Originally created by @matheospower on GitHub (May 8, 2024).
Is your feature request related to a problem? Please describe.
I'm experimenting with various LLM pipelines and would like to use open-webui as the chat interface. To achieve this, I'd like to request a feature that allows connecting the chat interface to my custom pipeline API/endpoint.
Describe the solution you'd like
Ideally, I'd want to connect to my custom pipeline through an API by providing a URL (e.g., http://localhost:4217/) and a name for the assistant (e.g., "Custom Assistant"). The generated text would then be displayed in the chat UI.
Describe alternatives you've considered
I've attempted to simulate connections with my custom endpoint as an Ollama or OpenAI API, but haven't been successful so far. Guidance on what changes are required or a guide on creating a compatible custom API would be helpful.
Additional context
I've searched through GitHub issues and Discord channels but couldn't find an exact match for this request. If someone could provide guidance on how to proceed, I'd be happy to contribute to the solution.
Originally created by @matheospower on GitHub (May 8, 2024).
**Is your feature request related to a problem? Please describe.**
I'm experimenting with various LLM pipelines and would like to use open-webui as the chat interface. To achieve this, I'd like to request a feature that allows connecting the chat interface to my custom pipeline API/endpoint.
**Describe the solution you'd like**
Ideally, I'd want to connect to my custom pipeline through an API by providing a URL (e.g., http://localhost:4217/) and a name for the assistant (e.g., "Custom Assistant"). The generated text would then be displayed in the chat UI.
**Describe alternatives you've considered**
I've attempted to simulate connections with my custom endpoint as an Ollama or OpenAI API, but haven't been successful so far. Guidance on what changes are required or a guide on creating a compatible custom API would be helpful.
**Additional context**
I've searched through GitHub issues and Discord channels but couldn't find an exact match for this request. If someone could provide guidance on how to proceed, I'd be happy to contribute to the solution.
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 @matheospower on GitHub (May 8, 2024).
Is your feature request related to a problem? Please describe.
I'm experimenting with various LLM pipelines and would like to use open-webui as the chat interface. To achieve this, I'd like to request a feature that allows connecting the chat interface to my custom pipeline API/endpoint.
Describe the solution you'd like
Ideally, I'd want to connect to my custom pipeline through an API by providing a URL (e.g., http://localhost:4217/) and a name for the assistant (e.g., "Custom Assistant"). The generated text would then be displayed in the chat UI.
Describe alternatives you've considered
I've attempted to simulate connections with my custom endpoint as an Ollama or OpenAI API, but haven't been successful so far. Guidance on what changes are required or a guide on creating a compatible custom API would be helpful.
Additional context
I've searched through GitHub issues and Discord channels but couldn't find an exact match for this request. If someone could provide guidance on how to proceed, I'd be happy to contribute to the solution.