from huggingface_hub import hf_hub_download
from llama_cpp import Llama
model_path = hf_hub_download(
    repo_id="Tvisterious/Llama-3.1-8B-text-to-sql-10K-RussianDataset_Q6_K",
    filename="Llama-3.1-8B-text-to-sql-10K-RussianDataset_Q6_K.gguf",
    cache_dir="./models"
)
llm = Llama(
    model_path=model_path,
    n_ctx=1024,
    n_threads=8
)
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
        ### Instruction:
        SQL Prompt: {}
        ### Input:
        Company database: {}
        ### Response:
        SQL: {}
        """
response = llm(
    alpaca_prompt.format(
                "Сколько есть работников с красными машинами?", # instruction 'How many workers have red cars?'
                "T_Workers(worker_id, name, age, id_car), T_Cars(car_id, mark, type, color)", # input with DB context
                "", # output - leave this blank for generation!
                ),
    max_tokens=256,
    temperature=0.7
)
print(response['choices'][0]['text'])