Instructions to use juierror/flan-t5-text2sql-with-schema-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use juierror/flan-t5-text2sql-with-schema-v2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="juierror/flan-t5-text2sql-with-schema-v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("juierror/flan-t5-text2sql-with-schema-v2")
model = AutoModelForSeq2SeqLM.from_pretrained("juierror/flan-t5-text2sql-with-schema-v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use juierror/flan-t5-text2sql-with-schema-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "juierror/flan-t5-text2sql-with-schema-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "juierror/flan-t5-text2sql-with-schema-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/juierror/flan-t5-text2sql-with-schema-v2

SGLang

How to use juierror/flan-t5-text2sql-with-schema-v2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "juierror/flan-t5-text2sql-with-schema-v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "juierror/flan-t5-text2sql-with-schema-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "juierror/flan-t5-text2sql-with-schema-v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "juierror/flan-t5-text2sql-with-schema-v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use juierror/flan-t5-text2sql-with-schema-v2 with Docker Model Runner:
```
docker model run hf.co/juierror/flan-t5-text2sql-with-schema-v2
```

The results are a little off.

by moon-cake22 - opened Aug 2, 2023

Discussion

moon-cake22

Aug 2, 2023

I tried it with this input "convert question and table into SQL query. tables: student_name(id,name), student_age(student_id,age). question: how many students with name jui and age less than 25"

I get "SELECT count(*) FROM student_name WHERE name = 'jui' AND age < 25". I just renamed the input parameters, didn't change the overall structure of the tables.

juierror

Owner Aug 3, 2023

@moon-cake22 Thank you very much for the testing.

I notice this point as well. The current result is not good for some type of table. I will try to improve it further.

temiwale88

Aug 17, 2023

@juierror . Could you please provide scripts for how you're finetuning this model? Thanks!

juierror

Owner Aug 21, 2023

@temiwale88

Sorry for late reply, here is the code

https://github.com/juierror/flan-t5-text-to-sql/blob/main/flan_t5_text2sql_multi_table.ipynb

temiwale88

Aug 22, 2023

Thank you!

tordbb

Aug 22, 2023

Thanks for letting us play around with the model. Here is another prompt that came out wrong, if you want more training material:

print(inference(
"Among the artists having concerts in year 2020, which artist has a song whose title equals the name of the stadium on which the concert takes place?",
{
"stadium": ["stadium_id", "location", "name", "capacity", "highest", "lowest", "average"],
"singer": ["singer_id", "name", "country", "song_name"],
"concert": ["concert_id", "stadium_id", "year"],
"singer_in_concert": ["concert_id", "singer_id"]
}))

Returned (which would not work):

SELECT T1.song_name
FROM singer AS T1
JOIN concert AS T2 ON T1.singer_id = T2.singer_id
WHERE T2.year = 2020
AND T1.stadium_id = (
SELECT stadium_id FROM concert WHERE YEAR = 2020
)

juierror

Owner Aug 23, 2023

@tordbb Thank you very much.

Kushrjain

Oct 4, 2023

@juierror Have you retrained the model to reduce the error queries as mentioned by other users? Where can I find the new model?

juierror

Owner Oct 4, 2023

@Kushrjain

To be frank, I still did not have a time to retrain the model. The current model is still not updated.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment