feat: add document retrieval functionality and display in chatbot interface

app.py

@@ -22,6 +22,7 @@ def init_app():
         pinecone_connector = PineconeConnector()
         vs_manager = VectoreStoreManager(pinecone_connector)
 
+        st.session_state["retrived_documents"] = []
         st.session_state["messages"] = []
         st.session_state["assistant"] = Rag(vectore_store=vs_manager)
         st.session_state["data_dict"] = config['variables']

pages/chatbot.py

@@ -14,11 +14,26 @@ def display_messages():
                 st.write(f"**Model :** {model}")
                 st.markdown(message.content)
                 st_copy_to_clipboard(message.content,key=f"message_{i}")
+                show_retrieved_documents(st.session_state.chat_history[i-1].content)
         
         elif isinstance(message, HumanMessage):
             with st.chat_message("Moi"):
                 st.write(message.content)
 
+def show_retrieved_documents(query: str = ''):
+    if query == '':
+        return
+    
+    # Créer l'expander pour les documents trouvés
+    expander = st.expander("Documents trouvés")
+    
+    # Boucler à travers les documents récupérés
+    for item in st.session_state.get("retrived_documents", []):
+        if 'query' in item:
+            if item["query"] == query:
+                for doc in item.get("documents", []):
+                    expander.write(doc)
+
 
 def launchQuery(query: str = None):
 

rag.py

@@ -1,5 +1,6 @@
 import os
 
+import streamlit as st
 from dotenv import load_dotenv
 from langchain_community.vectorstores import FAISS
 from langchain_mistralai.chat_models import ChatMistralAI
@@ -89,6 +90,8 @@ class Rag:
         # Retrieve the VectoreStore
         contextCommon = self.vector_store.retriever(query, self.embedding)
 
+        st.session_state["retrived_documents"].append({ "query": query, "documents": contextCommon })
+
         # Dictionnaire de base avec les variables principales
         chain_input = {
             "query": query,