README23 / testing_app.py
ahmad-agilekode's picture
Upload 9 files
ee98f9e verified
Raw History Blame Contribute Delete
7.09 kB
import os
import uuid
from dotenv import load_dotenv
load_dotenv()
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_core.tools import tool
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 InMemoryChatMessageHistory
class CustomState(TypedDict):
messages: Annotated[List[BaseMessage], add_messages]
user_id: str
chat_history: Optional[List[List[str]]]
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)
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
)
class MemoryStore:
def get_memory(self, user_id: str):
return InMemoryChatMessageHistory()
store = MemoryStore()
def retrieve(query: str):
"""Retrieve information related to the last query."""
retrieved_docs = vector_store.similarity_search(query, k=6)
print("\n🔎 Retrieved Documents:")
for i, doc in enumerate(retrieved_docs, 1):
print(f"\n--- Document {i} ---")
print(f"Source: {doc.metadata}")
print(f"Content (excerpt):\n{doc.page_content}...")
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_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:] if hasattr(memory, 'messages') else []
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)
return {**state, "messages": [response], "user_id": user_id}
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()
import gradio as gr
def clear_history(user_id_state):
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)