Update app.py

app.py

@@ -1,26 +1,54 @@
 import gradio as gr
-import json
-from langchain_community.vectorstores import FAISS
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain.chains import ConversationalRetrievalChain
-from langchain.memory import ConversationBufferMemory
-from langchain_community.llms import HuggingFaceHub
-
-# --- Load local RAG pipeline (Flowise JSON) ---
-PIPELINE_PATH = "Chat1 Chatflow.json"
-with open(PIPELINE_PATH, "r") as f:
-    pipeline = json.load(f)
-
-# Dummy — you can later parse nodes from JSON to build chain dynamically
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
-llm = HuggingFaceHub(repo_id="mistralai/Mistral-7B-Instruct-v0.2", model_kwargs={"temperature": 0.0})
-vectorstore = FAISS.from_texts(["Prüfungsordnung PDF", "Hochschulgesetz NRW"], embedding=embeddings)
-qa_chain = ConversationalRetrievalChain.from_llm(llm, vectorstore.as_retriever(), memory=memory)
-
-def chat(message, history):
-    result = qa_chain({"question": message})
-    return result["answer"]
-
-demo = gr.ChatInterface(fn=chat, title="Prüfungsrecht Chatbot", description="Offline RAG pipeline ohne Flowise")
-demo.launch()
+import requests
+import os
+
+# --- Flowise endpoint ---
+# Nếu bạn chạy Flowise cục bộ: ngrok http 3000
+FLOWISE_API = os.getenv("FLOWISE_API", "https://<your-ngrok-or-render-url>/api/v1/prediction")
+
+def chat_with_bot(message, history):
+    """
+    Gửi câu hỏi người dùng đến Flowise API và nhận câu trả lời.
+    """
+    payload = {"question": message}
+    try:
+        response = requests.post(FLOWISE_API, json=payload, timeout=60)
+        data = response.json()
+
+        answer = data.get("text", "Keine Antwort gefunden.")
+        sources = data.get("sourceDocuments", [])
+
+        if sources:
+            refs = "\n\n**Quellen:**\n" + "\n".join([
+                f"- {src.get('metadata', {}).get('source', 'Unbekannt')}"
+                for src in sources
+            ])
+        else:
+            refs = ""
+
+        return answer + refs
+
+    except Exception as e:
+        return f"Fehler: {e}"
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# 🤖 Chatbot für Prüfungsrecht")
+    gr.Markdown("Fragen Sie zur Prüfungsordnung oder zum Hochschulgesetz NRW. "
+                "Der Chatbot zitiert direkt aus den Quellen (PDF & Webseite).")
+
+    chat = gr.ChatInterface(
+        fn=chat_with_bot,
+        title="Prüfungsrecht RAG-Chatbot",
+        examples=[
+            "Was steht in §10 über Wiederholungsprüfungen?",
+            "Welche Regel gilt laut Hochschulgesetz für Prüfungsanspruch?",
+        ]
+    )
+
+    gr.HTML("""
+    <h3>📄 Quellen anzeigen</h3>
+    <iframe src="https://recht.nrw.de/lmi/owa/br_text_anzeigen?v_id=10000000000000000654" width="100%" height="400"></iframe>
+    """)
+
+if __name__ == "__main__":
+    demo.launch()