Expected inputs Azure ML Studio
Hi, I've imported your model in Azure ML Studio and then deployed it to an endpoint. Now I would like to use this endpoint but I can't figure out what the input should look like. Could you help me with this please ?
Thanks
Hi there, please use the recommended prompt on Github, where table_metadata_string is your tables DDL statements with comments about column descriptions, like here
### Task
Generate a SQL query to answer [QUESTION]{user_question}[/QUESTION]
### Instructions
- If you cannot answer the question with the available database schema, return 'I do not know'
### Database Schema
The query will run on a database with the following schema:
{table_metadata_string}
### Answer
Given the database schema, here is the SQL query that answers [QUESTION]{user_question}[/QUESTION]
[SQL]
Hi, yes I've been trying to send this to the endpoint but I don't know the expected format of the input.
From the screenshot bellow you can see that we're expecting to pass a JSON object with the attribute 'input_data' (this causes no error when running and I get an empty response)
But then I don't know how to provide the prompt, here's an example of what I've tried and the error I get:
And the resulting error in the logs of the endpoint where the model was deployed:
My question would be: what's the expected name of the key instead of where I've chosen 'question' ? And what should be the type of the value associated to this key ?