Spaces:
Sleeping
Sleeping
File size: 2,361 Bytes
ff6c924 ca1537a ff6c924 2ca051d 2e4368d ff6c924 2e4368d 2ca051d 2e4368d ff6c924 ca1537a 2e4368d ca1537a 2e4368d ca1537a 2e4368d ca1537a 2e4368d ca1537a 2e4368d ca1537a ff6c924 ca1537a 2ca051d ff6c924 2e4368d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
import os
import faiss
import pickle
import numpy as np
import re
from sentence_transformers import SentenceTransformer
from transformers import AutoTokenizer, pipeline
from huggingface_hub import InferenceClient
# Token Hugging Face depuis les secrets (Space)
HF_TOKEN = os.environ.get("edup2")
use_client = False
# Tentative de chargement de Mistral
try:
if HF_TOKEN:
MODEL_NAME = "mistralai/Mistral-7B-Instruct-v0.1"
client = InferenceClient(MODEL_NAME, token=HF_TOKEN)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, token=HF_TOKEN)
use_client = True
else:
raise ValueError("Pas de token trouvé pour Mistral.")
except Exception as e:
print(f"⚠️ Impossible de charger Mistral : {e}")
MODEL_NAME = "google/flan-t5-base"
generator = pipeline("text2text-generation", model=MODEL_NAME)
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
use_client = False
# Chargement de l’index FAISS et des documents
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
# Modèle d’embedding
def get_embedding_model():
return SentenceTransformer("sentence-transformers/multi-qa-MiniLM-L6-cos-v1")
# Recherche dans l’index
def query_index(question, index, documents, model, k=3):
question_embedding = model.encode([question])
_, indices = index.search(np.array(question_embedding).astype("float32"), k)
return [documents[i] for i in indices[0]]
# Nettoyage du contexte
def nettoyer_context(context):
context = re.sub(r"\[\'(.*?)\'\]", r"\1", context)
context = context.replace("None", "")
return context
# Génération de la réponse
def generate_answer(question, context):
prompt = f"""Voici des informations sur des établissements et formations :
{context}
Formule ta réponse comme un conseiller d’orientation bienveillant, de manière fluide et naturelle.
Question : {question}
Réponse :"""
if use_client:
response = client.text_generation(prompt=prompt, max_new_tokens=300, timeout=30)
return response
else:
result = generator(prompt, max_new_tokens=256, do_sample=True)
return result[0]["generated_text"]
|