Upload 7 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+faiss_index/faiss_index.faiss filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,37 @@
 ---
-title: Edu Pilot
-emoji: 🐠
-colorFrom: yellow
-colorTo: red
+pinned: false
+title: Edu P
+emoji: 🎓
+colorFrom: purple
+colorTo: blue
 sdk: streamlit
-sdk_version: 1.44.0
+sdk_version: 1.31.1
 app_file: app.py
-pinned: false
+
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+
+# Chatbot d'Orientation Scolaire (RAG + Mistral)
+
+Ce projet est un chatbot basé sur le modèle open-source Mistral 7B, utilisant un index FAISS pour récupérer les documents pertinents à partir d'une base de données, et générer des réponses contextualisées.
+
+## Lancer l'application
+
+1. Installe les dépendances :
+
+```
+pip install -r requirements.txt
+```
+
+2. Lance l'application Streamlit :
+
+```
+streamlit run app.py
+```
+
+## Structure
+
+- `app.py` : interface utilisateur
+- `rag_utils.py` : logique RAG
+- `faiss_index/` : index FAISS + documents associés

app.py

@@ -0,0 +1,41 @@
+import streamlit as st
+from rag_utils import load_faiss_index, get_embedding_model, query_index, generate_answer, nettoyer_context
+
+st.set_page_config(page_title="🎓 EduPilot", page_icon="🧠")
+st.title("🎓 EduPilot ")
+
+# Initialiser la mémoire de session
+if "chat_history" not in st.session_state:
+    st.session_state.chat_history = []
+
+# Chargement des données et du modèle d'embedding
+index, documents = load_faiss_index()
+model_embed = get_embedding_model()
+
+# Entrée utilisateur
+user_input = st.text_input("Pose ta question ici :")
+
+if user_input:
+    st.session_state.chat_history.append(f"Utilisateur : {user_input}")
+
+    # Recherche des documents
+    top_docs = query_index(user_input, index, documents, model_embed)
+    context = nettoyer_context("\n".join(top_docs))
+
+    # Ajouter les 6 derniers échanges comme contexte
+    history = "\n".join(st.session_state.chat_history[-6:])
+    full_prompt = f"{history}\n\nContexte :\n{context}"
+
+    # Génération de la réponse
+    response = generate_answer(user_input, full_prompt)
+    st.session_state.chat_history.append(f"Chatbot : {response}")
+
+    # Affichage
+    st.markdown("### ✨ Réponse du chatbot :")
+    st.write(response)
+
+    with st.expander("🧠 Historique de la conversation"):
+        for msg in st.session_state.chat_history:
+            st.write(msg)
+st.markdown("---")
+st.caption("🔹 Développé avec ❤️ par EduPilot")

faiss_index/documents.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc6100b51468166d2e0b5e0ca119f239e648cb5d539dd256dc886ef39f45f46
+size 36366182

faiss_index/faiss_index.faiss

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43efadcf8c063cedf2414c75df1dd801404c0ba263b0e35de8f21c25436d0694
+size 165167661

gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+faiss_index/faiss_index.faiss filter=lfs diff=lfs merge=lfs -text

rag_utils.py

@@ -0,0 +1,52 @@
+import faiss
+import pickle
+import numpy as np
+import re
+from sentence_transformers import SentenceTransformer
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+
+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("sentence-transformers/multi-qa-MiniLM-L6-cos-v1")
+
+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]]
+
+def nettoyer_context(context):
+    context = re.sub(r"\[\'(.*?)\'\]", r"\1", context)
+    context = context.replace("None", "")
+    return context
+
+def generate_answer(question, context):
+    model_file = hf_hub_download(
+        repo_id="TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
+        filename="mistral-7b-instruct-v0.1.Q4_K_M.gguf"
+    )
+
+    llm = Llama(
+        model_path=model_file,
+        n_ctx=2048,
+        n_threads=6,
+        verbose=False
+    )
+
+    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, sans énumérations brutes.
+
+Question : {question}
+Réponse :
+"""
+
+    output = llm(prompt, max_tokens=256, stop=["</s>"])
+    return output["choices"][0]["text"].strip()

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+faiss-cpu
+sentence-transformers
+llama-cpp-python
+huggingface_hub