I have read and followed all the instructions provided in the README.md.
(Reason: #7677) I am on the latest version of both Open WebUI and Ollama.
(Reason: Not necessary) I have included the browser console logs.
(Reason: Docker not used) 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 expect sensitive information to not be passed to the log files if logging-level exceeds DEBUG. This includes not logging sensitive information when doing an auto-complete for prompts.
Actual Behavior:
Sensitive information is logged for auto-completion of prompts.
Description
Bug Summary:
Sensitive information is logged for auto-completion of prompts even though that should not be the case.
Reproduction Details
Steps to Reproduce:
Make sure to save the output-log of the running open-webui instance. Type something (e.g. "wer" for example below) in the prompt text-field with auto-completion activated and wait until auto-completion generates a suggestion.
If you try this for ongoing conversations, you will see a lot more details about the conversation being logged / shown.
Logs and Screenshots
Console Logs:
INFO: 10.31.108.32:0 - "GET /ws/socket.io/?EIO=4&transport=polling&t=PEhhdQh&sid=wNtHGgGtocr_232AAAAC HTTP/1.0" 200 OK
INFO: 10.31.108.32:0 - "POST /ws/socket.io/?EIO=4&transport=polling&t=PEhhjXf&sid=wNtHGgGtocr_232AAAAC HTTP/1.0" 200 OK
INFO: 10.31.108.32:0 - "GET /api/v1/users/user/settings HTTP/1.0" 200 OK
INFO [open_webui.apps.openai.main] get_all_models()
{'model': 'myModel 1.0', 'messages': [{'role': 'user', 'content': '### Task:\nYou are an autocompletion system. Continue the text in `<text>` based on the **completion type** in `<type>` and the given language. \n\n### **Instructions**:\n1. Analyze `<text>` for context and meaning. \n2. Use `<type>` to guide your output: \n - **General**: Provide a natural, concise continuation. \n - **Search Query**: Complete as if generating a realistic search query. \n3. Start as if you are directly continuing `<text>`. Do **not** repeat, paraphrase, or respond as a model. Simply complete the text. \n4. Ensure the continuation:\n - Flows naturally from `<text>`. \n - Avoids repetition, overexplaining, or unrelated ideas. \n5. If unsure, return: `{ "text": "" }`. \n\n### **Output Rules**:\n- Respond only in JSON format: `{ "text": "<your_completion>" }`.\n\n### **Examples**:\n#### Example 1: \nInput: \n<type>General</type> \n<text>The sun was setting over the horizon, painting the sky</text> \nOutput: \n{ "text": "with vibrant shades of orange and pink." }\n\n#### Example 2: \nInput: \n<type>Search Query</type> \n<text>Top-rated restaurants in</text> \nOutput: \n{ "text": "New York City for Italian cuisine." } \n\n---\n### Context:\n<chat_history>\n\n</chat_history>\n<type>search query</type> \n<text>wer</text> \n#### Output:\n'}], 'stream': False, 'metadata': {'task': 'autocomplete_generation', 'task_body': {'model': 'myModel 1.0', 'prompt': 'wer', 'type': 'search query', 'stream': False}, 'chat_id': None}}
INFO: 10.31.108.32:0 - "POST /api/task/auto/completions HTTP/1.0" 200 OK
INFO: 10.31.108.32:0 - "GET /ws/socket.io/?EIO=4&transport=polling&t=PEhhiqz&sid=GyNWJfF7-EAYjC3_AAAA HTTP/1.0" 200 OK
INFO: 10.31.108.32:0 - "POST /ws/socket.io/?EIO=4&transport=polling&t=PEhhoxm&sid=GyNWJfF7-EAYjC3_AAAA HTTP/1.0" 200 OK
Additional Information
No environment-variables for logging have been explicitly set via .env. But I see the same result if every LOG_LEVEL was set to "INFO" explicitly.
Originally created by @c-hoffmann on GitHub (Dec 9, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/7720
Originally assigned to: @tjbck on GitHub.
## Installation Method
pip
## Environment
- **Open WebUI Version:** v0.4.7
- **Ollama (if applicable):** n/a
- **Operating System:** Server: RHEL9; Client: Win11
- **Browser:** Firefox 133.0
**Confirmation:**
- [X] I have read and followed all the instructions provided in the README.md.
- [ ] (Reason: #7677) I am on the latest version of both Open WebUI and Ollama.
- [ ] (Reason: Not necessary) I have included the browser console logs.
- [ ] (Reason: Docker not used) 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 expect sensitive information to not be passed to the log files if [logging-level exceeds DEBUG](https://docs.openwebui.com/getting-started/advanced-topics/logging/#application-serverbackend-logging). This includes not logging sensitive information when doing an auto-complete for prompts.
## Actual Behavior:
Sensitive information is logged for auto-completion of prompts.
## Description
**Bug Summary:**
Sensitive information is logged for auto-completion of prompts even though that should not be the case.
## Reproduction Details
**Steps to Reproduce:**
Make sure to save the output-log of the running open-webui instance. Type something (e.g. "wer" for example below) in the prompt text-field with auto-completion activated and wait until auto-completion generates a suggestion.
If you try this for ongoing conversations, you will see a lot more details about the conversation being logged / shown.
## Logs and Screenshots
**Console Logs:**
```
INFO: 10.31.108.32:0 - "GET /ws/socket.io/?EIO=4&transport=polling&t=PEhhdQh&sid=wNtHGgGtocr_232AAAAC HTTP/1.0" 200 OK
INFO: 10.31.108.32:0 - "POST /ws/socket.io/?EIO=4&transport=polling&t=PEhhjXf&sid=wNtHGgGtocr_232AAAAC HTTP/1.0" 200 OK
INFO: 10.31.108.32:0 - "GET /api/v1/users/user/settings HTTP/1.0" 200 OK
INFO [open_webui.apps.openai.main] get_all_models()
{'model': 'myModel 1.0', 'messages': [{'role': 'user', 'content': '### Task:\nYou are an autocompletion system. Continue the text in `<text>` based on the **completion type** in `<type>` and the given language. \n\n### **Instructions**:\n1. Analyze `<text>` for context and meaning. \n2. Use `<type>` to guide your output: \n - **General**: Provide a natural, concise continuation. \n - **Search Query**: Complete as if generating a realistic search query. \n3. Start as if you are directly continuing `<text>`. Do **not** repeat, paraphrase, or respond as a model. Simply complete the text. \n4. Ensure the continuation:\n - Flows naturally from `<text>`. \n - Avoids repetition, overexplaining, or unrelated ideas. \n5. If unsure, return: `{ "text": "" }`. \n\n### **Output Rules**:\n- Respond only in JSON format: `{ "text": "<your_completion>" }`.\n\n### **Examples**:\n#### Example 1: \nInput: \n<type>General</type> \n<text>The sun was setting over the horizon, painting the sky</text> \nOutput: \n{ "text": "with vibrant shades of orange and pink." }\n\n#### Example 2: \nInput: \n<type>Search Query</type> \n<text>Top-rated restaurants in</text> \nOutput: \n{ "text": "New York City for Italian cuisine." } \n\n---\n### Context:\n<chat_history>\n\n</chat_history>\n<type>search query</type> \n<text>wer</text> \n#### Output:\n'}], 'stream': False, 'metadata': {'task': 'autocomplete_generation', 'task_body': {'model': 'myModel 1.0', 'prompt': 'wer', 'type': 'search query', 'stream': False}, 'chat_id': None}}
INFO: 10.31.108.32:0 - "POST /api/task/auto/completions HTTP/1.0" 200 OK
INFO: 10.31.108.32:0 - "GET /ws/socket.io/?EIO=4&transport=polling&t=PEhhiqz&sid=GyNWJfF7-EAYjC3_AAAA HTTP/1.0" 200 OK
INFO: 10.31.108.32:0 - "POST /ws/socket.io/?EIO=4&transport=polling&t=PEhhoxm&sid=GyNWJfF7-EAYjC3_AAAA HTTP/1.0" 200 OK
```
## Additional Information
No environment-variables for logging have been explicitly set via `.env`. But I see the same result if every `LOG_LEVEL `was set to "INFO" explicitly.
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 @c-hoffmann on GitHub (Dec 9, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/7720
Originally assigned to: @tjbck on GitHub.
Installation Method
pip
Environment
Open WebUI Version: v0.4.7
Ollama (if applicable): n/a
Operating System: Server: RHEL9; Client: Win11
Browser: Firefox 133.0
Confirmation:
Expected Behavior:
I expect sensitive information to not be passed to the log files if logging-level exceeds DEBUG. This includes not logging sensitive information when doing an auto-complete for prompts.
Actual Behavior:
Sensitive information is logged for auto-completion of prompts.
Description
Bug Summary:
Sensitive information is logged for auto-completion of prompts even though that should not be the case.
Reproduction Details
Steps to Reproduce:
Make sure to save the output-log of the running open-webui instance. Type something (e.g. "wer" for example below) in the prompt text-field with auto-completion activated and wait until auto-completion generates a suggestion.
If you try this for ongoing conversations, you will see a lot more details about the conversation being logged / shown.
Logs and Screenshots
Console Logs:
Additional Information
No environment-variables for logging have been explicitly set via
.env. But I see the same result if everyLOG_LEVELwas set to "INFO" explicitly.@tjbck commented on GitHub (Dec 10, 2024):
Good catch, fixed on dev!