Runtime error during local development

[dmwelgus]

I'm seeing the following runtime error when I try to run the extension locally:

I think it might be an issue with how the examples were loaded to Big Query. Is explore_assistant_examples supposed to have a separate row for each example (i.e. {'input': ..., 'output': ...}) or is it supposed to have a single row with the examples packed into an array (e.g. [{'input': ..., 'output': ...}, {'input': ..., 'output': ...}]).

[dmwelgus]

Nevermind. The issue was that I didn't have any examples loaded into explore_assistant_refinement_examples. It's working now

[arodriguezd]

Hi, I have the same problem, I have deployed a GCP instance for the frontend and we are using BigQuery as backend the backend deployment was made with the example found in the repository.
All in the same project. The Bigquery API has been enabled at the instance level. On the other hand the nginx has been installed, to perform proxy with the application.

Also take down the examples in the bigquery.

charge the capture of one of the examples.

Thanks in advance for any help.

[cavvia]

I also got this error with the BigQuery backend. In my case I verified via BigQuery Studio that both example tables are loaded with data (using the script provided). The BigQuery connection was also working fine.

On the BigQuery side, I can see requests coming in via the logging console but no errors. However, when looking at the query traces, I could see the query using a WHERE explore="model:explore" syntax in its constraint. This was unexpected and should be documented in the examples script documentation. Those scripts take a --explore_id arg which should actually be populated with a model:explore syntax in order for this to work. After re-running those scripts with the correct explore_id the error cleared.

[LukaFontanilla]

@cavvia there will be some documentation updates coming soon that will cover unclear instructions like the proper format the explore_id.