langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 03:55:25 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

Is there any integration case for dify to connect to the locally deployed jina-embeddings-v3 model? #7466

New Issue
Closed
opened 2026-02-21 18:20:44 -05:00 by yindo · 4 comments
yindo commented 2026-02-21 18:20:44 -05:00
Owner
Copy Link
Copy Source

Originally created by @lanqy123 on GitHub (Dec 30, 2024).

Self Checks

  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit 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.

Provide a description of requested docs changes

Is there any integration case for dify to connect to the locally deployed jina-embeddings-v3 model?

Originally created by @lanqy123 on GitHub (Dec 30, 2024). ### Self Checks - [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 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. ### Provide a description of requested docs changes Is there any integration case for dify to connect to the locally deployed jina-embeddings-v3 model?
yindo added the 👻 feat:rag label 2026-02-21 18:20:44 -05:00
yindo closed this issue 2026-02-21 18:20:44 -05:00
yindo commented 2026-02-21 18:20:44 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Dec 30, 2024):

Yes, there is an integration case for Dify to connect to a locally deployed jina-embeddings-v3 model using Xinference. You can configure this by setting up the model in Dify under Settings > Model Provider > Xinference and selecting the Embeddings type in the configuration box. To deploy Xinference locally, install it via PyPI and start it using the xinference-local command. After deploying the model, connect it in Dify by entering the model name, server URL, and model UID in the settings [1][2][3].

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 (Dec 30, 2024): <!-- Answer --> Yes, there is an integration case for Dify to connect to a locally deployed `jina-embeddings-v3` model using Xinference. You can configure this by setting up the model in Dify under `Settings > Model Provider > Xinference` and selecting the `Embeddings` type in the configuration box. To deploy Xinference locally, install it via PyPI and start it using the `xinference-local` command. After deploying the model, connect it in Dify by entering the model name, server URL, and model UID in the settings <sup>[[1]](https://github.com/langgenius/dify-docs/blob/main/jp/development/models-integration/xinference.md)</sup><sup>[[2]](https://github.com/langgenius/dify-docs/blob/main/zh_CN/development/models-integration/localai.md)</sup><sup>[[3]](https://github.com/langgenius/dify-docs/blob/main/en/development/models-integration/xinference.md)</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/36c081b6-2591-4ce0-8f9e-f3adaedd1321?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/36c081b6-2591-4ce0-8f9e-f3adaedd1321?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/36c081b6-2591-4ce0-8f9e-f3adaedd1321?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/36c081b6-2591-4ce0-8f9e-f3adaedd1321?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/36c081b6-2591-4ce0-8f9e-f3adaedd1321?feedback_type=hallucination) | [Other](https://app.dosu.dev/response-feedback/36c081b6-2591-4ce0-8f9e-f3adaedd1321?feedback_type=other)</sup>
yindo commented 2026-02-21 18:20:44 -05:00
Author
Owner
Copy Link
Copy Source

@leslie2046 commented on GitHub (Dec 30, 2024):

图片
How about have a try in xinference?

@leslie2046 commented on GitHub (Dec 30, 2024): ![图片](https://github.com/user-attachments/assets/a464b538-7266-4197-841c-83098a04d301) How about have a try in xinference?
yindo commented 2026-02-21 18:20:44 -05:00
Author
Owner
Copy Link
Copy Source

@lanqy123 commented on GitHub (Dec 30, 2024):

image
When I tried to install "xinference[all]" on my GPU using pip, I encountered an error as shown in the image: "Failed to build llama-cpp-python. ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (llama-cpp-python)."

@lanqy123 commented on GitHub (Dec 30, 2024): ![image](https://github.com/user-attachments/assets/8d282d4d-7e16-4f6b-8e49-7cdadcf6db19) When I tried to install "xinference[all]" on my GPU using pip, I encountered an error as shown in the image: "Failed to build llama-cpp-python. ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (llama-cpp-python)."
yindo commented 2026-02-21 18:20:45 -05:00
Author
Owner
Copy Link
Copy Source

@leslie2046 commented on GitHub (Dec 30, 2024):

I have also encountered this problem before,you can take a look at this:
https://github.com/xorbitsai/inference/issues/1050

@leslie2046 commented on GitHub (Dec 30, 2024): I have also encountered this problem before,you can take a look at this: https://github.com/xorbitsai/inference/issues/1050
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 👻 feat:rag
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#7466
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?