I have read and followed all the instructions provided in the README.md.
I am on 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 the exact steps to reproduce the bug in the "Steps to Reproduce" section below.
Expected Behavior:
I just set up Exa web search, following its integration with the last OWUI release.
In the Admin Settings > Web Search, I enabled the web search toggle, entered my Exa API Key, set "Search Results Count" to 10 and "Concurrent Requests" to 1.
Then, using Claude 3.5 Sonnet through direct API connection (set in Admin Settings > Connections > Manage OpenAI API Connections, rather than the Anthropic Manifold function), I turned on the Web Search button before asking "What is Open WebUI?".
I was expecting getting an answer including the search results from Exa.
Actual Behavior:
I got a "404: Not Found" message as an answer.
Description
Bug Summary:
[Provide a brief but clear summary of the bug]
Reproduction Details
Steps to Reproduce:
[Outline the steps to reproduce the bug. Be as detailed as possible.]
Logs and Screenshots
Browser Console Logs:
[Log] modelId – "claude-3-5-sonnet-latest" (Help.BNof0llX.js, line 138)
[Log] {chat_id: "35a0a6b2-1a64-4c58-b790-25495b5c7df2", message_id: "ab436644-28a0-46d7-9b7d-ad8da21eaf8f", data: {type: "status", data: {action: "web_search", description: "Generating search query", done: false}}} (Help.BNof0llX.js, line 137)
[Log] Object (Help.BNof0llX.js, line 137)
chat_id: "35a0a6b2-1a64-4c58-b790-25495b5c7df2"
data: {type: "status", data: Object}
message_id: "ab436644-28a0-46d7-9b7d-ad8da21eaf8f"
Object Prototype
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] Object (Help.BNof0llX.js, line 137)
chat_id: "35a0a6b2-1a64-4c58-b790-25495b5c7df2"
data: {type: "status", data: Object}
message_id: "ab436644-28a0-46d7-9b7d-ad8da21eaf8f"
Object Prototype
__defineGetter__(propertyName, getterFunction)
__defineSetter__(propertyName, setterFunction)
__lookupGetter__(propertyName)
__lookupSetter__(propertyName)
constructor: function()
hasOwnProperty(propertyName)
isPrototypeOf(property)
propertyIsEnumerable(propertyName)
toLocaleString()
toString()
valueOf()
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Error] Failed to load resource: the server responded with a status of 400 () (completions, line 0)
[Log] null (Help.BNof0llX.js, line 142)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: []} (0.CT-1rLZG.js, line 1)
Docker Container Logs:
open-webui | INFO [open_webui.retrieval.web.exa] Searching with Exa for query: what is Open WebUI?
open-webui | INFO [open_webui.retrieval.web.exa] Found 10 results
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'github.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'webui.me'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'webui.me'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'pimylifeup.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'dev.to'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | INFO [open_webui.routers.retrieval] save_docs_to_vector_db: document Open WebUI, Redirection, ğŸ�¡ Home | Open WebUI, GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...), Break free from ChatGPT with OpenWebUI - The Open Source Way - DEV Community, â� Features | Open WebUI, 🚀 Getting Started | Open WebUI, Self-hosting an AI Chatbot with Open WebUI on the Raspberry Pi - Pi My Life Up web-search-2fc2b0750fdffd37674af6c795fe4f54b830e43a0f4296dbf99f
open-webui | INFO [open_webui.routers.retrieval] Using token text splitter: cl100k_base
open-webui | INFO [open_webui.routers.retrieval] adding to collection web-search-2fc2b0750fdffd37674af6c795fe4f54b830e43a0f4296dbf99f
open-webui | INFO [open_webui.routers.openai] get_all_models()
pipelines | INFO: 172.18.0.1:47112 - "GET /models HTTP/1.1" 200 OK
open-webui | ERROR [open_webui.routers.openai] 404, message='Not Found', url='https://api.anthropic.com/v1/chat/completions'
open-webui | Traceback (most recent call last):
open-webui | File "/app/backend/open_webui/routers/openai.py", line 696, in generate_chat_completion
open-webui | r.raise_for_status()
open-webui | File "/usr/local/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1161, in raise_for_status
open-webui | raise ClientResponseError(
open-webui | aiohttp.client_exceptions.ClientResponseError: 404, message='Not Found', url='https://api.anthropic.com/v1/chat/completions'
open-webui | INFO [open_webui.retrieval.utils] query_doc:result [['60ffc76e-66b7-46a8-bfb8-6a9e8d1a5e08', 'df65bd50-a4c7-436a-a1a3-9ebd884b344a', '15e932b2-676b-47c0-ad0e-56847c7dfc4b', '16d95fc5-4b0a-4d01-adbf-6020e3107abc']] [[{'description': 'Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG, making it a powerful AI deployment solution.', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/', 'start_index': -1, 'title': 'ğŸ�¡ Home | Open WebUI'}, {'description': 'User-friendly AI Interface (Supports Ollama, OpenAI API, ...) - open-webui/open-webui', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://github.com/open-webui/open-webui', 'start_index': -1, 'title': 'GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...)'}, {'description': 'Welcome to the Open WebUI Documentation Hub! Below is a list of essential guides and resources to help you get started, manage, and develop with Open WebUI.', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/getting-started/', 'start_index': 0, 'title': '🚀 Getting Started | Open WebUI'}, {'description': 'Key Features of Open WebUI â\xad�', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/features/', 'start_index': 25136, 'title': 'â\xad� Features | Open WebUI'}]]
open-webui | ERROR [open_webui.routers.openai] 404, message='Not Found', url='https://api.anthropic.com/v1/chat/completions'
open-webui | Traceback (most recent call last):
open-webui | File "/app/backend/open_webui/routers/openai.py", line 696, in generate_chat_completion
open-webui | r.raise_for_status()
open-webui | File "/usr/local/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1161, in raise_for_status
open-webui | raise ClientResponseError(
open-webui | aiohttp.client_exceptions.ClientResponseError: 404, message='Not Found', url='https://api.anthropic.com/v1/chat/completions'
open-webui | Raw existing memories: []
open-webui |
open-webui | Processed memory contents: []
open-webui |
open-webui | Making request to OpenAI API: https://openrouter.ai/api/v1/chat/completions
open-webui |
open-webui | INFO: 195.134.162.26:0 - "POST /api/chat/completions HTTP/1.1" 400 Bad Request
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
Screenshots/Screen Recordings (if applicable):
Additional Information
Exa Web Search DOES work with OpenAI models :
open-webui | INFO [open_webui.retrieval.web.exa] Searching with Exa for query: What is Open WebUI and its functionalities
open-webui | INFO [open_webui.retrieval.web.exa] Found 10 results
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'github.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'webui.me'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'webui.me'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'www.eve-ng.net'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | INFO [open_webui.routers.retrieval] save_docs_to_vector_db: document Open WebUI, Redirection, ğŸ�¡ Home | Open WebUI, EVE WEB UI Interface functions and features -, GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...), â� Features | Open WebUI, Just a moment..., 🚀 Getting Started | Open WebUI web-search-673364bb72fd18bdb4f14f7eb419cd06012ea981b20732e9b2a6
open-webui | INFO [open_webui.routers.retrieval] Using token text splitter: cl100k_base
open-webui | INFO [open_webui.routers.retrieval] adding to collection web-search-673364bb72fd18bdb4f14f7eb419cd06012ea981b20732e9b2a6
open-webui | INFO [open_webui.routers.openai] get_all_models()
pipelines | INFO: 172.18.0.1:45572 - "GET /models HTTP/1.1" 200 OK
open-webui | INFO [open_webui.retrieval.utils] query_doc:result [['ed19b293-d459-4441-b0eb-987f21018a26', '3529fc1a-b756-4dd2-a5d1-cf365e7c7fba', 'e5c4b395-c0cc-47ae-910e-6b9dd9d18dd2', 'c18bc942-b43b-401b-8893-3b79d7ec9c5f']] [[{'description': 'Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG, making it a powerful AI deployment solution.', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/', 'start_index': -1, 'title': '� Home | Open WebUI'}, {'description': 'User-friendly AI Interface (Supports Ollama, OpenAI API, ...) - open-webui/open-webui', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://github.com/open-webui/open-webui', 'start_index': -1, 'title': 'GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...)'}, {'description': 'Welcome to the Open WebUI Documentation Hub! Below is a list of essential guides and resources to help you get started, manage, and develop with Open WebUI.', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/getting-started/', 'start_index': 0, 'title': '🚀 Getting Started | Open WebUI'}, {'description': 'User-friendly AI Interface (Supports Ollama, OpenAI API, ...) - open-webui/open-webui', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://github.com/open-webui/open-webui', 'start_index': 15735, 'title': 'GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...)'}]]
open-webui | INFO [open_webui.retrieval.utils] query_doc:result [['e5c4b395-c0cc-47ae-910e-6b9dd9d18dd2', '3529fc1a-b756-4dd2-a5d1-cf365e7c7fba', 'e0d59cc0-1050-4e63-aa01-608a51a0eb5a', '3fd8481b-9dd6-4f6e-b985-88b2c4d5526c']] [[{'description': 'Welcome to the Open WebUI Documentation Hub! Below is a list of essential guides and resources to help you get started, manage, and develop with Open WebUI.', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/getting-started/', 'start_index': 0, 'title': '🚀 Getting Started | Open WebUI'}, {'description': 'User-friendly AI Interface (Supports Ollama, OpenAI API, ...) - open-webui/open-webui', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://github.com/open-webui/open-webui', 'start_index': -1, 'title': 'GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...)'}, {'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/tutorial/images/', 'start_index': 0, 'title': 'Open WebUI'}, {'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/tutorial/openai/', 'start_index': 0, 'title': 'Open WebUI'}]]
open-webui | INFO [open_webui.routers.openai] get_all_models()
pipelines | INFO: 172.18.0.1:53928 - "GET /models HTTP/1.1" 200 OK
open-webui | Raw existing memories: []
open-webui |
open-webui | Processed memory contents: []
open-webui |
open-webui | Making request to OpenAI API: https://openrouter.ai/api/v1/chat/completions
open-webui |
open-webui | INFO: 195.134.162.26:0 - "POST /api/chat/completions HTTP/1.1" 200 OK
open-webui | INFO [open_webui.routers.openai] get_all_models()
pipelines | INFO: 172.18.0.1:37500 - "GET /models HTTP/1.1" 200 OK
open-webui | INFO [open_webui.routers.openai] get_all_models()
pipelines | INFO: 172.18.0.1:37504 - "GET /models HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "POST /api/chat/completed HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/all/tags HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/74623284-8cb0-4a0b-9312-262d7e9be0e4 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /audio/notification.mp3 HTTP/1.1" 206 Partial Content
open-webui | INFO: 195.134.162.26:0 - "POST /api/v1/chats/74623284-8cb0-4a0b-9312-262d7e9be0e4 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/all/tags HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /audio/notification.mp3 HTTP/1.1" 206 Partial Content
open-webui | INFO: connection closed
Note
If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!
Originally created by @leonardsellem on GitHub (Feb 5, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/9409
# Bug Report
## Installation Method
Docker
## Environment
- **Open WebUI Version:** v0.5.9
- **Ollama (if applicable):** N/A
- **Operating System:** macOS Sequoia (15.2)
- **Browser (if applicable):** Safari 18.2
**Confirmation:**
- [x] I have read and followed all the instructions provided in the README.md.
- [x] I am on 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 the exact steps to reproduce the bug in the "Steps to Reproduce" section below.
## Expected Behavior:
I just set up Exa web search, following its integration with the last OWUI release.
In the Admin Settings > Web Search, I enabled the web search toggle, entered my Exa API Key, set "Search Results Count" to 10 and "Concurrent Requests" to 1.
Then, using Claude 3.5 Sonnet through direct API connection (set in Admin Settings > Connections > Manage OpenAI API Connections, rather than the Anthropic Manifold function), I turned on the Web Search button before asking "What is Open WebUI?".
I was expecting getting an answer including the search results from Exa.
## Actual Behavior:
I got a "404: Not Found" message as an answer.
## Description
**Bug Summary:**
[Provide a brief but clear summary of the bug]
## Reproduction Details
**Steps to Reproduce:**
[Outline the steps to reproduce the bug. Be as detailed as possible.]
## Logs and Screenshots
**Browser Console Logs:**
```
[Log] modelId – "claude-3-5-sonnet-latest" (Help.BNof0llX.js, line 138)
[Log] {chat_id: "35a0a6b2-1a64-4c58-b790-25495b5c7df2", message_id: "ab436644-28a0-46d7-9b7d-ad8da21eaf8f", data: {type: "status", data: {action: "web_search", description: "Generating search query", done: false}}} (Help.BNof0llX.js, line 137)
[Log] Object (Help.BNof0llX.js, line 137)
chat_id: "35a0a6b2-1a64-4c58-b790-25495b5c7df2"
data: {type: "status", data: Object}
message_id: "ab436644-28a0-46d7-9b7d-ad8da21eaf8f"
Object Prototype
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] Object (Help.BNof0llX.js, line 137)
chat_id: "35a0a6b2-1a64-4c58-b790-25495b5c7df2"
data: {type: "status", data: Object}
message_id: "ab436644-28a0-46d7-9b7d-ad8da21eaf8f"
Object Prototype
__defineGetter__(propertyName, getterFunction)
__defineSetter__(propertyName, setterFunction)
__lookupGetter__(propertyName)
__lookupSetter__(propertyName)
constructor: function()
hasOwnProperty(propertyName)
isPrototypeOf(property)
propertyIsEnumerable(propertyName)
toLocaleString()
toString()
valueOf()
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Error] Failed to load resource: the server responded with a status of 400 () (completions, line 0)
[Log] null (Help.BNof0llX.js, line 142)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: ["claude-3-5-sonnet-latest"]} (0.CT-1rLZG.js, line 1)
[Log] usage – {models: []} (0.CT-1rLZG.js, line 1)
```
**Docker Container Logs:**
```
open-webui | INFO [open_webui.retrieval.web.exa] Searching with Exa for query: what is Open WebUI?
open-webui | INFO [open_webui.retrieval.web.exa] Found 10 results
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'github.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'webui.me'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'webui.me'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'pimylifeup.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'dev.to'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | INFO [open_webui.routers.retrieval] save_docs_to_vector_db: document Open WebUI, Redirection, ğŸ�¡ Home | Open WebUI, GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...), Break free from ChatGPT with OpenWebUI - The Open Source Way - DEV Community, â� Features | Open WebUI, 🚀 Getting Started | Open WebUI, Self-hosting an AI Chatbot with Open WebUI on the Raspberry Pi - Pi My Life Up web-search-2fc2b0750fdffd37674af6c795fe4f54b830e43a0f4296dbf99f
open-webui | INFO [open_webui.routers.retrieval] Using token text splitter: cl100k_base
open-webui | INFO [open_webui.routers.retrieval] adding to collection web-search-2fc2b0750fdffd37674af6c795fe4f54b830e43a0f4296dbf99f
open-webui | INFO [open_webui.routers.openai] get_all_models()
pipelines | INFO: 172.18.0.1:47112 - "GET /models HTTP/1.1" 200 OK
open-webui | ERROR [open_webui.routers.openai] 404, message='Not Found', url='https://api.anthropic.com/v1/chat/completions'
open-webui | Traceback (most recent call last):
open-webui | File "/app/backend/open_webui/routers/openai.py", line 696, in generate_chat_completion
open-webui | r.raise_for_status()
open-webui | File "/usr/local/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1161, in raise_for_status
open-webui | raise ClientResponseError(
open-webui | aiohttp.client_exceptions.ClientResponseError: 404, message='Not Found', url='https://api.anthropic.com/v1/chat/completions'
open-webui | INFO [open_webui.retrieval.utils] query_doc:result [['60ffc76e-66b7-46a8-bfb8-6a9e8d1a5e08', 'df65bd50-a4c7-436a-a1a3-9ebd884b344a', '15e932b2-676b-47c0-ad0e-56847c7dfc4b', '16d95fc5-4b0a-4d01-adbf-6020e3107abc']] [[{'description': 'Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG, making it a powerful AI deployment solution.', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/', 'start_index': -1, 'title': 'ğŸ�¡ Home | Open WebUI'}, {'description': 'User-friendly AI Interface (Supports Ollama, OpenAI API, ...) - open-webui/open-webui', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://github.com/open-webui/open-webui', 'start_index': -1, 'title': 'GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...)'}, {'description': 'Welcome to the Open WebUI Documentation Hub! Below is a list of essential guides and resources to help you get started, manage, and develop with Open WebUI.', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/getting-started/', 'start_index': 0, 'title': '🚀 Getting Started | Open WebUI'}, {'description': 'Key Features of Open WebUI â\xad�', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/features/', 'start_index': 25136, 'title': 'â\xad� Features | Open WebUI'}]]
open-webui | ERROR [open_webui.routers.openai] 404, message='Not Found', url='https://api.anthropic.com/v1/chat/completions'
open-webui | Traceback (most recent call last):
open-webui | File "/app/backend/open_webui/routers/openai.py", line 696, in generate_chat_completion
open-webui | r.raise_for_status()
open-webui | File "/usr/local/lib/python3.11/site-packages/aiohttp/client_reqrep.py", line 1161, in raise_for_status
open-webui | raise ClientResponseError(
open-webui | aiohttp.client_exceptions.ClientResponseError: 404, message='Not Found', url='https://api.anthropic.com/v1/chat/completions'
open-webui | Raw existing memories: []
open-webui |
open-webui | Processed memory contents: []
open-webui |
open-webui | Making request to OpenAI API: https://openrouter.ai/api/v1/chat/completions
open-webui |
open-webui | INFO: 195.134.162.26:0 - "POST /api/chat/completions HTTP/1.1" 400 Bad Request
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
```
**Screenshots/Screen Recordings (if applicable):**

## Additional Information
Exa Web Search DOES work with OpenAI models :
```
open-webui | INFO [open_webui.retrieval.web.exa] Searching with Exa for query: What is Open WebUI and its functionalities
open-webui | INFO [open_webui.retrieval.web.exa] Found 10 results
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'github.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'webui.me'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'webui.me'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'docs.openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'openwebui.com'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | /usr/local/lib/python3.11/site-packages/urllib3/connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host 'www.eve-ng.net'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
open-webui | warnings.warn(
open-webui | INFO [open_webui.routers.retrieval] save_docs_to_vector_db: document Open WebUI, Redirection, ğŸ�¡ Home | Open WebUI, EVE WEB UI Interface functions and features -, GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...), â� Features | Open WebUI, Just a moment..., 🚀 Getting Started | Open WebUI web-search-673364bb72fd18bdb4f14f7eb419cd06012ea981b20732e9b2a6
open-webui | INFO [open_webui.routers.retrieval] Using token text splitter: cl100k_base
open-webui | INFO [open_webui.routers.retrieval] adding to collection web-search-673364bb72fd18bdb4f14f7eb419cd06012ea981b20732e9b2a6
open-webui | INFO [open_webui.routers.openai] get_all_models()
pipelines | INFO: 172.18.0.1:45572 - "GET /models HTTP/1.1" 200 OK
open-webui | INFO [open_webui.retrieval.utils] query_doc:result [['ed19b293-d459-4441-b0eb-987f21018a26', '3529fc1a-b756-4dd2-a5d1-cf365e7c7fba', 'e5c4b395-c0cc-47ae-910e-6b9dd9d18dd2', 'c18bc942-b43b-401b-8893-3b79d7ec9c5f']] [[{'description': 'Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform designed to operate entirely offline. It supports various LLM runners like Ollama and OpenAI-compatible APIs, with built-in inference engine for RAG, making it a powerful AI deployment solution.', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/', 'start_index': -1, 'title': '� Home | Open WebUI'}, {'description': 'User-friendly AI Interface (Supports Ollama, OpenAI API, ...) - open-webui/open-webui', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://github.com/open-webui/open-webui', 'start_index': -1, 'title': 'GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...)'}, {'description': 'Welcome to the Open WebUI Documentation Hub! Below is a list of essential guides and resources to help you get started, manage, and develop with Open WebUI.', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/getting-started/', 'start_index': 0, 'title': '🚀 Getting Started | Open WebUI'}, {'description': 'User-friendly AI Interface (Supports Ollama, OpenAI API, ...) - open-webui/open-webui', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://github.com/open-webui/open-webui', 'start_index': 15735, 'title': 'GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...)'}]]
open-webui | INFO [open_webui.retrieval.utils] query_doc:result [['e5c4b395-c0cc-47ae-910e-6b9dd9d18dd2', '3529fc1a-b756-4dd2-a5d1-cf365e7c7fba', 'e0d59cc0-1050-4e63-aa01-608a51a0eb5a', '3fd8481b-9dd6-4f6e-b985-88b2c4d5526c']] [[{'description': 'Welcome to the Open WebUI Documentation Hub! Below is a list of essential guides and resources to help you get started, manage, and develop with Open WebUI.', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/getting-started/', 'start_index': 0, 'title': '🚀 Getting Started | Open WebUI'}, {'description': 'User-friendly AI Interface (Supports Ollama, OpenAI API, ...) - open-webui/open-webui', 'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://github.com/open-webui/open-webui', 'start_index': -1, 'title': 'GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...)'}, {'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/tutorial/images/', 'start_index': 0, 'title': 'Open WebUI'}, {'embedding_config': '{"engine": "openai", "model": "text-embedding-3-large"}', 'language': 'en', 'source': 'https://docs.openwebui.com/tutorial/openai/', 'start_index': 0, 'title': 'Open WebUI'}]]
open-webui | INFO [open_webui.routers.openai] get_all_models()
pipelines | INFO: 172.18.0.1:53928 - "GET /models HTTP/1.1" 200 OK
open-webui | Raw existing memories: []
open-webui |
open-webui | Processed memory contents: []
open-webui |
open-webui | Making request to OpenAI API: https://openrouter.ai/api/v1/chat/completions
open-webui |
open-webui | INFO: 195.134.162.26:0 - "POST /api/chat/completions HTTP/1.1" 200 OK
open-webui | INFO [open_webui.routers.openai] get_all_models()
pipelines | INFO: 172.18.0.1:37500 - "GET /models HTTP/1.1" 200 OK
open-webui | INFO [open_webui.routers.openai] get_all_models()
pipelines | INFO: 172.18.0.1:37504 - "GET /models HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "POST /api/chat/completed HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/all/tags HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/74623284-8cb0-4a0b-9312-262d7e9be0e4 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /audio/notification.mp3 HTTP/1.1" 206 Partial Content
open-webui | INFO: 195.134.162.26:0 - "POST /api/v1/chats/74623284-8cb0-4a0b-9312-262d7e9be0e4 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/all/tags HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /api/v1/chats/?page=1 HTTP/1.1" 200 OK
open-webui | INFO: 195.134.162.26:0 - "GET /audio/notification.mp3 HTTP/1.1" 206 Partial Content
open-webui | INFO: connection closed
```
## Note
If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @leonardsellem on GitHub (Feb 5, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/9409
Bug Report
Installation Method
Docker
Environment
Open WebUI Version: v0.5.9
Ollama (if applicable): N/A
Operating System: macOS Sequoia (15.2)
Browser (if applicable): Safari 18.2
Confirmation:
Expected Behavior:
I just set up Exa web search, following its integration with the last OWUI release.
In the Admin Settings > Web Search, I enabled the web search toggle, entered my Exa API Key, set "Search Results Count" to 10 and "Concurrent Requests" to 1.
Then, using Claude 3.5 Sonnet through direct API connection (set in Admin Settings > Connections > Manage OpenAI API Connections, rather than the Anthropic Manifold function), I turned on the Web Search button before asking "What is Open WebUI?".
I was expecting getting an answer including the search results from Exa.
Actual Behavior:
I got a "404: Not Found" message as an answer.
Description
Bug Summary:
[Provide a brief but clear summary of the bug]
Reproduction Details
Steps to Reproduce:
[Outline the steps to reproduce the bug. Be as detailed as possible.]
Logs and Screenshots
Browser Console Logs:
Docker Container Logs:
Screenshots/Screen Recordings (if applicable):

Additional Information
Exa Web Search DOES work with OpenAI models :
Note
If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!
@tjbck commented on GitHub (Feb 5, 2025):
@abdalrohman