-
Notifications
You must be signed in to change notification settings - Fork 149
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
Update client docs with new endpoint source #126
Conversation
docs/reference/python_client.md
Outdated
@@ -67,7 +67,7 @@ Example: | |||
```python | |||
from lorax import Client | |||
|
|||
endpoint_url = f"https://api.app.predibase.com/v1/llms/{llm_deployment_name}" | |||
endpoint_url = f"https://serving.app.predibase.com/{predibase_tenant_id}/llm/llm-deployment-{llm_deployment_name}/generate" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we remove the llm-deployment-
when resolving the URL in the backend - we would need to update the VS for this too.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
+1, less verbose the better.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you also explain how to obtain the tenant ID?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Also, we need to use /
endpoint, not /generate
.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
updated with information on the tenant short code. I'll need to update the VS to add /
as a supported route
@@ -155,7 +155,9 @@ def generate( | |||
payload = resp.json() | |||
if resp.status_code != 200: | |||
raise parse_error(resp.status_code, payload) | |||
return Response(**payload[0]) | |||
if isinstance(payload, list): | |||
return Response(**payload[0]) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This smells like bad design IMO. The REST API should be consistent and predictable. We should not be writing client-side hacks to account for inconsistency in the REST API.
No description provided.