025

• Feat: Receive reply messages of different event types from the agent #3221

  #8100 merged Jun 6, 2025

• task_limiter with trio.Semaphore

  #8102 merged Jun 6, 2025

• fix: single task executor getting all tasks from Redis queue

  #7330 merged Jun 6, 2025

3 Issues closed by 2 people

• [Bug]: QWenCV failed to extract text from structured streaming responses

  #8097 closed Jun 6, 2025

• [Bug]: when stream=false，new message without sessionid does no

  #8070 closed Jun 6, 2025

• [Question]: Can ragflow demo be used as external knowledge base of dify?

  #8103 closed Jun 6, 2025

9 Issues opened by 9 people

• [Question]: Technical Specifications of Ragflow's Data Capacity and Key Considerations

  #8117 opened Jun 7, 2025

• [Bug]: LMstudio rerank model isn't supported

  #8116 opened Jun 6, 2025

• [Feature Request]: Add Webhook Component to RAGFlow Workflows

  #8115 opened Jun 6, 2025

• [Bug]: pyicu installation failure on ubuntu os via v sync --python 3.10 --all-extras

  #8110 opened Jun 6, 2025

• [Question]: In v0.19.0, why does only the General chunking method automatically call the VL model to parse pdf docs? Other chunking methods still use OCR even if the PDF parser is set to a VL model.

  #8109 opened Jun 6, 2025

• [Feature Request]: Retrieval component support cross-lang search

  #8107 opened Jun 6, 2025

• [Question]: The Linux operating system based on ARM architecture parses documents too slowly

  #8105 opened Jun 6, 2025

• [Question]: My document context language is Chinese, but generated question is English or mixed. why? and how to configure it ? thanks

  #8104 opened Jun 6, 2025

• [Question]: Build docker Image Fail

  #8101 opened Jun 6, 2025

15 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• [Feature Request]:optional ai model during chunk creation

  #8071 commented on Jun 6, 2025 • 0 new comments

• [Question]: QA Chunk Embedding and File Management API

  #8087 commented on Jun 6, 2025 • 0 new comments

• [Bug]: Can't upload more than 10 MB in batch, locally deployed docker

  #8027 commented on Jun 6, 2025 • 0 new comments

• [Bug]: GraphRAG will not finish - multiple failures and parsing stuck after 36 hours and $200 on openai-mini models

  #7957 commented on Jun 6, 2025 • 0 new comments

• [Bug]: Text excerpts from file prompts.py contianed in generated answer

  #8060 commented on Jun 6, 2025 • 0 new comments

• [Question]: Cann't start ragflow-es-01

  #2884 commented on Jun 6, 2025 • 0 new comments

• [Question]: Why is it not necessary to set up an embedding model when creating a chat assistant?

  #8086 commented on Jun 6, 2025 • 0 new comments

• [Question]: Get real images from pdf

  #8085 commented on Jun 6, 2025 • 0 new comments

• [Question]: When I select an img2txt model for PDF document parsing, what task should I choose when deploying this model?

  #8079 commented on Jun 6, 2025 • 0 new comments

• [Bug]: graphrag task doesn't create

  #8065 commented on Jun 6, 2025 • 0 new comments

• [Bug]: 404 Not Found: The requested URL was not found on the server. If you entered the URL manually please check your spelling and try again.

  #5250 commented on Jun 6, 2025 • 0 new comments

• [Feature Request]: Begin component takes a variable so I cannot embed it into a webpage, but translation agent needs to get user's input

  #7322 commented on Jun 6, 2025 • 0 new comments

• [Bug]: Queuing task to parse documents when other already parsing Kbs are deleted

  #5355 commented on Jun 6, 2025 • 0 new comments

• [Question]: The VRAM usage when running the model with ragflow is much higher than when running it with ollama run qwen3:14b.

  #7859 commented on Jun 7, 2025 • 0 new comments

• Feat: Support production deployment mode by using gunicorn.

  #7845 commented on Jun 6, 2025 • 0 new comments