Skip to content
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.

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

H2ogpt openai endpoints #1849

Closed
CommitAndPray opened this issue Sep 18, 2024 · 5 comments
Closed

H2ogpt openai endpoints #1849

CommitAndPray opened this issue Sep 18, 2024 · 5 comments

Comments

@CommitAndPray
Copy link

Hi, can someone explain how I can test these endpoints? I keep getting the same error as shown in the screenshot. If I need to get a key, how can I obtain it?
image
image

@pseudotensor
Copy link
Collaborator

OpenAI endpoints are on port 5000 by default.

@CommitAndPray
Copy link
Author

Thank you for responding. Do I need an API key to test the endpoints, or can I just set the api_key to empty

@pseudotensor
Copy link
Collaborator

EMPTY is default. You can set the key, like I showed in the FAQ for how to setup gpt.h2o.ai

### Deploying like gpt.h2o.ai

@CommitAndPray
Copy link
Author

Thank you, I can now test H2O GPT on Open Web UI. My question is: will it use the documents I have already uploaded to H2O GPT, or will it follow the RAG process and parameters of Open Web UI? Does it interact with the files in my vector database?

@pseudotensor
Copy link
Collaborator

The database is separate. On the backend operations would use h2oGPT except for the database.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants