Repository files navigation

• installdocker
• installcurl (or, if you're feeling brave,asql)
• Make sure docker allows at least 3GB of RAM (seeDocker>Preferences>Advancedor equivalent) for SQLova, or 5GB for IRNet or ValueNet.

I take pretrained models published along with academic papers, and do whatever it takesto make them testable on fresh data (academic work often omits that, with code tiedto a particular benchmark dataset). I spend days tracking down and patching obscuredata preprocessing steps so you don't have to.

So far I've packaged three models:

• SQLova. Works on single tables.
• ValueNet. Works on multiple tables, andmakes an effort to predict parameters.
• IRNet. Works on multiple tables, but doesn'tpredict parameters.

In each case, I've mangled the original network somewhat, so if they interest you do follow upwith the original sources.

This wraps up a published pretrained model for SQLova (https://github.com/naver/sqlova/).

Fetch and start SQLova running as an api server on port 5050:

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

Be patient, the image is about 4.2GB. Once it is running, it'll take a few secondsto load models and then you can start asking questions about CSV tables. For example:

curl -F "csv=@bridges.csv" -F "q=how long is throgs neck" localhost:5050# {"answer":[1800],"params":["throgs neck"],"sql":"SELECT (length) FROM bridges WHERE bridge = ?"}

This is using the samplebridges.csv included in this repo.

Here are some examples of the answers and sql inferred for plain-text questions aboutthis table:

With theplayers.csv sample from WikiSQL:

Some questions aboutiris.csv:

There are plenty of types of questions this model cannot answer (and that aren't coveredin the dataset it is trained on, or in the sql it is permitted to generate).

This wraps up a published pretrained model for ValueNet (https://github.com/brunnurs/valuenet).

Fetch and start ValueNet running as an api server on port 5050:

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

You can then ask questions of individual csv files as before, or several csv files(just repeat-F "csv=@fileN.csv") or a simple sqlite db with tables related by foreign keys.In this last case, the model can answer using joins.

curl -F "sqlite=@companies.sqlite" -F "q=who is the CEO of Omni Cooperative" localhost:5050# {"answer":[["Dracula"]], "sql":"SELECT T1.name FROM people AS T1 JOIN organizations AS T2 \#   ON T1.id = T2.ceo_id WHERE T2.company = 'Omni Cooperative'"}curl -F "csv=@bridges.csv" -F "q=how many designers are there?" localhost:5050# {"answer":[[5]],"sql":"SELECT DISTINCT count(DISTINCT T1.designer) FROM bridges AS T1"}curl -F "csv=@bridges.csv" -F "csv=@airports.csv" -F "q=how many designers are there?" localhost:5050# same answercurl -F "csv=@bridges.csv" -F "csv=@airports.csv" -F "q=what is the name of the airport with the highest latitude?" localhost:5050# {"answer":[["Disraeli Inlet Water Aerodrome"]],#  "sql":"SELECT T1.name FROM airports AS T1 ORDER BY T1.latitude_deg DESC LIMIT 1"}

I've includes material to convert user tables into the form needed to query them. Don'tjudge the network by its quality here, go do a deep dive with the original - I've deviatedfrom the original in important respects, including how named entity recognition is done.

I've written upsome experiments with ValueNet.

This wraps up a published pretrained model for IRNet (https://github.com/microsoft/IRNet).Upstream released a better model after I packaged this, so don't judge the model by playingwith it here.

Fetch and start IRNet running as an api server on port 5050:

docker run --name irnet -d -p 5050:5050 -v $PWD/cache:/cache paulfitz/irnet

Be super patient! Especially on the first run, when a few large models need tobe downloaded and unpacked.

You can then ask questions of individual csv files as before, or several csv files(just repeat-F "csv=@fileN.csv") or a simple sqlite db with tables related by foreign keys.In this last case, the model can answer using joins.

curl -F "sqlite=@companies.sqlite" -F "q=what city is The Firm headquartered in?" localhost:5050# Answer: SELECT T1.city FROM locations AS T1 JOIN organizations AS T2 WHERE T2.company = 1curl -F "sqlite=@companies.sqlite" -F "q=who is the CEO of Omni Cooperative" localhost:5050# Answer: SELECT T1.name FROM people AS T1 JOIN organizations AS T2 WHERE T2.company = 1curl -F "sqlite=@companies.sqlite" -F "q=what company has Dracula as CEO" localhost:5050# Answer: SELECT T1.company FROM organizations AS T1 JOIN people AS T2 WHERE T2.name = 1

(Note there's no value prediction, so e.g. the where clauses are= 1 rather than somethingmore useful).

Curl can be replaced by Postman for those who like that. Here's a working set-up:

I hope to track research in the area and substitute in models as they become available:

• Spider leaderboard

• WikiSQL leaderboard

• SparC leaderboard

• RAT-SQL

• Photon by the SalesForce group is a good live demo oftext-to-SQL.