Update app.py

app.py

@@ -1244,33 +1244,22 @@ INTENT_LABELS = {
     "General": ["who are you", "tell me something", "what can you do", "fun fact"],
 }
 
-def parse_query(query: str) -> dict:
-    prompt = """Analyze the following query and determine required subtasks. Return a JSON object containing:
-    - summarize_files: list of document indices to summarize
-    - qa_pairs: list of QA objects [{"question": "question", "doc_indices": [relevant doc indices]}]
-    - compare_files: list of document index pairs to compare [[doc1_idx, doc2_idx]]
-    - find_relations: boolean, whether to analyze document relationships
-    
-    For example, query "What are the differences between document A and B, and summarize A" should return:
-    {
-        "summarize_files": [0],
-        "qa_pairs": [],
-        "compare_files": [[0, 1]],
-        "find_relations": false
-    }
-    
-    Query: """ + query
-    
-    response = llm_gpt4.invoke(prompt)
-    try:
-        return json.loads(response.content)
-    except:
-        return {
-            "summarize_files": [],
-            "qa_pairs": [{"question": query, "doc_indices": [0]}],
-            "compare_files": [],
-            "find_relations": False
-        }
+# AutoGen Multi-Agent Collaboration Logic 
+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)
+            score = float(query_emb @ example_emb.T)
+            if score > best_score:
+                best_score = score
+                best_label = label
+    return best_label if best_label else "General"
 
 def autogen_multi_document_analysis(query: str, docs: list, file_names: list) -> str:
     try:      
@@ -1397,22 +1386,7 @@ def autogen_multi_document_analysis(query: str, docs: list, file_names: list) ->
         print(f"ERROR in AutoGen processing: {str(e)}")
         return f"Error analyzing documents: {str(e)}"
 
-# AutoGen Multi-Agent Collaboration Logic 
-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)
-            score = float(query_emb @ example_emb.T)
-            if score > best_score:
-                best_score = score
-                best_label = label
-    return best_label if best_label else "General"
+
 
 def decide_next(state):
     query = state.get("query", "")
@@ -1420,34 +1394,6 @@ def decide_next(state):
     label = detect_intent_embedding(query, file_names)
     return label
 
-# === Define Task objects ===
-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,  # Note: The name must match the defined agent (using 'z' if applicable)
-    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 Node Functions ===
 
@@ -1508,25 +1454,6 @@ def summariser_run(state):
         print(f"ERROR in summariser_run: {str(e)}")
         return {"summary": "Error generating summary."}
 
-# === LangGraph Definition ===
-def build_langgraph_pipeline():
-    graph = StateGraph(dict)
-    graph.add_node("Router", lambda state: state)  # Router: simply pass the state
-    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()
-
-
 
 def get_file_path_tab6(file):
     if isinstance(file, str):