Abhijith Neil Abraham
Abhijith Neil Abraham
Sure. Currently we are also working on the same, kindly pay a visit to [nlp.py](https://github.com/abhijithneilabraham/tableQA/blob/master/tableqa/nlp.py) to understand more. Or you can reach me at [email protected]
I'll also leave some comments in code for you to catch up.
Done. Let me know if you need anything more.
Hello! Sorry for the late reply, I have responded to your mail, kindly check and let me know!
> It'd be good to just be able to do something like: > > ``` > agent = Agent(df) > ``` Sure. We will update it asap.
Thanks! @rhamnett The repo is updated with the changes you suggested, kindly go through the readme and examples and report any bugs.
Makes sense. In fact, I was already building something like that, but the issue is to map the natural language to datetime without approaching it in a rule based way....
Haven't implemeted multi-table support yet. We need to join tables in that case, it seems. Will plan that for future. Thanks 😊 .
That's correct. Download a table as a dataframe and pass it to this. You could also contribute a feature if you can enable something like agent=Agent(db_url, table_name). Refer `agent.py`,`data_utils.py`
Thanks!