[GH-ISSUE #15251] issue: Exa.ai search is failing #17508

Closed
opened 2026-04-19 23:17:15 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @arcreactor81 on GitHub (Jun 24, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/15251

Check Existing Issues

  • I have searched the existing issues and discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.6.15

Ollama Version (if applicable)

No response

Operating System

Windows 11

Browser (if applicable)

No response

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

Toggling web search should allow me to use the exa.ai search capability, which was true as of last update.

Actual Behavior

Issue: Web search functionality fails with a 400 error when no search engine API key is found in environment variables.
raise HTTPException(
status_code=400,
detail="No search engine API key found in environment variables"
)
Location:

 File: /app/backend/open_webui/routers/retrieval.py  
 Line: 1867 (in process_web_search() function)

Tried using multiple models from different providers, but same issue.

Steps to Reproduce

Trigger a web search query to exa.ai endpoint; all other search providers are working as intended, but not exa.ai.

Logs & Screenshots

results = await process_web_search(

                └ <function process_web_search at 0x7f31a4a70fe0>

File "/app/backend/open_webui/routers/retrieval.py", line 1867, in process_web_search

raise HTTPException(

      └ <class 'fastapi.exceptions.HTTPException'>

fastapi.exceptions.HTTPException: 400: No search engine API key found in environment variables
2025-06-24 05:31:22.211 | INFO | open_webui.routers.openai:get_all_models:391 - get_all_models() - {}
2025-06-24 05:31:22.820 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:33820 - "GET /_app/version.json HTTP/1.1" 304 - {}
2025-06-24 05:31:25.874 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:54148 - "POST /api/chat/completions HTTP/1.1" 200 - {}
2025-06-24 05:31:25.916 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:54148 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-06-24 05:31:32.459 | INFO | open_webui.routers.openai:get_all_models:391 - get_all_models() - {}
2025-06-24 05:31:32.505 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:33830 - "POST /api/chat/completed HTTP/1.1" 200 - {}
2025-06-24 05:31:32.576 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:33830 - "POST /api/v1/chats/09f93307-6098-47ee-a9ff-1f34b1715a02 HTTP/1.1" 200 - {}
2025-06-24 05:31:32.606 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:33830 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-06-24 05:31:38.019 | INFO | open_webui.routers.openai:get_all_models:391 - get_all_models() - {}
2025-06-24 05:31:41.831 | INFO | open_webui.routers.openai:get_all_models:391 - get_all_models() - {}
2025-06-24 05:31:41.962 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:54164 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-06-24 05:31:41.963 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:54168 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}
2025-06-24 05:31:41.965 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:54170 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {}

Additional Information

No response

Originally created by @arcreactor81 on GitHub (Jun 24, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/15251 ### Check Existing Issues - [x] I have searched the existing issues and discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.6.15 ### Ollama Version (if applicable) _No response_ ### Operating System Windows 11 ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior Toggling web search should allow me to use the exa.ai search capability, which was true as of last update. ### Actual Behavior Issue: Web search functionality fails with a 400 error when no search engine API key is found in environment variables. raise HTTPException( status_code=400, detail="No search engine API key found in environment variables" ) Location: File: /app/backend/open_webui/routers/retrieval.py Line: 1867 (in process_web_search() function) Tried using multiple models from different providers, but same issue. ### Steps to Reproduce Trigger a web search query to exa.ai endpoint; all other search providers are working as intended, but not exa.ai. ### Logs & Screenshots ``` results = await process_web_search( └ <function process_web_search at 0x7f31a4a70fe0> ``` File "/app/backend/open_webui/routers/retrieval.py", line 1867, in process_web_search ``` raise HTTPException( └ <class 'fastapi.exceptions.HTTPException'> ``` fastapi.exceptions.HTTPException: 400: No search engine API key found in environment variables 2025-06-24 05:31:22.211 | INFO | open_webui.routers.openai:get_all_models:391 - get_all_models() - {} 2025-06-24 05:31:22.820 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:33820 - "GET /_app/version.json HTTP/1.1" 304 - {} 2025-06-24 05:31:25.874 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:54148 - "POST /api/chat/completions HTTP/1.1" 200 - {} 2025-06-24 05:31:25.916 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:54148 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-06-24 05:31:32.459 | INFO | open_webui.routers.openai:get_all_models:391 - get_all_models() - {} 2025-06-24 05:31:32.505 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:33830 - "POST /api/chat/completed HTTP/1.1" 200 - {} 2025-06-24 05:31:32.576 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:33830 - "POST /api/v1/chats/09f93307-6098-47ee-a9ff-1f34b1715a02 HTTP/1.1" 200 - {} 2025-06-24 05:31:32.606 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:33830 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-06-24 05:31:38.019 | INFO | open_webui.routers.openai:get_all_models:391 - get_all_models() - {} 2025-06-24 05:31:41.831 | INFO | open_webui.routers.openai:get_all_models:391 - get_all_models() - {} 2025-06-24 05:31:41.962 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:54164 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-06-24 05:31:41.963 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:54168 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} 2025-06-24 05:31:41.965 | INFO | uvicorn.protocols.http.httptools_impl:send:476 - 172.17.0.1:54170 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 - {} ### Additional Information _No response_
GiteaMirror added the bug label 2026-04-19 23:17:15 -05:00
Author
Owner

@tjbck commented on GitHub (Jun 24, 2025):

Unable to reproduce, I'd suggest you check whether the API key has been correctly registered.

<!-- gh-comment-id:2999189272 --> @tjbck commented on GitHub (Jun 24, 2025): Unable to reproduce, I'd suggest you check whether the API key has been correctly registered.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#17508