sappuff/text2sql-t5

1import torch2from transformers import T5Tokenizer, T5ForConditionalGeneration3import gradio as gr4 5# Initialize the tokenizer from Hugging Face Transformers library6tokenizer = T5Tokenizer.from_pretrained('t5-small')7 8# Load the model9device = torch.device("cuda" if torch.cuda.is_available() else "cpu")10model = T5ForConditionalGeneration.from_pretrained('cssupport/t5-small-awesome-text-to-sql')11model = model.to(device)12model.eval()13 14def generate_sql(input_prompt):15    # Tokenize the input prompt16    inputs = tokenizer(input_prompt, padding=True, truncation=True, return_tensors="pt").to(device)17    18    # Forward pass19    with torch.no_grad():20        outputs = model.generate(**inputs, max_length=512)21    22    # Decode the output IDs to a string (SQL query in this case)23    generated_sql = tokenizer.decode(outputs[0], skip_special_tokens=True)24    25    return generated_sql26 27# Test the function28#input_prompt = "tables:\n" + "CREATE TABLE Catalogs (date_of_latest_revision VARCHAR)" + "\n" +"query for: Find the dates on which more than one revisions were made."29#input_prompt = "tables:\n" + "CREATE TABLE table_22767 ( \"Year\" real, \"World\" real, \"Asia\" text, \"Africa\" text, \"Europe\" text, \"Latin America/Caribbean\" text, \"Northern America\" text, \"Oceania\" text )" + "\n" +"query for:what will the population of Asia be when Latin America/Caribbean is 783 (7.5%)?."30#input_prompt = "tables:\n" + "CREATE TABLE procedures ( subject_id text, hadm_id text, icd9_code text, short_title text, long_title text ) CREATE TABLE diagnoses ( subject_id text, hadm_id text, icd9_code text, short_title text, long_title text ) CREATE TABLE lab ( subject_id text, hadm_id text, itemid text, charttime text, flag text, value_unit text, label text, fluid text ) CREATE TABLE demographic ( subject_id text, hadm_id text, name text, marital_status text, age text, dob text, gender text, language text, religion text, admission_type text, days_stay text, insurance text, ethnicity text, expire_flag text, admission_location text, discharge_location text, diagnosis text, dod text, dob_year text, dod_year text, admittime text, dischtime text, admityear text ) CREATE TABLE prescriptions ( subject_id text, hadm_id text, icustay_id text, drug_type text, drug text, formulary_drug_cd text, route text, drug_dose text )" + "\n" +"query for:" + "what is the total number of patients who were diagnosed with icd9 code 2254?"31#input_prompt = "tables:\n" + "CREATE TABLE student_course_attendance (student_id VARCHAR); CREATE TABLE students (student_id VARCHAR)" + "\n" + "query for:" + "List the id of students who never attends courses?"32 33#generated_sql = generate_sql(input_prompt)34 35#print(f"The generated SQL query is: {generated_sql}")36#OUTPUT: The generated SQL query is: SELECT student_id FROM students WHERE NOT student_id IN (SELECT student_id FROM student_course_attendance)37 38def launch(input):39    generated_sql = generate_sql(input)40    return generated_sql41 42iface = gr.Interface(launch,43                    inputs="text",44                    outputs="text")45iface.launch(share=True)