10000 How can I integrate a new OpenAI-like API or an Ollama-specific one into this tool · Issue #1 · otto8-ai/otto8 · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

How can I integrate a new OpenAI-like API or an Ollama-specific one into this tool #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
ymolists opened this issue Jan 27, 2025 · 3 comments
Open

How can I integrate a new OpenAI-like API or an Ollama-specific one into this tool #1

ymolists opened this issue Jan 27, 2025 · 3 comments

Comments

@ymolists
Copy link

First We truly appreciate all the contributions and efforts from everyone involved in making this project successful and open sourcing it

In which part of this repository should I integrate a new OpenAI-like API or an Ollama-specific one? Are there existing modules or files where such APIs are typically added, and what considerations should be taken into account during integration?

Regards
@avoidik
Copy link
avoidik commented Jan 28, 2025

This is the wrapper around the obot framework. With minor adjustments you may configure these models - https://docs.obot.ai/configuration/model-providers

@iwilltry42
Copy link

model-providers are just tools that will be invoked in a specific way.
For OpenAI-like APIs we have a common proxy abstraction in the openai-model-provider.
All open model-providers are defined in our tools repository: https://github.com/obot-platform/tools

FYI: I'll be adding a generic OpenAI-like provider today or tomorrow.

You can configure model-providers through the Obot/Otto8 admin interface.

@ymolists
Copy link
Author
ymolists commented Jan 28, 2025 •
edited
Loading

Thank you all for your input! 😊

I reviewed the ollama-model-provider and couldn't determine how a specific model is chosen when invoking ollama. Is this feature currently supported, or could it be added in the future?

Tbc when I mention "adding" a feature, I'm referring specifically to making it simple to choose a model directly through the UI. While I could set up an environment variable and hardcode the selection, I believe providing this capability via the user interface would be more seamless for users

Regards

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@avoidik @ymolists @iwilltry42
0