-
-
Notifications
You must be signed in to change notification settings - Fork 1.6k
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
[FEAT]: Add a "SQL Talk Agent" #1298
Comments
to have a feature like this would be great! We need something like this |
Are long-running persisted operations supported at all? If the agent is performing a task that takes more than a few minutes, will it survive if say, the user closes the HTTP connection or the server is shutdown and then is restarted for some reason. |
@nileshtrivedi no, if the client closes the connection while the agent is doing something it halts the agent to prevent runaway llms. If you kill/reboot the server there there is absolutely no way for it to continue for sure. It is not a cron so it would not continue on reboot. |
to have a feature like this would be great! We need something like this |
I agree as well 👍🏻 |
What would you like to see?
Add a new data agent, to interact with datasets in AWS, GCP, local and others.
This new agent needs to have at least 4 function callings:
list_datasets
: Get a list of datasets that will help answer the user's questionlist_tables
: List tables in a dataset that will help answer the user's questionget_table
: Get information about a table, including the description, schema, and number of rows that will help answer the user's question. Always use the fully qualified dataset and table names.sql_query
: Get information from data in BigQuery using SQL queriesthe user should be able to add an API Key for the cloud service, and the source for the dataset in Google Cloud BigQuery or AWS Athena, etc
gemini example: https://github.com/GoogleCloudPlatform/generative-ai/blob/main/gemini/function-calling/sql-talk-app/app.py
example: https://youtu.be/pj5mRDy9lG8
The text was updated successfully, but these errors were encountered: