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. (not applicable)
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:
When Ollama is configured via Connections in Admin Settings it will override OLLAMA_BASE_URL as the default.
Actual Behavior:
I have been trying to get this auto memory function to work and have ran into a few issues. After fixing a typo (ClentError instead of ClientError), I ran into the following issue when it was trying to retrieve current memories for de-duplication:
HTTPConnectionPool(host='host.docker.internal', port=11434): Max retries exceeded with url
Looking at the docs a bit more I found that OLLAMA_BASE_URL defaults to http://host.docker.internal:11434. My Ollama runs behind Caddy and is not on the same host.
After setting OLLAMA_BASE_URL to the same value as what was in my Connections settings, this function is now working.
Description
Bug Summary:
Unexpected HTTP errors from internal functions calling Ollama.
Reproduction Details
Steps to Reproduce:
Install the current 0.2 version of auto learn.
Leave defaults in place so that OLLAMA_BASE_URL is set to the default value of http://host.docker.internal:11434
Originally created by @joestump on GitHub (Nov 22, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/7226
# Bug Report
## Installation Method
Docker via Docker Compose
## Environment
- **Open WebUI Version:** `latest`
- **Ollama (if applicable):** `latest`
- **Operating System:** Ubuntu 22.04
**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. (not applicable)~~
- [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:
When Ollama is configured via Connections in Admin Settings it will override `OLLAMA_BASE_URL` as the default.
## Actual Behavior:
I have been trying to get [this auto memory function](https://openwebui.com/f/caplescrest/auto_memory) to work and have ran into a few issues. After fixing a typo (`ClentError` instead of `ClientError`), I ran into the following issue when it was trying to retrieve current memories for de-duplication:
```
HTTPConnectionPool(host='host.docker.internal', port=11434): Max retries exceeded with url
```
Looking at the docs a bit more I found that [`OLLAMA_BASE_URL`](https://docs.openwebui.com/getting-started/advanced-topics/env-configuration#ollama_base_url) defaults to `http://host.docker.internal:11434`. My Ollama runs behind Caddy and is not on the same host.
After setting `OLLAMA_BASE_URL` to the same value as what was in my Connections settings, this function is now working.
## Description
**Bug Summary:**
Unexpected HTTP errors from internal functions calling Ollama.
## Reproduction Details
**Steps to Reproduce:**
1. Install the current 0.2 version of auto learn.
2. Leave defaults in place so that `OLLAMA_BASE_URL` is set to the default value of `http://host.docker.internal:11434`
3. Try to use an internal function from a function.
## Logs and Screenshots
You can see logs, screenshots, and my debugging efforts in this discussion: https://github.com/open-webui/open-webui/discussions/7220
Kinda related, but it'd be hecka nice if the functions/tool pages linked out to a GitHub user profile or repository for the function. I have no way of reporting the ClentError typo to the author.
<!-- gh-comment-id:2493791890 -->
@joestump commented on GitHub (Nov 22, 2024):
Kinda related, but it'd be hecka nice if the functions/tool pages linked out to a GitHub user profile or repository for the function. I have no way of reporting the `ClentError` typo to the author.
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 @joestump on GitHub (Nov 22, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/7226
Bug Report
Installation Method
Docker via Docker Compose
Environment
latestlatestConfirmation:
I have included the browser console logs. (not applicable)Expected Behavior:
When Ollama is configured via Connections in Admin Settings it will override
OLLAMA_BASE_URLas the default.Actual Behavior:
I have been trying to get this auto memory function to work and have ran into a few issues. After fixing a typo (
ClentErrorinstead ofClientError), I ran into the following issue when it was trying to retrieve current memories for de-duplication:Looking at the docs a bit more I found that
OLLAMA_BASE_URLdefaults tohttp://host.docker.internal:11434. My Ollama runs behind Caddy and is not on the same host.After setting
OLLAMA_BASE_URLto the same value as what was in my Connections settings, this function is now working.Description
Bug Summary:
Unexpected HTTP errors from internal functions calling Ollama.
Reproduction Details
Steps to Reproduce:
OLLAMA_BASE_URLis set to the default value ofhttp://host.docker.internal:11434Logs and Screenshots
You can see logs, screenshots, and my debugging efforts in this discussion: https://github.com/open-webui/open-webui/discussions/7220
@joestump commented on GitHub (Nov 22, 2024):
Kinda related, but it'd be hecka nice if the functions/tool pages linked out to a GitHub user profile or repository for the function. I have no way of reporting the
ClentErrortypo to the author.