langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 20:15:31 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

stuck at Queuing status when upload document always #8160

New Issue
Closed
opened 2026-02-21 18:24:15 -05:00 by yindo · 3 comments
yindo commented 2026-02-21 18:24:15 -05:00
Owner
Copy Link
Copy Source

Originally created by @gengshenghong on GitHub (Feb 11, 2025).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
  • Please do not modify this template :) and fill in all the required fields.

Dify version

0.10.2

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

I self-host dify in k8s (with postgreSQL, redis,mivlus), everything works for some days. But it stuck at queue when upload document suddenly with any document (even the same document worked previous).

What I have tried:
I do not see errors in the logs.
I even tried to clean all the redis (including celery redis) data, and restart all dify components, it just never come back to work.
I can confirm the embedding model is working (1. it works previously 2. the embeeding model is deployed with ollama, without key or rate limit configured 3. I use curl in dify-worker container to test the embeeding model endpoint and it works)

Is there any way to debug furture?

Below is the dify worker container logs for reference:
[2025-02-11 03:32:16,595: DEBUG/MainProcess] basic.qos: prefetch_count->4 [2025-02-11 03:32:16,606: INFO/MainProcess] Task tasks.clean_dataset_task.clean_dataset_task[b433fce1-488d-4f5e-9d15-f0636eb85e80] received [2025-02-11 03:32:16,606: DEBUG/MainProcess] TaskPool: Apply <function fast_trace_task at 0x7f4f32fe5120> (args:('tasks.clean_dataset_task.clean_dataset_task', 'b433fce1-488d-4f5e-9d15-f0636eb85e80', {'lang': 'py', 'task': 'tasks.clean_dataset_task.clean_dataset_task', 'id': 'b433fce1-488d-4f5e-9d15-f0636eb85e80', 'shadow': None, 'eta': None, 'expires': None, 'group': None, 'group_index': None, 'retries': 0, 'timelimit': [None, None], 'root_id': 'b433fce1-488d-4f5e-9d15-f0636eb85e80', 'parent_id': None, 'argsrepr': "('1970836c-13ab-489c-a83b-082dd0de029b', 'ae14b912-7426-488f-aa7f-891b1f02f31d', 'high_quality', None, 'af926f1e-201e-4e1b-ae03-890562c5e5f4', 'text_model')", 'kwargsrepr': '{}', 'origin': 'gen23@dify-api-76f66558f4-mxg9k', 'ignore_result': True, 'replaced_task_nesting': 0, 'stamped_headers': None, 'stamps': {}, 'redelivered': True, 'properties': {'correlation_id': 'b433fce1-488d-4f5e-9d15-f0636eb85e80', 'reply_to': '21f711d8-f46e-3f83-9011-222fb56844b7', 'delivery_mode': 2, 'delivery_info': {'exchange': '', 'routing_key': 'dataset', 'redelivered': True}, 'priority': 0, 'body_encoding': 'base64',... kwargs:{}) [2025-02-11 03:32:16,607: INFO/MainProcess] Start clean dataset when dataset deleted: 1970836c-13ab-489c-a83b-082dd0de029b [2025-02-11 03:32:16,745: INFO/MainProcess] Cleaning documents for dataset: 1970836c-13ab-489c-a83b-082dd0de029b [2025-02-11 03:32:16,790: INFO/MainProcess] Task tasks.document_indexing_task.document_indexing_task[4f1f0c28-187c-43a8-b81d-1f417df052a6] received [2025-02-11 03:32:16,791: DEBUG/MainProcess] TaskPool: Apply <function fast_trace_task at 0x7f4f32fe5120> (args:('tasks.document_indexing_task.document_indexing_task', '4f1f0c28-187c-43a8-b81d-1f417df052a6', {'lang': 'py', 'task': 'tasks.document_indexing_task.document_indexing_task', 'id': '4f1f0c28-187c-43a8-b81d-1f417df052a6', 'shadow': None, 'eta': None, 'expires': None, 'group': None, 'group_index': None, 'retries': 0, 'timelimit': [None, None], 'root_id': '4f1f0c28-187c-43a8-b81d-1f417df052a6', 'parent_id': None, 'argsrepr': "('29aad936-b1d1-42a7-b288-96edd6ad5619', ['adb7eb08-01bf-4903-a835-d7c5a38ee5f5'])", 'kwargsrepr': '{}', 'origin': 'gen23@dify-api-76f66558f4-mxg9k', 'ignore_result': True, 'replaced_task_nesting': 0, 'stamped_headers': None, 'stamps': {}, 'properties': {'correlation_id': '4f1f0c28-187c-43a8-b81d-1f417df052a6', 'reply_to': '60338d9d-598a-3cdb-8078-347bad1d8640', 'delivery_mode': 2, 'delivery_info': {'exchange': '', 'routing_key': 'dataset'}, 'priority': 0, 'body_encoding': 'base64', 'delivery_tag': '03b9bda7-a875-4b43-87e4-59eba096b876'}, 'reply_to': '60338d9d-598a-3cdb-8078-347bad1d8640',... kwargs:{})

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

Originally created by @gengshenghong on GitHub (Feb 11, 2025). ### Self Checks - [x] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [x] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [x] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [x] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:） - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version 0.10.2 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce I self-host dify in k8s (with postgreSQL, redis,mivlus), everything works for some days. But it stuck at queue when upload document suddenly with any document (even the same document worked previous). What I have tried: I do not see errors in the logs. I even tried to clean all the redis (including celery redis) data, and restart all dify components, it just never come back to work. I can confirm the embedding model is working (1. it works previously 2. the embeeding model is deployed with ollama, without key or rate limit configured 3. I use curl in dify-worker container to test the embeeding model endpoint and it works) Is there any way to debug furture? Below is the dify worker container logs for reference: `[2025-02-11 03:32:16,595: DEBUG/MainProcess] basic.qos: prefetch_count->4 [2025-02-11 03:32:16,606: INFO/MainProcess] Task tasks.clean_dataset_task.clean_dataset_task[b433fce1-488d-4f5e-9d15-f0636eb85e80] received [2025-02-11 03:32:16,606: DEBUG/MainProcess] TaskPool: Apply <function fast_trace_task at 0x7f4f32fe5120> (args:('tasks.clean_dataset_task.clean_dataset_task', 'b433fce1-488d-4f5e-9d15-f0636eb85e80', {'lang': 'py', 'task': 'tasks.clean_dataset_task.clean_dataset_task', 'id': 'b433fce1-488d-4f5e-9d15-f0636eb85e80', 'shadow': None, 'eta': None, 'expires': None, 'group': None, 'group_index': None, 'retries': 0, 'timelimit': [None, None], 'root_id': 'b433fce1-488d-4f5e-9d15-f0636eb85e80', 'parent_id': None, 'argsrepr': "('1970836c-13ab-489c-a83b-082dd0de029b', 'ae14b912-7426-488f-aa7f-891b1f02f31d', 'high_quality', None, 'af926f1e-201e-4e1b-ae03-890562c5e5f4', 'text_model')", 'kwargsrepr': '{}', 'origin': 'gen23@dify-api-76f66558f4-mxg9k', 'ignore_result': True, 'replaced_task_nesting': 0, 'stamped_headers': None, 'stamps': {}, 'redelivered': True, 'properties': {'correlation_id': 'b433fce1-488d-4f5e-9d15-f0636eb85e80', 'reply_to': '21f711d8-f46e-3f83-9011-222fb56844b7', 'delivery_mode': 2, 'delivery_info': {'exchange': '', 'routing_key': 'dataset', 'redelivered': True}, 'priority': 0, 'body_encoding': 'base64',... kwargs:{}) [2025-02-11 03:32:16,607: INFO/MainProcess] Start clean dataset when dataset deleted: 1970836c-13ab-489c-a83b-082dd0de029b [2025-02-11 03:32:16,745: INFO/MainProcess] Cleaning documents for dataset: 1970836c-13ab-489c-a83b-082dd0de029b [2025-02-11 03:32:16,790: INFO/MainProcess] Task tasks.document_indexing_task.document_indexing_task[4f1f0c28-187c-43a8-b81d-1f417df052a6] received [2025-02-11 03:32:16,791: DEBUG/MainProcess] TaskPool: Apply <function fast_trace_task at 0x7f4f32fe5120> (args:('tasks.document_indexing_task.document_indexing_task', '4f1f0c28-187c-43a8-b81d-1f417df052a6', {'lang': 'py', 'task': 'tasks.document_indexing_task.document_indexing_task', 'id': '4f1f0c28-187c-43a8-b81d-1f417df052a6', 'shadow': None, 'eta': None, 'expires': None, 'group': None, 'group_index': None, 'retries': 0, 'timelimit': [None, None], 'root_id': '4f1f0c28-187c-43a8-b81d-1f417df052a6', 'parent_id': None, 'argsrepr': "('29aad936-b1d1-42a7-b288-96edd6ad5619', ['adb7eb08-01bf-4903-a835-d7c5a38ee5f5'])", 'kwargsrepr': '{}', 'origin': 'gen23@dify-api-76f66558f4-mxg9k', 'ignore_result': True, 'replaced_task_nesting': 0, 'stamped_headers': None, 'stamps': {}, 'properties': {'correlation_id': '4f1f0c28-187c-43a8-b81d-1f417df052a6', 'reply_to': '60338d9d-598a-3cdb-8078-347bad1d8640', 'delivery_mode': 2, 'delivery_info': {'exchange': '', 'routing_key': 'dataset'}, 'priority': 0, 'body_encoding': 'base64', 'delivery_tag': '03b9bda7-a875-4b43-87e4-59eba096b876'}, 'reply_to': '60338d9d-598a-3cdb-8078-347bad1d8640',... kwargs:{}) ` ### ✔️ Expected Behavior _No response_ ### ❌ Actual Behavior _No response_
yindo added the 🐞 bug label 2026-02-21 18:24:15 -05:00
yindo closed this issue 2026-02-21 18:24:15 -05:00
yindo commented 2026-02-21 18:24:16 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Feb 11, 2025):

Hey @gengshenghong! I'm here to help you out with any bugs, questions, or contributions you have for the project. Let's work together to solve the issue you're facing.

I found some similar threads that might help you debug the issue of documents getting stuck at the "Queuing" status:

  1. Open Issue: Knowledgebase upload file stay in Queue suggests checking if the Celery worker has been started, as it is necessary for processing tasks such as segmentation and indexing in the knowledge base.

  2. Closed Issues:

    • One solution involves checking if the rate limit for the Embedding model API key has been reached, ensuring the Celery worker service is running correctly, and verifying that all necessary services are up using docker compose ps [1].
    • Another solution recommends upgrading to the latest version of Dify, as the issue with files staying in the Queuing status has been fixed in newer versions [2].

For your specific setup using Kubernetes, PostgreSQL, Redis, and Milvus, consider the following steps:

  • Verify Rate Limits: Ensure that you have not reached the rate limit for your Embedding model API key.
  • Check Celery Worker: Make sure the Celery worker service is running properly. Check the logs of the worker pods for any issues.
  • Service Status: Confirm that all necessary services are running and that all relevant pods are in a healthy state.
  • Pending Processes: Look for any pending segmentation or embedding processes and ensure all dependencies are functioning correctly.
  • Upgrade Dify: Consider upgrading to the latest version of Dify, as this may resolve the issue [2].

These steps should help you identify and resolve the issue with documents getting stuck in the queue.

To continue talking to Dosu, mention @dosu.

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other

@dosubot[bot] commented on GitHub (Feb 11, 2025): <!-- Greeting --> Hey @gengshenghong! I'm here to help you out with any bugs, questions, or contributions you have for the project. Let's work together to solve the issue you're facing. <!-- Answer --> I found some similar threads that might help you debug the issue of documents getting stuck at the "Queuing" status: 1. **Open Issue**: [Knowledgebase upload file stay in Queue](https://github.com/langgenius/dify/issues/9043) suggests checking if the Celery worker has been started, as it is necessary for processing tasks such as segmentation and indexing in the knowledge base. 2. **Closed Issues**: - One solution involves checking if the rate limit for the Embedding model API key has been reached, ensuring the Celery worker service is running correctly, and verifying that all necessary services are up using `docker compose ps` <sup>[[1]](https://github.com/langgenius/dify/issues/9043)</sup>. - Another solution recommends upgrading to the latest version of Dify, as the issue with files staying in the Queuing status has been fixed in newer versions <sup>[[2]](https://github.com/langgenius/dify/issues/11657)</sup>. For your specific setup using Kubernetes, PostgreSQL, Redis, and Milvus, consider the following steps: - **Verify Rate Limits**: Ensure that you have not reached the rate limit for your Embedding model API key. - **Check Celery Worker**: Make sure the Celery worker service is running properly. Check the logs of the worker pods for any issues. - **Service Status**: Confirm that all necessary services are running and that all relevant pods are in a healthy state. - **Pending Processes**: Look for any pending segmentation or embedding processes and ensure all dependencies are functioning correctly. - **Upgrade Dify**: Consider upgrading to the latest version of Dify, as this may resolve the issue <sup>[[2]](https://github.com/langgenius/dify/issues/11657)</sup>. These steps should help you identify and resolve the issue with documents getting stuck in the queue. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.* --- <sup>Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/955fc95a-aaeb-4a20-b4f7-82fd3ad4a880?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/955fc95a-aaeb-4a20-b4f7-82fd3ad4a880?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/955fc95a-aaeb-4a20-b4f7-82fd3ad4a880?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/955fc95a-aaeb-4a20-b4f7-82fd3ad4a880?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/955fc95a-aaeb-4a20-b4f7-82fd3ad4a880?feedback_type=hallucination) | [Other](https://app.dosu.dev/response-feedback/955fc95a-aaeb-4a20-b4f7-82fd3ad4a880?feedback_type=other)</sup>
yindo commented 2026-02-21 18:24:16 -05:00
Author
Owner
Copy Link
Copy Source

@gengshenghong commented on GitHub (Feb 11, 2025):

I also configured below to enable all debug and log file:

# // debug log
  - name: LOG_LEVEL
    value: "DEBUG"
  # Log file path
  - name: LOG_FILE
    value: "/app/logs/server.log"
  - name: DEBUG
    value: "true"

the worker log file also does not show any error.

@gengshenghong commented on GitHub (Feb 11, 2025): I also configured below to enable all debug and log file: ``` # // debug log - name: LOG_LEVEL value: "DEBUG" # Log file path - name: LOG_FILE value: "/app/logs/server.log" - name: DEBUG value: "true" ``` the worker log file also does not show any error.
yindo commented 2026-02-21 18:24:16 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Feb 11, 2025):

Sorry we do not provide support for k8s deployment. :) Please reach out to business@dify.ai

@crazywoola commented on GitHub (Feb 11, 2025): Sorry we do not provide support for k8s deployment. :) Please reach out to business@dify.ai
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label 🐞 bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#8160
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?