Spaces:
Sleeping
Sleeping
File size: 9,910 Bytes
d0f04e4 ede60f4 d0f04e4 ede60f4 d0f04e4 ede60f4 547817c d0f04e4 ede60f4 d0f04e4 ede60f4 547817c ede60f4 547817c ede60f4 d0f04e4 ede60f4 d0f04e4 4afe1b1 d0f04e4 ede60f4 d0f04e4 ede60f4 d0f04e4 ede60f4 d0f04e4 ede60f4 d0f04e4 4afe1b1 d0f04e4 4afe1b1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 | import os
import uuid
import json
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, Literal
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
from pydantic import BaseModel, Field
from relevant_links import RELEVANT_NATURALIZATION_LINKS
from prompts import SYSTEM_MESSAGE_TEXT, ROUTER_SYS
# --- 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]]]
# --- Router Structured Output Schema (SINGLE MODEL) ---
class RouterDecision(BaseModel):
action: Literal["reply", "retrieve"]
language: Literal["de", "en", "tr", "ar"]
text: Optional[str] = None
normalized_query: Optional[str] = None
# --- AI Models ---
if not os.environ.get("OPENAI_API_KEY"):
os.environ["OPENAI_API_KEY"] = input("Enter API key for OpenAI: ")
llm = init_chat_model("gpt-4.1", model_provider="openai", temperature=0.5)
# router with structured output using the single model
_router_llm_base = init_chat_model("gpt-4.1", model_provider="openai", temperature=0.7)
router_llm = _router_llm_base.with_structured_output(
schema=RouterDecision,
method="json_schema"
)
# --- 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=4)
serialized = "\n\n".join(
(f"[Source]({doc.metadata.get('source', '')}):\n{doc.page_content}")
for doc in retrieved_docs
)
return serialized, retrieved_docs
def generate_user_id():
return "user_" + uuid.uuid4().hex[:6]
# --- STRICT Router (Structured Output + Retry + Runtime guards) ---
def route_or_reply(user_text: str, prior_msgs: List[BaseMessage]) -> dict:
history_slice = prior_msgs[-4:] if prior_msgs else []
msgs = [SystemMessage(ROUTER_SYS)] + history_slice + [HumanMessage(user_text)]
last_err = None
for attempt in range(2):
try:
obj = router_llm.invoke(msgs)
data = obj.model_dump()
action = data.get("action")
if action == "reply":
if not data.get("text"):
raise ValueError("RouterDecision 'reply' requires 'text'.")
data.pop("normalized_query", None)
elif action == "retrieve":
if not data.get("normalized_query"):
raise ValueError("RouterDecision 'retrieve' requires 'normalized_query'.")
data.pop("text", None)
else:
raise ValueError(f"Unknown action: {action}")
return data
except Exception as e:
last_err = e
print(f"[Router Parse/Validation Error Attempt {attempt+1}]:", repr(e))
return {"action": "reply", "language": "en", "text": "Sorry, something went wrong. Please try again."}
# --- Main Node ---
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
decision = route_or_reply(latest_user_msg.content, history)
print("[Router]", decision)
if decision.get("action") == "reply":
response = AIMessage(content=decision.get("text", ""))
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}
normalized_query = decision.get("normalized_query") or latest_user_msg.content
retrieved_text, _ = retrieve(normalized_query)
history_tail = history[-5:]
system_msg = SystemMessage(
SYSTEM_MESSAGE_TEXT
+ "\n\nStrictly use the following documents to answer the question. "
"If helpful, include direct source links in your answer: "
+ retrieved_text
)
prompt = [system_msg] + history_tail + [latest_user_msg]
response = llm.invoke(prompt)
print("The retrieved text is ", retrieved_text)
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)
|