You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Getting this error in new versions of RAG app. Please let me know how to fix this error.
Background:
I have created a RAG app using Databricks Mosaic AI Agent and was able to ask questions and got responses. I wanted to modify the prompts and create new version. But, every time I create a new version, I get the same error message in the new chatbot application (not able to ask questions in new versions).
I create new version means, I deployed the model to create a new API endpoint using the below code:
from databricks import agents
#Register the chain to UC
uc_registered_model_info = mlflow.register_model(model_uri=logged_chain_info.model_uri, name=MODEL_NAME_FQN)
#Deploy to enable the Review APP and create an API endpoint
deployment_info = agents.deploy(model_name=MODEL_NAME_FQN, model_version=uc_registered_model_info.version, scale_to_zero=True)
instructions_to_reviewer = f"""### Instructions for Testing ...
"""
#Add the user-facing instructions to the Review App
agents.set_review_instructions(MODEL_NAME_FQN, instructions_to_reviewer)
wait_for_model_serving_endpoint_to_be_ready(deployment_info.endpoint_name)
Thanks,
Naveen
The text was updated successfully, but these errors were encountered:
Hi,
Getting this error in new versions of RAG app. Please let me know how to fix this error.
Background:
I have created a RAG app using Databricks Mosaic AI Agent and was able to ask questions and got responses. I wanted to modify the prompts and create new version. But, every time I create a new version, I get the same error message in the new chatbot application (not able to ask questions in new versions).
I create new version means, I deployed the model to create a new API endpoint using the below code:
from databricks import agents
#Register the chain to UC
uc_registered_model_info = mlflow.register_model(model_uri=logged_chain_info.model_uri, name=MODEL_NAME_FQN)
#Deploy to enable the Review APP and create an API endpoint
deployment_info = agents.deploy(model_name=MODEL_NAME_FQN, model_version=uc_registered_model_info.version, scale_to_zero=True)
instructions_to_reviewer = f"""### Instructions for Testing ...
"""
#Add the user-facing instructions to the Review App
agents.set_review_instructions(MODEL_NAME_FQN, instructions_to_reviewer)
wait_for_model_serving_endpoint_to_be_ready(deployment_info.endpoint_name)
Thanks,
Naveen
The text was updated successfully, but these errors were encountered: