langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-25 13:36:01 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

Problems with connecting to models during offline deployment #11925

New Issue
Closed
opened 2026-02-21 19:04:47 -05:00 by yindo · 1 comment
yindo commented 2026-02-21 19:04:47 -05:00
Owner
Copy Link
Copy Source

Originally created by @volongoto on GitHub (Mar 21, 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

1.0.1

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

The environment I'm currently deploying is Dify 1.0.1 and plugin-daemon-0.0.6. Since it's an offline deployment and interfaces with an LLM, the offline environment requires pip dependencies. I need to set up an offline PyPI mirror source by myself. I'd like to ask about the relevant requirements.txt list or where I can find out which dependencies are needed. There are no log errors during the current interfacing process, but I still can't interface with the DeepSeek deployed with the offline vLLM.

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

Originally created by @volongoto on GitHub (Mar 21, 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 1.0.1 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce The environment I'm currently deploying is Dify 1.0.1 and plugin-daemon-0.0.6. Since it's an offline deployment and interfaces with an LLM, the offline environment requires pip dependencies. I need to set up an offline PyPI mirror source by myself. I'd like to ask about the relevant requirements.txt list or where I can find out which dependencies are needed. There are no log errors during the current interfacing process, but I still can't interface with the DeepSeek deployed with the offline vLLM. ### ✔️ Expected Behavior _No response_ ### ❌ Actual Behavior _No response_
yindo added the 🐞 bug label 2026-02-21 19:04:47 -05:00
yindo closed this issue 2026-02-21 19:04:47 -05:00
yindo commented 2026-02-21 19:04:47 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Mar 21, 2025):

Hey @volongoto! I'm here to help you with any bugs, questions, or contributions you have for Dify. Let's tackle this issue together!

I found a similar closed issue titled Issues with Model Marketplace API and pip mirror configuration in Self Hosted, which was resolved by adding support for the PIP_MIRROR_URL environment variable [1]. This might be relevant to your situation if you need to configure a local PyPI mirror for your offline deployment.

For setting up an offline PyPI mirror source for Dify 1.0.1, you can refer to the pyproject.toml file for the list of dependencies. The main dependencies are listed under [tool.poetry.dependencies]. Here are some of the key dependencies:

  • authlib = "1.3.1"
  • azure-identity = "1.16.1"
  • beautifulsoup4 = "4.12.2"
  • boto3 = "1.35.99"
  • flask = "~3.1.0"
  • numpy = "~1.26.4"
  • pandas = { version = "~2.2.2", extras = ["performance", "excel", "output-formatting"] }
  • redis = { version = "~5.0.3", extras = ["hiredis"] }
  • sqlalchemy = "~2.0.29"
  • transformers = "~4.35.0"

For plugin-daemon-0.0.6, specific dependency information wasn't found, so you might need to check its requirements.txt or equivalent file separately [2].

To configure Dify to use a local PyPI mirror during installation, modify the PIP_MIRROR_URL in your docker-compose.yaml file to point to your local mirror URL [3].

To continue talking to Dosu, mention @dosu.

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

@dosubot[bot] commented on GitHub (Mar 21, 2025): <!-- Greeting --> Hey @volongoto! I'm here to help you with any bugs, questions, or contributions you have for Dify. Let's tackle this issue together! <!-- Answer --> I found a similar closed issue titled [Issues with Model Marketplace API and pip mirror configuration in Self Hosted](https://github.com/langgenius/dify/issues/14579), which was resolved by adding support for the `PIP_MIRROR_URL` environment variable <sup>[[1]](https://github.com/langgenius/dify/issues/14579)</sup>. This might be relevant to your situation if you need to configure a local PyPI mirror for your offline deployment. For setting up an offline PyPI mirror source for Dify 1.0.1, you can refer to the `pyproject.toml` file for the list of dependencies. The main dependencies are listed under `[tool.poetry.dependencies]`. Here are some of the key dependencies: - `authlib = "1.3.1"` - `azure-identity = "1.16.1"` - `beautifulsoup4 = "4.12.2"` - `boto3 = "1.35.99"` - `flask = "~3.1.0"` - `numpy = "~1.26.4"` - `pandas = { version = "~2.2.2", extras = ["performance", "excel", "output-formatting"] }` - `redis = { version = "~5.0.3", extras = ["hiredis"] }` - `sqlalchemy = "~2.0.29"` - `transformers = "~4.35.0"` For `plugin-daemon-0.0.6`, specific dependency information wasn't found, so you might need to check its `requirements.txt` or equivalent file separately <sup>[[2]](https://github.com/langgenius/dify/blob/e324e59930557cd0345f795604d9c3d1feb0009e/api/pyproject.toml)</sup>. To configure Dify to use a local PyPI mirror during installation, modify the `PIP_MIRROR_URL` in your `docker-compose.yaml` file to point to your local mirror URL <sup>[[3]](https://github.com/langgenius/dify/issues/14553)</sup>. <!-- 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/8f91b78b-7bb9-40bd-8542-2f546a99508f?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/8f91b78b-7bb9-40bd-8542-2f546a99508f?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/8f91b78b-7bb9-40bd-8542-2f546a99508f?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/8f91b78b-7bb9-40bd-8542-2f546a99508f?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/8f91b78b-7bb9-40bd-8542-2f546a99508f?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/8f91b78b-7bb9-40bd-8542-2f546a99508f?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/8f91b78b-7bb9-40bd-8542-2f546a99508f?feedback_type=other)</sup>
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#11925
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?