-
Notifications
You must be signed in to change notification settings - Fork 284
Open
Description
System Info
In https://github.com/predibase/lorax/tree/main/clients/python#predibase-inference-endpoints
shouldn't the endpoint_url be updated?
Instead of
endpoint_url = f"https://api.app.predibase.com/v1/llms/{llm_deployment_name}"
shouldn't it be as mentioned in
https://loraexchange.ai/reference/python_client/#predibase-inference-endpoints
# You can get your Predibase API token by going to Settings > My Profile > Generate API Token
# You can get your Predibase Tenant short code by going to Settings > My Profile > Overview > Tenant ID
endpoint_url = f"https://serving.app.predibase.com/{predibase_tenant_short_code}/deployments/v2/llms/{llm_deployment_name}"
pypi release with this update would then reflect in https://pypi.org/project/lorax-client/
Information
- Docker
- The CLI directly
Tasks
- An officially supported command
- My own modifications
Reproduction
This is a README.md bug
Expected behavior
In clients/python/README.md (section: Predibase Inference Endpoints),
endpoint_url should be updated to
# You can get your Predibase API token by going to Settings > My Profile > Generate API Token
# You can get your Predibase Tenant short code by going to Settings > My Profile > Overview > Tenant ID
endpoint_url = f"https://serving.app.predibase.com/{predibase_tenant_short_code}/deployments/v2/llms/{llm_deployment_name}"
Metadata
Metadata
Assignees
Labels
No labels