[ 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.
Expected Behavior:
I am expecting to be able to add a model and to be able to utilize it
Actual Behavior:
I click on the Workspace link and see the page under the Models tab. I click on Discover a Model and get to the Open WebUI Community page.((https://openwebui.com/).
I select a model (like codewriter), view it, and click on the "Get" button. In the popup that comes up, I put in my ollama URL and click on the Inport to WebUI button. This sends me back to the model page. The difference is that, as shown in the workspace image below, I am seeing the "Create Model" page with information about codewriter included.
There is one problem: please note the Base Model (From) list in the page. Without a base model, I cannot add the codewriter model (or any model).; The problem is, of course, that there are no base models in that list. There appears to be no known way to include a base model because it is a list.
Of course, I then decided to "import" the model. I return to the WebUI Community page, and click on the Get button, and this time I click on the Download as JSON link. I save codewriter to a JSON file, then retun to my Workspace page on WebUI and click on the "imoport Models" link. I actually succeed in installing the model.
But then, when I try to use the model, I get the following failure:
I am getting the same behavior regardless of the model I select.
Bug Summary:
The Open WebUI is incapable of adding new models, and its import of models has something wrong in the JSON.
Reproduction Details
Steps to Reproduce:
Click on the Workspace Link in the main page
Select Discover a Model
Select a model from the WebUI Community page
Click on its Get button
See the new Workspace page that has the information about the selected model but which cannot create it because there is no "base model" to select
Originally created by @factor3 on GitHub (Sep 13, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/5409
# Bug Report
## Installation Method
Docker, using Open WebUI with ollama support:
docker run -d -p 3000:8080 --gpus=all -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:ollama
## Environment
Ubuntu V22.04 Docker
- **Open WebUI Version:** latest
- **Ollama (if applicable):**latest?
- **Operating System:** Ubuntu v22.04
- **Browser (if applicable):** Chrome, Firefox
**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.
## Expected Behavior:
I am expecting to be able to add a model and to be able to utilize it
## Actual Behavior:
I click on the Workspace link and see the page under the Models tab. I click on Discover a Model and get to the Open WebUI Community page.((https://openwebui.com/).
I select a model (like codewriter), view it, and click on the "Get" button. In the popup that comes up, I put in my ollama URL and click on the Inport to WebUI button. This sends me back to the model page. The difference is that, as shown in the workspace image below, I am seeing the "Create Model" page with information about codewriter included.
[Workspace](https://github.com/user-attachments/assets/d4815b2c-4fe1-4fa3-a6a3-6ebf24d3bad2)
There is one problem: please note the Base Model (From) list in the page. Without a base model, I cannot add the codewriter model (or any model).; The problem is, of course, that there are no base models in that list. There appears to be no known way to include a base model because it is a *list*.
Of course, I then decided to "import" the model. I return to the WebUI Community page, and click on the Get button, and this time I click on the Download as JSON link. I save codewriter to a JSON file, then retun to my Workspace page on WebUI and click on the "imoport Models" link. I actually succeed in installing the model.
But then, when I try to use the model, I get the following failure:
I am getting the same behavior regardless of the model I select.
**Bug Summary:**
The Open WebUI is incapable of adding new models, and its import of models has something wrong in the JSON.
## Reproduction Details
**Steps to Reproduce:**
1. Click on the Workspace Link in the main page
2. Select Discover a Model
3. Select a model from the WebUI Community page
4. Click on its Get button
5. See the new Workspace page that has the information about the selected model but which cannot create it because there is no "base model" to select
Hello @factor3 You might first go terminal or command prompt . then run Ollama pull llama3.1:70b or direct from model place Admin - Model - Check if you can pull model here.
<!-- gh-comment-id:2350759915 -->
@peuportier commented on GitHub (Sep 14, 2024):
Hello @factor3 You might first go terminal or command prompt . then run Ollama pull llama3.1:70b or direct from model place Admin - Model - Check if you can pull model here.
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 @factor3 on GitHub (Sep 13, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/5409
Bug Report
Installation Method
Docker, using Open WebUI with ollama support:
docker run -d -p 3000:8080 --gpus=all -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:ollama
Environment
Ubuntu V22.04 Docker
Open WebUI Version: latest
**Ollama (if applicable):**latest?
Operating System: Ubuntu v22.04
Browser (if applicable): Chrome, Firefox
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.
Expected Behavior:
I am expecting to be able to add a model and to be able to utilize it
Actual Behavior:
I click on the Workspace link and see the page under the Models tab. I click on Discover a Model and get to the Open WebUI Community page.((https://openwebui.com/).
I select a model (like codewriter), view it, and click on the "Get" button. In the popup that comes up, I put in my ollama URL and click on the Inport to WebUI button. This sends me back to the model page. The difference is that, as shown in the workspace image below, I am seeing the "Create Model" page with information about codewriter included.
Workspace
There is one problem: please note the Base Model (From) list in the page. Without a base model, I cannot add the codewriter model (or any model).; The problem is, of course, that there are no base models in that list. There appears to be no known way to include a base model because it is a list.
Of course, I then decided to "import" the model. I return to the WebUI Community page, and click on the Get button, and this time I click on the Download as JSON link. I save codewriter to a JSON file, then retun to my Workspace page on WebUI and click on the "imoport Models" link. I actually succeed in installing the model.
But then, when I try to use the model, I get the following failure:
I am getting the same behavior regardless of the model I select.
Bug Summary:
The Open WebUI is incapable of adding new models, and its import of models has something wrong in the JSON.
Reproduction Details
Steps to Reproduce:
@peuportier commented on GitHub (Sep 14, 2024):
Hello @factor3 You might first go terminal or command prompt . then run Ollama pull llama3.1:70b or direct from model place Admin - Model - Check if you can pull model here.