import os import uuid from datetime import datetime from dotenv import load_dotenv load_dotenv() from supabase import create_client from langchain_core.runnables import RunnableConfig from typing import TypedDict, List, Optional, Annotated from langchain_core.messages import BaseMessage, AIMessage, HumanMessage, SystemMessage from langgraph.graph.message import add_messages from langgraph.graph import StateGraph, END from langchain_openai import OpenAIEmbeddings from langchain.chat_models import init_chat_model from langchain_pinecone import Pinecone as LangchainPinecone from langchain_core.chat_history import BaseChatMessageHistory from langchain_core.messages import messages_from_dict, messages_to_dict # --- Supabase Setup --- SUPABASE_URL = os.getenv("SUPABASE_URL") SUPABASE_KEY = os.getenv("SUPABASE_KEY") supabase = create_client(SUPABASE_URL, SUPABASE_KEY) # --- Custom State --- class CustomState(TypedDict): messages: Annotated[List[BaseMessage], add_messages] user_id: str chat_history: Optional[List[List[str]]] # --- AI Model --- if not os.environ.get("OPENAI_API_KEY"): os.environ["OPENAI_API_KEY"] = input("Enter API key for OpenAI: ") llm = init_chat_model("gpt-4o", model_provider="openai", temperature=0.0) # --- Vector Store --- pinecone_api_key = os.getenv("PINECONE_API_KEY", "").strip() pinecone_index_name = os.getenv("PINECONE_INDEX_NAME", "").strip() embeddings = OpenAIEmbeddings(model="text-embedding-3-large") vector_store = LangchainPinecone( index_name=pinecone_index_name, embedding=embeddings, pinecone_api_key=pinecone_api_key ) # --- Supabase Chat Memory --- class SupabaseChatMessageHistory(BaseChatMessageHistory): def __init__(self, user_id: str, supabase_client): self.user_id = user_id self.supabase = supabase_client @property def messages(self): response = self.supabase.table("chat_memory").select("*").eq("user_id", self.user_id).execute() data = response.data[0] if response.data else {} return messages_from_dict(data.get("messages", [])) def add_message(self, message): all_messages = messages_to_dict(self.messages + [message]) self.supabase.table("chat_memory").upsert({ "user_id": self.user_id, "messages": all_messages }).execute() def add_user_message(self, content: str): self.add_message(HumanMessage(content=content)) def add_ai_message(self, content: str): self.add_message(AIMessage(content=content)) def clear(self): self.supabase.table("chat_memory").delete().eq("user_id", self.user_id).execute() class MemoryStore: def get_memory(self, user_id: str): return SupabaseChatMessageHistory(user_id, supabase) store = MemoryStore() # --- Logging --- def log_interaction_cloud(user_id: str, question: str, answer: str): payload = { "user_id": user_id, "question": question, "answer": answer, "timestamp": datetime.utcnow().isoformat(), } try: res = supabase.table("logs").insert(payload).execute() print("[Supabase Log Success]:", res.data) except Exception as e: print("[Supabase Log Error]:", e) # --- Retrieval --- def retrieve(query: str): retrieved_docs = vector_store.similarity_search(query, k=6) serialized = "\n\n".join( (f"Source: {doc.metadata}\n" f"Content: {doc.page_content}") for doc in retrieved_docs ) return serialized, retrieved_docs # --- System Message --- SYSTEM_MESSAGE_TEXT = ( "You are Einbürgerungs-Helfer, a highly skilled, friendly, and helpful administrative assistant for naturalization matters in Germany." " You only support the following languages: German, English, Turkish, and Arabic." " You MUST always respond in the language of the user's last message." " If a user sends a message in an unsupported language, politely inform them with the following message:" " 'Bitte stellen Sie Ihre Frage auf Deutsch, Englisch, Türkisch oder Arabisch.'" " Your sole purpose is to assist individuals who are eligible for German naturalization but have not yet applied." " You only answer questions directly related to the current naturalization process in Germany." " You do not assist with completing applications or submitting them." " Your answers must be based solely on the provided context. Do NOT generate answers from your own knowledge." " Your responses must always be accurate, concise, and easy to understand." " Never hallucinate, never go beyond the topic of naturalization, and never share information that is false or misleading." " If you do not have enough knowledge to answer a question based on the provided context, respond with:" " 'I do not have enough knowledge to answer your question accurately. Please email your question to SBD-Umfrage@polsoz.fu-berlin.de, and we will respond as soon as possible.'" " If a user uses toxic, offensive, or inappropriate language, kindly ask them to rephrase their question" " and explain that such behavior is not acceptable." ) def generate_user_id(): return "user_" + uuid.uuid4().hex[:6] def query_or_respond(state: CustomState) -> CustomState: user_id = state.get("user_id") or generate_user_id() human_messages = [m for m in state["messages"] if m.type == "human"] latest_user_msg = human_messages[-1] memory = store.get_memory(user_id) history = memory.messages[-5:] retrieved_text, _ = retrieve(latest_user_msg.content) context = SystemMessage(SYSTEM_MESSAGE_TEXT + "\n\nRetrieved Context:\n" + retrieved_text) prompt = [context] + history + [latest_user_msg] response = llm.invoke(prompt) memory.add_user_message(latest_user_msg.content) memory.add_ai_message(response.content) log_interaction_cloud(user_id, latest_user_msg.content, response.content) return {**state, "messages": [response], "user_id": user_id} # --- Graph --- graph_builder = StateGraph(CustomState) graph_builder.add_node("query_or_respond", query_or_respond) graph_builder.set_entry_point("query_or_respond") graph_builder.add_edge("query_or_respond", END) graph = graph_builder.compile() # --- Gradio UI --- import gradio as gr def clear_history(user_id_state): if user_id_state: store.get_memory(user_id_state).clear() return [["", "Ich bin hier, um Ihnen bei allen Fragen zur Einbürgerung in Deutschland zu helfen..."]], user_id_state, "", user_id_state def respond(user_message, chatbot, user_id_input, chat_state, user_id_state): if not user_message: return chatbot, chat_state, user_id_input, "", user_id_state user_id = user_id_state or user_id_input or generate_user_id() state: CustomState = { "messages": [HumanMessage(content=user_message)], "user_id": user_id, "chat_history": None } config = RunnableConfig(configurable={"session_id": user_id}) final_state = graph.invoke(state, config=config) bot_response = final_state["messages"][-1].content chatbot.append([user_message, bot_response]) return chatbot, chatbot, user_id, "", user_id description = """ ### Was ist **Einbürgerungs-Helfer**? **Deutsch:** Einbürgerungs-Helfer hilft dir, den Weg zur deutschen Staatsangehörigkeit zu verstehen – einfach, mehrsprachig, datenschutzfreundlich. """ with gr.Blocks(theme=gr.themes.Soft(primary_hue="blue")) as iface: gr.Markdown(f"# Einbürgerungs-Helfer\n{description}") with gr.Row(): user_id_input = gr.Textbox(label="Benutzer-ID (User ID)", placeholder="z.B. user_123", lines=1) clear_btn = gr.Button("🗑️ Verlauf löschen") user_id_state = gr.State(value="") chat_state = gr.State([]) chatbot = gr.Chatbot( label="Chat", show_copy_button=True, value=[[None, "Ich bin hier, um Ihnen bei allen Fragen zur Einbürgerung in Deutschland zu helfen.\nLassen Sie uns loslegen – wie kann ich Ihnen heute helfen?"]] ) msg_input = gr.Textbox(placeholder="Frage eingeben...", label="Deine Nachricht", lines=1, value="") with gr.Row(): submit_btn = gr.Button("Senden", variant="primary") submit_btn.click(fn=respond, inputs=[msg_input, chatbot, user_id_input, chat_state, user_id_state], outputs=[chatbot, chat_state, user_id_input, msg_input, user_id_state]) msg_input.submit(fn=respond, inputs=[msg_input, chatbot, user_id_input, chat_state, user_id_state], outputs=[chatbot, chat_state, user_id_input, msg_input, user_id_state]) clear_btn.click(fn=clear_history, inputs=[user_id_state], outputs=[chatbot, user_id_input, msg_input, user_id_state]) iface.launch(server_name="0.0.0.0", server_port=int(os.getenv("PORT", 7860)), share=True)