langgenius/dify-official-plugins
1
0
Fork 0
mirror of https://github.com/langgenius/dify-official-plugins.git synced 2026-07-22 01:55:27 -04:00
Code Issues 54 Packages Projects Releases Wiki Activity

Using OpenAI-API-compatible to connect to the privately deployed full-version DeepSeek model, saving failed with an error.” #573

New Issue
Closed
opened 2026-02-16 10:19:47 -05:00 by yindo · 8 comments
yindo commented 2026-02-16 10:19:47 -05:00
Owner
Copy Link
Copy Source

Originally created by @JiesenSun on GitHub (Aug 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 Dify issues & Dify Official Plugins, 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

1.7.1

Plugin version

0.2.0-local

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

When using OpenAI-API-compatible to connect to the privately deployed full-version DeepSeek model, saving results in an error as shown in the screenshot: [ERROR] PluginDaemonInternalServerError: killed by timeout. However, when using the following curl request, the model works normally.

curl https://32.12.192.220:3001/v1/chat/completions \
  -H "Authorization: Bearer sk-352c453ac9a041a3a07e60c93e54" \
  -H "Content-Type: application/json" \
  -d '{
        "model": "deepseek-r1-0528-local",
        "messages": [
          {"role": "system", "content": "你是一个有用的助手。"},
          {"role": "user", "content": "给我写一首七言律诗，主题是秋天。"}
        ],
        "temperature": 0.7
      }'
Image Image Image

✔️ Error log

No response

Originally created by @JiesenSun on GitHub (Aug 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 [Dify issues](https://github.com/langgenius/dify/issues) & [Dify Official Plugins](https://github.com/langgenius/dify-official-plugins/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 1.7.1 ### Plugin version 0.2.0-local ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce **When using OpenAI-API-compatible to connect to the privately deployed full-version DeepSeek model, saving results in an error as shown in the screenshot: [ERROR] PluginDaemonInternalServerError: killed by timeout. However, when using the following curl request, the model works normally.** ``` curl https://32.12.192.220:3001/v1/chat/completions \ -H "Authorization: Bearer sk-352c453ac9a041a3a07e60c93e54" \ -H "Content-Type: application/json" \ -d '{ "model": "deepseek-r1-0528-local", "messages": [ {"role": "system", "content": "你是一个有用的助手。"}, {"role": "user", "content": "给我写一首七言律诗，主题是秋天。"} ], "temperature": 0.7 }' ``` <img width="2262" height="1252" alt="Image" src="https://github.com/user-attachments/assets/7d221e4e-f5f8-45fa-8d8d-d2f2fdbca4d5" /> <img width="2318" height="1240" alt="Image" src="https://github.com/user-attachments/assets/12ca74d4-47f9-4355-8c7e-c418ae8a18f0" /> <img width="2328" height="1520" alt="Image" src="https://github.com/user-attachments/assets/65935776-0567-46eb-96bf-aa8fcea00daf" /> ### ✔️ Error log _No response_
yindo closed this issue 2026-02-16 10:19:47 -05:00
yindo commented 2026-02-16 10:19:47 -05:00
Author
Owner
Copy Link
Copy Source

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

This timeout error is a common issue when connecting Dify (self-hosted Docker) to OpenAI-API-compatible models like DeepSeek. Even if curl works, the plugin may hit a timeout due to differences in how requests are handled and how timeouts are enforced in the plugin daemon.

Key things to check and try:

  • Docker network config: Make sure your plugin daemon and Dify containers can reach the DeepSeek endpoint. If you use localhost or 127.0.0.1 in your endpoint, switch to host.docker.internal or your host's LAN IP. Set SANDBOX_ENABLE_NETWORK=true and ensure PLUGIN_DAEMON_URL is correct in your environment variables. This is a frequent cause of plugin timeouts in Docker setups [ref].

  • Timeout settings: In Dify v1.7.1, plugin timeout is not user-configurable. If your DeepSeek model is slow to respond, the plugin may be killed by the default timeout. Newer Dify versions (after 1.7.1) add timeout controls for MCP tools, but these are not available in your version [ref].

  • Plugin/SDK bugs: Some plugin errors are caused by code issues (like passing multiple values for completion_params), or by the plugin expecting a specific response format (e.g., a space after data: in streaming responses). If your DeepSeek API returns a slightly different format, you may need to patch the plugin code (see this workaround).

  • Credential validation: Double-check your model name, endpoint, and API key. Even small mismatches can cause validation to fail or time out [ref].

  • Logs: Check both Docker and plugin daemon logs for more details on the timeout or connection error.

Workarounds:

  • If possible, upgrade to a newer Dify version that allows you to set a higher timeout for MCP tools.
  • If you need an immediate workaround, you may need to patch the plugin's HTTP client timeout in the code, or try running Dify outside Docker to rule out network issues.
  • Some users have resolved similar issues by downgrading to Dify 0.15.3, but this is not ideal for most setups [ref].

If you need more specific help, share your plugin config (endpoint, model name, etc.) and any relevant logs from the plugin daemon.

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Join Discord Share on X

@dosubot[bot] commented on GitHub (Aug 21, 2025): <!-- Answer --> This timeout error is a common issue when connecting Dify (self-hosted Docker) to OpenAI-API-compatible models like DeepSeek. Even if curl works, the plugin may hit a timeout due to differences in how requests are handled and how timeouts are enforced in the plugin daemon. Key things to check and try: - **Docker network config**: Make sure your plugin daemon and Dify containers can reach the DeepSeek endpoint. If you use `localhost` or `127.0.0.1` in your endpoint, switch to `host.docker.internal` or your host's LAN IP. Set `SANDBOX_ENABLE_NETWORK=true` and ensure `PLUGIN_DAEMON_URL` is correct in your environment variables. This is a frequent cause of plugin timeouts in Docker setups [[ref]](https://github.com/langgenius/dify-official-plugins/issues/1243). - **Timeout settings**: In Dify v1.7.1, plugin timeout is not user-configurable. If your DeepSeek model is slow to respond, the plugin may be killed by the default timeout. Newer Dify versions (after 1.7.1) add timeout controls for MCP tools, but these are not available in your version [[ref]](https://github.com/langgenius/dify/pull/23605). - **Plugin/SDK bugs**: Some plugin errors are caused by code issues (like passing multiple values for `completion_params`), or by the plugin expecting a specific response format (e.g., a space after `data:` in streaming responses). If your DeepSeek API returns a slightly different format, you may need to patch the plugin code (see [this workaround](https://github.com/langgenius/dify-official-plugins/issues/392)). - **Credential validation**: Double-check your model name, endpoint, and API key. Even small mismatches can cause validation to fail or time out [[ref]](https://github.com/langgenius/dify-official-plugins/issues/498). - **Logs**: Check both Docker and plugin daemon logs for more details on the timeout or connection error. **Workarounds:** - If possible, upgrade to a newer Dify version that allows you to set a higher timeout for MCP tools. - If you need an immediate workaround, you may need to patch the plugin's HTTP client timeout in the code, or try running Dify outside Docker to rule out network issues. - Some users have resolved similar issues by downgrading to Dify 0.15.3, but this is not ideal for most setups [[ref]](https://github.com/langgenius/dify-official-plugins/issues/392). If you need more specific help, share your plugin config (endpoint, model name, etc.) and any relevant logs from the plugin daemon. <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- <sup>How did I do? [Good](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=other)</sup>&nbsp;&nbsp;[![Join Discord](https://img.shields.io/badge/join-5865F2?logo=discord&logoColor=white&label=)](https://go.dosu.dev/discord-bot)&nbsp;[![Share on X](https://img.shields.io/badge/X-share-black)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/1542)
yindo commented 2026-02-16 10:19:47 -05:00
Author
Owner
Copy Link
Copy Source

@JiesenSun commented on GitHub (Aug 21, 2025):

This timeout error is a common issue when connecting Dify (self-hosted Docker) to OpenAI-API-compatible models like DeepSeek. Even if curl works, the plugin may hit a timeout due to differences in how requests are handled and how timeouts are enforced in the plugin daemon.

Key things to check and try:

  • Docker network config: Make sure your plugin daemon and Dify containers can reach the DeepSeek endpoint. If you use localhost or 127.0.0.1 in your endpoint, switch to host.docker.internal or your host's LAN IP. Set SANDBOX_ENABLE_NETWORK=true and ensure PLUGIN_DAEMON_URL is correct in your environment variables. This is a frequent cause of plugin timeouts in Docker setups [ref].
  • Timeout settings: In Dify v1.7.1, plugin timeout is not user-configurable. If your DeepSeek model is slow to respond, the plugin may be killed by the default timeout. Newer Dify versions (after 1.7.1) add timeout controls for MCP tools, but these are not available in your version [ref].
  • Plugin/SDK bugs: Some plugin errors are caused by code issues (like passing multiple values for completion_params), or by the plugin expecting a specific response format (e.g., a space after data: in streaming responses). If your DeepSeek API returns a slightly different format, you may need to patch the plugin code (see this workaround).
  • Credential validation: Double-check your model name, endpoint, and API key. Even small mismatches can cause validation to fail or time out [ref].
  • Logs: Check both Docker and plugin daemon logs for more details on the timeout or connection error.

Workarounds:

  • If possible, upgrade to a newer Dify version that allows you to set a higher timeout for MCP tools.
  • If you need an immediate workaround, you may need to patch the plugin's HTTP client timeout in the code, or try running Dify outside Docker to rule out network issues.
  • Some users have resolved similar issues by downgrading to Dify 0.15.3, but this is not ideal for most setups [ref].

If you need more specific help, share your plugin config (endpoint, model name, etc.) and any relevant logs from the plugin daemon.

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Join Discord Share on X

Confirmed that accessing via curl inside the container works fine, and the model’s streaming output is very fast.

@JiesenSun commented on GitHub (Aug 21, 2025): > This timeout error is a common issue when connecting Dify (self-hosted Docker) to OpenAI-API-compatible models like DeepSeek. Even if curl works, the plugin may hit a timeout due to differences in how requests are handled and how timeouts are enforced in the plugin daemon. > > Key things to check and try: > > * **Docker network config**: Make sure your plugin daemon and Dify containers can reach the DeepSeek endpoint. If you use `localhost` or `127.0.0.1` in your endpoint, switch to `host.docker.internal` or your host's LAN IP. Set `SANDBOX_ENABLE_NETWORK=true` and ensure `PLUGIN_DAEMON_URL` is correct in your environment variables. This is a frequent cause of plugin timeouts in Docker setups [[ref]](https://github.com/langgenius/dify-official-plugins/issues/1243). > * **Timeout settings**: In Dify v1.7.1, plugin timeout is not user-configurable. If your DeepSeek model is slow to respond, the plugin may be killed by the default timeout. Newer Dify versions (after 1.7.1) add timeout controls for MCP tools, but these are not available in your version [[ref]](https://github.com/langgenius/dify/pull/23605). > * **Plugin/SDK bugs**: Some plugin errors are caused by code issues (like passing multiple values for `completion_params`), or by the plugin expecting a specific response format (e.g., a space after `data:` in streaming responses). If your DeepSeek API returns a slightly different format, you may need to patch the plugin code (see [this workaround](https://github.com/langgenius/dify-official-plugins/issues/392)). > * **Credential validation**: Double-check your model name, endpoint, and API key. Even small mismatches can cause validation to fail or time out [[ref]](https://github.com/langgenius/dify-official-plugins/issues/498). > * **Logs**: Check both Docker and plugin daemon logs for more details on the timeout or connection error. > > **Workarounds:** > > * If possible, upgrade to a newer Dify version that allows you to set a higher timeout for MCP tools. > * If you need an immediate workaround, you may need to patch the plugin's HTTP client timeout in the code, or try running Dify outside Docker to rule out network issues. > * Some users have resolved similar issues by downgrading to Dify 0.15.3, but this is not ideal for most setups [[ref]](https://github.com/langgenius/dify-official-plugins/issues/392). > > If you need more specific help, share your plugin config (endpoint, model name, etc.) and any relevant logs from the plugin daemon. > > _To reply, just mention [@dosu](https://go.dosu.dev/dosubot)._ > > How did I do? [Good](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/f15e2f3c-503f-4886-9da0-f47507c3ea40?feedback_type=other)  [![Join Discord](https://camo.githubusercontent.com/d562c2df5e4567ea41d37f1d91a4da0839d8341037045b103b2da268998de17f/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f6a6f696e2d3538363546323f6c6f676f3d646973636f7264266c6f676f436f6c6f723d7768697465266c6162656c3d)](https://go.dosu.dev/discord-bot) [![Share on X](https://camo.githubusercontent.com/4649f705e2396d6f328dbc8e800a0509c9c17b3b20253b36706c393df124b93d/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f582d73686172652d626c61636b)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/1542) Confirmed that accessing via curl inside the container works fine, and the model’s streaming output is very fast.
yindo commented 2026-02-16 10:19:47 -05:00
Author
Owner
Copy Link
Copy Source

@JiesenSun commented on GitHub (Aug 21, 2025):

After verification, downgrading to 0.15.3 allows saving successfully. But Why？🤔

@JiesenSun commented on GitHub (Aug 21, 2025): After verification, downgrading to 0.15.3 allows saving successfully. But Why？🤔
yindo commented 2026-02-16 10:19:47 -05:00
Author
Owner
Copy Link
Copy Source

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

This happens because Dify versions after 0.15.3 introduced stricter timeout handling, more rigorous credential validation, and new parameters (like the model name in the API endpoint) for OpenAI-compatible models. These changes can cause timeouts or validation failures with some endpoints that worked fine in 0.15.3, which had simpler and more permissive logic. In particular, the newer versions enforce fixed timeouts and may attempt extra credential checks or refreshes, leading to PluginDaemonInternalServerError: timeout—even if curl works and the model responds quickly. Many users have found that downgrading to 0.15.3 resolves these issues because it does not enforce the same strict checks or timeouts during model saving and validation [source 1] [source 2].

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Join Discord Share on X

@dosubot[bot] commented on GitHub (Aug 21, 2025): <!-- Answer --> This happens because Dify versions after 0.15.3 introduced stricter timeout handling, more rigorous credential validation, and new parameters (like the model name in the API endpoint) for OpenAI-compatible models. These changes can cause timeouts or validation failures with some endpoints that worked fine in 0.15.3, which had simpler and more permissive logic. In particular, the newer versions enforce fixed timeouts and may attempt extra credential checks or refreshes, leading to PluginDaemonInternalServerError: timeout—even if curl works and the model responds quickly. Many users have found that downgrading to 0.15.3 resolves these issues because it does not enforce the same strict checks or timeouts during model saving and validation [[source 1]](https://github.com/langgenius/dify-official-plugins/issues/392#issuecomment-2703580245) [[source 2]](https://github.com/langgenius/dify/issues/14918). <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- <sup>How did I do? [Good](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=other)</sup>&nbsp;&nbsp;[![Join Discord](https://img.shields.io/badge/join-5865F2?logo=discord&logoColor=white&label=)](https://go.dosu.dev/discord-bot)&nbsp;[![Share on X](https://img.shields.io/badge/X-share-black)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/1542)
yindo commented 2026-02-16 10:19:47 -05:00
Author
Owner
Copy Link
Copy Source

@JiesenSun commented on GitHub (Aug 22, 2025):

This happens because Dify versions after 0.15.3 introduced stricter timeout handling, more rigorous credential validation, and new parameters (like the model name in the API endpoint) for OpenAI-compatible models. These changes can cause timeouts or validation failures with some endpoints that worked fine in 0.15.3, which had simpler and more permissive logic. In particular, the newer versions enforce fixed timeouts and may attempt extra credential checks or refreshes, leading to PluginDaemonInternalServerError: timeout—even if curl works and the model responds quickly. Many users have found that downgrading to 0.15.3 resolves these issues because it does not enforce the same strict checks or timeouts during model saving and validation [source 1] [source 2].

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other  Join Discord Share on X

Will there be any improvements or optimizations in the future? Because of this issue, it is impossible to connect to the privately deployed large model and therefore unable to use Dify.

@JiesenSun commented on GitHub (Aug 22, 2025): > This happens because Dify versions after 0.15.3 introduced stricter timeout handling, more rigorous credential validation, and new parameters (like the model name in the API endpoint) for OpenAI-compatible models. These changes can cause timeouts or validation failures with some endpoints that worked fine in 0.15.3, which had simpler and more permissive logic. In particular, the newer versions enforce fixed timeouts and may attempt extra credential checks or refreshes, leading to PluginDaemonInternalServerError: timeout—even if curl works and the model responds quickly. Many users have found that downgrading to 0.15.3 resolves these issues because it does not enforce the same strict checks or timeouts during model saving and validation [[source 1]](https://github.com/langgenius/dify-official-plugins/issues/392#issuecomment-2703580245) [[source 2]](https://github.com/langgenius/dify/issues/14918). > > _To reply, just mention [@dosu](https://go.dosu.dev/dosubot)._ > > How did I do? [Good](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/588b37dc-b08b-452f-a413-0ed6f2f86a81?feedback_type=other)  [![Join Discord](https://camo.githubusercontent.com/d562c2df5e4567ea41d37f1d91a4da0839d8341037045b103b2da268998de17f/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f6a6f696e2d3538363546323f6c6f676f3d646973636f7264266c6f676f436f6c6f723d7768697465266c6162656c3d)](https://go.dosu.dev/discord-bot) [![Share on X](https://camo.githubusercontent.com/4649f705e2396d6f328dbc8e800a0509c9c17b3b20253b36706c393df124b93d/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f582d73686172652d626c61636b)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/1542) Will there be any improvements or optimizations in the future? Because of this issue, it is impossible to connect to the privately deployed large model and therefore unable to use Dify.
yindo commented 2026-02-16 10:19:47 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Aug 24, 2025):

https://github.com/langgenius/dify/blob/75199442c16fb2ad1758d1f813b0c9249fc150e9/docker/docker-compose.yaml#L521
https://github.com/langgenius/dify/blob/75199442c16fb2ad1758d1f813b0c9249fc150e9/docker/docker-compose.yaml#L757

@crazywoola commented on GitHub (Aug 24, 2025): https://github.com/langgenius/dify/blob/75199442c16fb2ad1758d1f813b0c9249fc150e9/docker/docker-compose.yaml#L521 https://github.com/langgenius/dify/blob/75199442c16fb2ad1758d1f813b0c9249fc150e9/docker/docker-compose.yaml#L757
yindo commented 2026-02-16 10:19:47 -05:00
Author
Owner
Copy Link
Copy Source

@JiesenSun commented on GitHub (Aug 25, 2025):

https://github.com/langgenius/dify/blob/75199442c16fb2ad1758d1f813b0c9249fc150e9/docker/docker-compose.yaml#L521 https://github.com/langgenius/dify/blob/75199442c16fb2ad1758d1f813b0c9249fc150e9/docker/docker-compose.yaml#L757

You mean that adding the following two configurations to the docker-compose.yaml file can solve this issue, right? And both of these are supported in version 1.7.X, correct?


PLUGIN_STORAGE_TYPE: ${PLUGIN_STORAGE_TYPE:-local}
PYTHON_ENV_INIT_TIMEOUT: ${PLUGIN_PYTHON_ENV_INIT_TIMEOUT:-120}
@JiesenSun commented on GitHub (Aug 25, 2025): > https://github.com/langgenius/dify/blob/75199442c16fb2ad1758d1f813b0c9249fc150e9/docker/docker-compose.yaml#L521 https://github.com/langgenius/dify/blob/75199442c16fb2ad1758d1f813b0c9249fc150e9/docker/docker-compose.yaml#L757 You mean that adding the following two configurations to the docker-compose.yaml file can solve this issue, right? And both of these are supported in version 1.7.X, correct? ``` PLUGIN_STORAGE_TYPE: ${PLUGIN_STORAGE_TYPE:-local} PYTHON_ENV_INIT_TIMEOUT: ${PLUGIN_PYTHON_ENV_INIT_TIMEOUT:-120} ```
yindo commented 2026-02-16 10:19:47 -05:00
Author
Owner
Copy Link
Copy Source

@JiesenSun commented on GitHub (Aug 25, 2025):

After checking carefully, I found that the docker-compose.yaml in the Dify 1.7.1 version of the project does include these two configurations. However, when connecting to the privately deployed DeepSeek-671B model, it still cannot be saved. What should I do?

@JiesenSun commented on GitHub (Aug 25, 2025): After checking carefully, I found that the docker-compose.yaml in the Dify 1.7.1 version of the project does include these two configurations. However, when connecting to the privately deployed DeepSeek-671B model, it still cannot be saved. What should I do?
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
bug
bug
dependencies
documentation
enhancement
good first issue
invalid
pull-request
Mirrored from GitHub Pull Request
 question
stale
No Label
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-official-plugins#573
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?