Update app.py

app.py

@@ -25,7 +25,7 @@ Your primary knowledge source is an internal 350-entry complaint and resolution
 
 You have access to the following information:
 1. Short-term chat history between you and the user.
-2. Retrieved context chunks from the internal complaint database.
+2. Retrieved context chunks from the internal complaint database and any uploaded datasets.
 
 You must:
 - Use the chat history to maintain context across turns.
@@ -74,6 +74,31 @@ def load_store():
     )
     return FAISS.load_local(str(DB_DIR), embeddings, allow_dangerous_deserialization=True)
 
+def build_store_from_upload(uploaded_file):
+    uploads_dir = Path("uploads")
+    uploads_dir.mkdir(exist_ok=True)
+    temp_path = uploads_dir / "user_dataset.pdf"
+    with open(temp_path, "wb") as f:
+        f.write(uploaded_file.getbuffer())
+
+    loader = PyPDFLoader(str(temp_path))
+    docs = loader.load()
+
+    splitter = RecursiveCharacterTextSplitter(
+        chunk_size=800,
+        chunk_overlap=150,
+        separators=["\n\n", "\n", " ", ""]
+    )
+    chunks = splitter.split_documents(docs)
+
+    embeddings = GoogleGenerativeAIEmbeddings(
+        model="models/text-embedding-004",
+        google_api_key=GOOGLE_API
+    )
+
+    vectorstore = FAISS.from_documents(chunks, embeddings)
+    return vectorstore
+
 def format_history(history, max_turns: int = 5) -> str:
     if not history:
         return "[No prior conversation]"
@@ -84,9 +109,12 @@ def format_history(history, max_turns: int = 5) -> str:
         lines.append(f"Assistant: {turn['assistant']}")
     return "\n".join(lines)
 
-def answer_query(query, history):
-    vectorstore = load_store()
-    docs = vectorstore.similarity_search(query, k=5)
+def answer_query(query, history, user_vectorstore=None):
+    base_store = load_store()
+    docs = base_store.similarity_search(query, k=5)
+    if user_vectorstore is not None:
+        user_docs = user_vectorstore.similarity_search(query, k=5)
+        docs = user_docs + docs
 
     context = "\n\n---\n\n".join([d.page_content for d in docs]) if docs else "[No matching context]"
     history_text = format_history(history)
@@ -113,12 +141,27 @@ st.title("🔋 EV Service Expert — RAG Chatbot")
 
 if "chat_history" not in st.session_state:
     st.session_state.chat_history = []
-
-if not DB_DIR.exists():
-    st.warning("Vector store missing. Click the button below to build it.")
-    if st.button("Build Vector Store"):
-        with st.spinner("Building vector store..."):
-            build_store()
+if "user_vectorstore" not in st.session_state:
+    st.session_state.user_vectorstore = None
+
+col1, col2 = st.columns(2)
+
+with col1:
+    if not DB_DIR.exists():
+        st.warning("Vector store missing. Click the button below to build it from 350_QA_dataset.pdf.")
+        if st.button("Build Default Vector Store"):
+            with st.spinner("Building vector store from internal dataset..."):
+                build_store()
+    else:
+        st.success("✅ Default EV knowledge base loaded.")
+
+with col2:
+    uploaded_file = st.file_uploader("Upload additional EV PDF dataset", type=["pdf"])
+    if uploaded_file is not None:
+        if st.button("Build Vector Store From Upload"):
+            with st.spinner("Building vector store from uploaded dataset..."):
+                st.session_state.user_vectorstore = build_store_from_upload(uploaded_file)
+            st.success("✅ Uploaded dataset vector store ready and will be used in answers.")
 
 st.markdown("### 💬 Conversation")
 for turn in st.session_state.chat_history:
@@ -134,7 +177,7 @@ if user_input:
         st.write(user_input)
     with st.chat_message("assistant"):
         with st.spinner("Searching knowledge base..."):
-            answer = answer_query(user_input, st.session_state.chat_history)
+            answer = answer_query(user_input, st.session_state.chat_history, st.session_state.user_vectorstore)
             st.write(answer)
     st.session_state.chat_history.append(
         {"user": user_input, "assistant": answer}