Image Generation fails with Request Aborted error

[svfwan]

What happened?

Hi everyone,

I have set up a custom helm deployment for a PoC and I wanted to enable Image Generation via Azure OpenAI (gpt-image-1). These are steps I have followed:

1. mapped these env variables to the librechat application:

• IMAGE_GEN_OAI_BASEURL
• IMAGE_GEN_OAI_API_KEY
• IMAGE_GEN_OAI_AZURE_API_VERSION

2. mounted this volume in the deployment yaml (config, data and logs as well they are working fine):

• volumeMounts:
  - name: images
  mountPath: "/app/client/public/images"
  volumes:
  • name: images
    emptyDir:
    sizeLimit: 50Mi # for testing purposes
    In general all the other features i.e image upload, file upload and chatting works fine

3. Set fileStrategy: "local" in the librechat.yaml which is correctly loaded (but not sure if this is relevant)

When I test the deployment locally on a k3s cluster (Rancher Desktop) it works and the image is generated without any issues. In our cloud infrastructure though after deploying these changes and testing the Image Tool with an Agent I receive this error in the UI"(Result Something went wrong when trying to generate the image. The OpenAI API may be unavailable: Error Message: Request was aborted." and these are the logs of the pod:

{"level":"error","message":"[image_gen_oai] Problem generating the image: An error occurred while setting up the request: Request was aborted.","stack":"Error: Request was aborted.\n at OpenAI.makeRequest (/app/node_modules/openai/core.js:324:23)\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async tool.name (/app/api/app/clients/tools/structured/OpenAIImageTool...","timestamp":"2025-05-21T12:08:52.596Z"}
{"level":"error","message":"[api/server/controllers/agents/client.js #sendCompletion] Operation aborted Aborted","stack":"Error: Aborted\n at EventTarget.listener (/app/node_modules/@langchain/core/dist/utils/signal.cjs:20:24)\n at [nodejs.internal.kHybridDispatch] (node:internal/event_target:831:20)\n at EventTarget.dispatchEvent (node:internal/event_target:766:26)\n ...","timestamp":"2025-05-21T12:08:52.598Z"}

Also when I try to upload an image and tell the Agent to recreate it/edit it then I receive this:

{"level":"error","message":"[image_edit_oai] Problem editing the image: No response received for POST /images/edits: canceled","requestInfo":{"method":"post","url":"/images/edits"},"stack":"CanceledError: canceled\n at EventTarget.abort (/app/node_modules/axios/dist/node/axios.cjs:2769:54)\n at [nodejs.internal.kHybridDispatch] (node:internal/event_target:831:20)\n at EventTarget.dispatchEvent (node:internal/event_target:766:26)\n at...","timestamp":"2025-05-21T12:18:34.009Z"}
{"level":"error","message":"[api/server/controllers/agents/client.js #sendCompletion] Operation aborted Aborted","stack":"Error: Aborted\n at EventTarget.listener (/app/node_modules/@langchain/core/dist/utils/signal.cjs:20:24)\n at [nodejs.internal.kHybridDispatch] (node:internal/event_target:831:20)\n at EventTarget.dispatchEvent (node:internal/event_target:766:26)\n ...","timestamp":"2025-05-21T12:18:34.010Z"}

I have also tried using a debug pod from within the same application namespace and tried this command:

curl -X POST "<endpoint>/gpt-image-1/images/generations?api-version=2025-04-01-preview" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <token>" \
  -d '{
     "prompt" : "A photograph of a red fox in an autumn forest",
     "size" : "1024x1024",
     "quality" : "medium",
     "output_compression" : 100,
     "output_format" : "png",
     "n" : 1
    }'

And this seems to work fine from within the terminal

Is there anything that I am missing config wise? Or is there a known issue I might be able to refer? Appreciate all the answers and help in advance

Version Information

librechat:v0.7.8

Steps to Reproduce

1. Create custom simple helm chart of LibreChat
2. Map env variables to LibreChat Deployment
3. Set fileStrategy to local in librechat.yaml (provided to deployment via mounting of configmap)

What browsers are you seeing the problem on?

Chrome

Relevant log output

Generate Image


{"level":"error","message":"[image_gen_oai] Problem generating the image: An error occurred while setting up the request: Request was aborted.","stack":"Error: Request was aborted.\n at OpenAI.makeRequest (/app/node_modules/openai/core.js:324:23)\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async tool.name (/app/api/app/clients/tools/structured/OpenAIImageTool...","timestamp":"2025-05-21T12:08:52.596Z"}
{"level":"error","message":"[api/server/controllers/agents/client.js #sendCompletion] Operation aborted Aborted","stack":"Error: Aborted\n at EventTarget.listener (/app/node_modules/@langchain/core/dist/utils/signal.cjs:20:24)\n at [nodejs.internal.kHybridDispatch] (node:internal/event_target:831:20)\n at EventTarget.dispatchEvent (node:internal/event_target:766:26)\n ...","timestamp":"2025-05-21T12:08:52.598Z"}


Edit Image


{"level":"error","message":"[image_edit_oai] Problem editing the image: No response received for POST /images/edits: canceled","requestInfo":{"method":"post","url":"/images/edits"},"stack":"CanceledError: canceled\n at EventTarget.abort (/app/node_modules/axios/dist/node/axios.cjs:2769:54)\n at [nodejs.internal.kHybridDispatch] (node:internal/event_target:831:20)\n at EventTarget.dispatchEvent (node:internal/event_target:766:26)\n at...","timestamp":"2025-05-21T12:18:34.009Z"}
{"level":"error","message":"[api/server/controllers/agents/client.js #sendCompletion] Operation aborted Aborted","stack":"Error: Aborted\n at EventTarget.listener (/app/node_modules/@langchain/core/dist/utils/signal.cjs:20:24)\n at [nodejs.internal.kHybridDispatch] (node:internal/event_target:831:20)\n at EventTarget.dispatchEvent (node:internal/event_target:766:26)\n ...","timestamp":"2025-05-21T12:18:34.010Z"}

Screenshots

No response

Code of Conduct

• I agree to follow this project's Code of Conduct

[neymarsabin]

I am also getting similar type of issue like @svfwan said in the above issue.

LibreChat         | 2025-05-29 11:56:47 error:
LibreChat         | 2025-05-29 11:56:47 error: [AskController] Error handling request 500 The server had an error while processing your request. Sorry about that!
LibreChat         | 2025-05-29 11:56:47 error: [handleAbortError] AI response error; aborting request: 500 The server had an error while processing your request. Sorry about that!```
I used `gpt-model-1` model with organization verified for image generation. 

[svfwan]

Hi @neymarsabin,

I solved the issue by increasing the HTTP timeout configuration for the route on our cluster (OpenShift). It wasn't related to the application code or OpenAI library. If you want I can provide the specific configuration that fixed the issue for me! :)

[neymarsabin]

Please send me the configuration. I set it up in a VPS with docker-compose and a proxy apache server, but image generation takes some time that I believe timeout the request. thanks @svfwan

[svfwan]

@neymarsabin In my case, I solved the issue on OpenShift by increasing the route timeout using this annotation in the Route definition:

haproxy.router.openshift.io/timeout: 3m

That fixed the timeout problem when generating images that took longer than usual. Since you are using Apache proxy, do you already have any timeout configurations set? Otherwise you can check this discussion (#7134 (comment)) post out which steered me into the right direction. Someone there mentioned they resolved the same issue by updating their nginx.conf. I'm not sure if these things are applicable in your case but yeah hope it helps 😅