vllm_inference.sh

#!/bin/bash


curl http://10.16.5.2:8000/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "ckpts/OmniSQL-7B",
        "messages": [{"role": "user", "content": "Task Overview:\nYou are a data science expert. Below, you are provided with a database schema and a natural language question. Your task is to understand the schema and generate a valid SQL query to answer the question.\n\nDatabase Engine:\nSQLite\n\nDatabase Schema:\nTable: cards(id, name, language, translation, baseSetSize)\n\nQuestion:\nAmong the sets of cards that have an Italian translation, how many of them have a base set number of under 100?\n\nInstructions:\n- Make sure you only output the information that is asked in the question. If the question asks for a specific column, make sure to only include that column in the SELECT clause, nothing more.\n- The generated query should return all of the information asked in the question without any missing or extra information.\n- Before generating the final SQL query, please think through the steps of how to write the query.\n\nOutput Format:\nIn your answer, please enclose the generated SQL query in a code block:\n```sql\n-- Your SQL query\n```\n\nTake a deep breath and think step by step to find the correct SQL query."}],
        "max_tokens": 1024,
        "temperature": 0
    }'