rag_utils.py

import faiss
import pickle
from sentence_transformers import SentenceTransformer
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
import torch
import numpy as np

def load_faiss_index(index_path="faiss_index/faiss_index.faiss", doc_path="faiss_index/documents.pkl"):
    index = faiss.read_index(index_path)
    with open(doc_path, "rb") as f:
        documents = pickle.load(f)
    return index, documents

def get_embedding_model():
    return SentenceTransformer("all-MiniLM-L6-v2")

def query_index(question, index, documents, model, k=3):
    question_embedding = model.encode([question])
    _, indices = index.search(np.array(question_embedding).astype("float32"), k)
    results = [documents[i] for i in indices[0]]
    return results

def generate_answer(question, context):
    model_id = "mistralai/Mistral-7B-Instruct-v0.1"
    tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
    prompt = f"Voici un contexte :\n{context}\n\nQuestion : {question}\nRéponse :"
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=256)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)