paulfitz / mlsql Goto Github PK

Hi,

1. Can you please tell me where you are converting the SQL query to the answer inside the dataset?
2. Can I use your edited predict.py file to generate sql and answers?

Thanks
Bill

Hi,

How to finetune the model with custom queries, tables in .csv and with SQL queries ?
Thank you in advance.

I have implemented it and used it and now I can get all the answers, but when I try the same on my custom csv file, it generates the query but doesn't "answer" for the query as it did to your csv files. May I know the reason?
and What is this params thing? I don't understand why not keeps the params in the query?

https://github.com/guotong1988/NL2SQL-BERT

I got an error while running the program.
What could be the cause?

input:
curl -F "[email protected]" -F "q=Is the accuracy of the algorithm gloom in the dataset chaos smaller than the accuracy of the algorithm brave in the dataset tooth?" localhost:5050
error:
{"error":"invalid argument 0: Sizes of tensors must match except in dimension 2. Got 3 and 4 in dimension 1 at /Users/soumith/code/builder/wheel/pytorch-src/aten/src/TH/generic/THTensorMath.cpp:3616"}

Hi,

How to run in local environment without using docker?

also, I want to import a natural language sentence into a program and get the arithmetic value and the nth value.
Can you tell me how?

Thank you in advance.

Everything works fine with curl.
But when i am using requests.post() in python
it works for the first time but fails in the second time and so on.
I have to change the name of the parameter

import requests
url = 'http://localhost:5050'
path = 'bridges.csv'
csv = {'csv' : open(path ,'rb')}
payload = {'debug' : False, 'q' : 'how long is throgs neck'}
r =  requests.post(url = url ,files=csv,data=payload)
r.json() > this works for the first time but fails afterwards 

#Second time failed output
r.text > u'{"base":"bridges_b884af26-ef36-4876-9d01-469044242365","error":"object of type \'NoneType\' has no len()"}\n'
r.status_code > 500

#if i do csv1 = {'csv' : open(path ,'rb')} # CHANGED THE NAME OF csv to csv1(or anyother) it works fine again
r =  requests.post(url = url ,files=csv1,data=payload)

Anybody knows the reason?

{
"error": "'utf-8' codec can't decode byte 0xc9 in position 602: invalid continuation byte"
}

The datasets like WikiSQL is that the table corresponding to question is given.

But in real industrial application, we have 100+ tables for 1 new question.

Thank you!

select col1, col2
from ...

is this type of query supported?

rdkit https://github.com/rdkit/rdkit

Hi,

as I am trying to run valuenet on my own examples, I am blocked at generating the "sqlite" format.

Here are the details.

Valuenet keeps the spider dat a in the directory valuenet/data/spider/original/database/

here , for each schema you have a directory, like "concert_singer", which contains two file:
"schema.sql" - the sql creation of the table and insertt values

and

"concert_singer.sqlite" which apparently contains the database and it is the file read by valuenet in order to execute
db_value_finder.find_similar_values_in_database

I would greatly appreciate if you could tell me how to generate the sqlite file form the "schema.sql" file , or anything will do.

Thank you

As 5050 port is already ON. How can I send and receive data using postman?

I used the following as given, however i do not get the expected results. Where do you think is the error, please help.

docker run --name sqlova -d -p 5050:5050 paulfitz/sqlova

\mlsql-master>curl -F "[email protected]" -F "q=how long is throgs neck" localhost:5050
curl: (52) Empty reply from server