Update app.py

app.py

@@ -1241,7 +1241,7 @@ def multi_agent_chat_advanced(query: str, file=None) -> str:
 
 
 # LangGraph 使用的節點函數（會接續你的 Crew Agent）
-
+# 初始化 embedding model
 embedding_model = SentenceTransformer("all-MiniLM-L6-v2")
 
 # Intent Embedding 分類（支援檔名）
@@ -1253,13 +1253,11 @@ INTENT_LABELS = {
 
 def detect_intent_embedding(query, file_names=[]):
     query_emb = embedding_model.encode(query, normalize_embeddings=True)
-
     best_label = None
     best_score = -1
     all_phrases = INTENT_LABELS.copy()
     if file_names:
         all_phrases["DocQA"] += [name.lower() for name in file_names]
-
     for label, examples in all_phrases.items():
         for example in examples:
             example_emb = embedding_model.encode(example, normalize_embeddings=True)
@@ -1275,12 +1273,40 @@ def decide_next(state):
     label = detect_intent_embedding(query, file_names)
     return label
 
-# ✅ node functions
+# === 定義 Task 物件 ===
+docqa_task = Task(
+    description="Document QA Task: Answer questions based on the uploaded document.",
+    expected_output="Answer from Document QA Agent.",
+    agent=document_qa_agent,
+    input_variables=["query"]
+)
 
+general_task = Task(
+    description="General Chat Task: Answer general queries.",
+    expected_output="Answer from General Agent.",
+    agent=general_agent,
+    input_variables=["query"]
+)
+
+summariser_task = Task(
+    description="Summarisation Task: Summarise document content.",
+    expected_output="Summary output.",
+    agent=summarizer_agent,  # 使用 summarizer_agent（注意字母 z）
+    input_variables=["query"]
+)
+
+search_task = Task(
+    description="Search Task: Retrieve information from the web.",
+    expected_output="Answer from Search Agent.",
+    agent=search_agent,
+    input_variables=["query"]
+)
+
+# === LangGraph 節點函數 ===
 def docqa_run(state):
     result = document_qa_agent.execute_task(docqa_task, inputs={"query": state["query"]})
     output = result.output.lower()
-    # fallback: no info found → general
+    # fallback: 若回答中含 "no relevant info", "not found", 或 "no answer"，則使用 General 模組
     if any(x in output for x in ["no relevant info", "not found", "no answer"]):
         return general_run(state)
     return {"answer": result.output}
@@ -1288,47 +1314,42 @@ def docqa_run(state):
 def general_run(state):
     result = general_agent.execute_task(general_task, inputs={"query": state["query"]})
     output = result.output.lower()
+    # 若 General Agent 回答不佳，則改用 Search 模組
     if any(x in output for x in ["i don't know", "no idea", "not sure", "can't answer"]):
         result = search_agent.execute_task(search_task, inputs={"query": state["query"]})
     return {"answer": result.output}
 
 def summariser_run(state):
-    result = summariser_agent.execute_task(summariser_task, inputs={"query": state["query"]})
+    result = summarizer_agent.execute_task(summariser_task, inputs={"query": state["query"]})
     return {"summary": result.output}
 
-# ✅ LangGraph 定義
-
+# === LangGraph 定義 ===
 def build_langgraph_pipeline():
     graph = StateGraph(dict)
-
-    graph.add_node("Router", lambda state: state)  # router 只傳入狀態即可
+    graph.add_node("Router", lambda state: state)  # Router 僅傳遞狀態
     graph.add_node("DocQA", docqa_run)
     graph.add_node("General", general_run)
     graph.add_node("Summarise", summariser_run)
-
     graph.set_entry_point("Router")
     graph.add_conditional_edges("Router", decide_next, {
         "DocQA": "DocQA",
         "General": "General",
         "Summarise": "Summarise",
     })
-
     graph.set_finish_point("DocQA")
     graph.set_finish_point("General")
     graph.set_finish_point("Summarise")
-
     return graph.compile()
 
-# ✅ 主執行函數
-
+# === 主執行函數 (Tab6) ===
 def langgraph_tab6_main(query: str, file=None):
     try:
         files = file if isinstance(file, list) else [file] if file else []
         all_docs, file_names = [], []
-
         for f in files:
             path = get_file_path(f)
-            if not path: continue
+            if not path:
+                continue
             file_names.append(os.path.basename(path))
             if path.lower().endswith(".pdf"):
                 loader = PyPDFLoader(path)
@@ -1337,21 +1358,16 @@ def langgraph_tab6_main(query: str, file=None):
             else:
                 loader = TextLoader(path)
             all_docs.extend(loader.load())
-
         if not all_docs:
             retriever = None  # 空 retriever
         else:
             chunks = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50).split_documents(all_docs)
             db = FAISS.from_documents(chunks, embeddings)
             retriever = db.as_retriever()
-
-        # 設定 retriever 到 global Agent，如果你需要可傳給 Agent
-        # 可選：document_qa_agent.retriever = retriever
-
+        # 可選：設定 retriever 到 global Agent（若需要）
         graph = build_langgraph_pipeline()
         state = {"query": query, "file_names": file_names}
         result = graph.invoke(state)
-
         if "answer" in result:
             return result["answer"]
         if "summary" in result: