added logs for debugging

.gitignore

@@ -1 +1,2 @@
-env*
+env*
+.env*

app.py

@@ -55,7 +55,7 @@ async def generate_answers(profile: gr.OAuthProfile | None, progress=gr.Progress
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None, gr.update(interactive=False)
+        return "Please Login to Hugging Face with the button.", None, gr.update(interactive=False), gr.update(value=0, visible=False)
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     try:
@@ -64,11 +64,11 @@ async def generate_answers(profile: gr.OAuthProfile | None, progress=gr.Progress
         questions_data = response.json()
         if not questions_data:
             print("Fetched questions list is empty.")
-            return "Fetched questions list is empty or invalid format.", None, gr.update(interactive=False)
+            return "Fetched questions list is empty or invalid format.", None, gr.update(interactive=False), gr.update(value=0, visible=False)
         print(f"Fetched {len(questions_data)} questions.")
     except Exception as e:
         print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None, gr.update(interactive=False)
+        return f"Error fetching questions: {e}", None, gr.update(interactive=False), gr.update(value=0, visible=False)
     agent = BasicAgent()
     results_log = []
     answers_payload = []
@@ -102,7 +102,7 @@ async def generate_answers(profile: gr.OAuthProfile | None, progress=gr.Progress
     cached_results_log = results_log
     progress(100, desc="Done.")
     results_df = pd.DataFrame(results_log)
-    return "Answer generation complete. Review and submit.", results_df, gr.update(interactive=True)
+    return "Answer generation complete. Review and submit.", results_df, gr.update(interactive=True), gr.update(value=100, visible=True)
 
 def submit_answers(profile: gr.OAuthProfile | None):
     """

debug_test.py

@@ -0,0 +1,36 @@
+import asyncio
+from langraph_agent import build_graph
+from langchain_core.messages import HumanMessage
+
+async def test_agent():
+    """Test the agent with a simple question"""
+    try:
+        print("Building graph...")
+        graph = build_graph(provider="groq")
+        
+        print("Testing with a simple question...")
+        question = "What is 2 + 3?"
+        messages = [HumanMessage(content=question)]
+        
+        print("Invoking agent...")
+        response = await graph.ainvoke({"messages": messages})
+        
+        print(f"Response type: {type(response)}")
+        print(f"Response keys: {response.keys() if isinstance(response, dict) else 'Not a dict'}")
+        
+        if 'messages' in response and response['messages']:
+            print(f"Number of messages: {len(response['messages'])}")
+            print(f"Last message content: {response['messages'][-1].content}")
+            return "SUCCESS"
+        else:
+            print("No messages in response or empty messages")
+            return "FAILED - No messages"
+    except Exception as e:
+        print(f"Error in test: {e}")
+        import traceback
+        traceback.print_exc()
+        return f"FAILED - {e}"
+
+if __name__ == "__main__":
+    result = asyncio.run(test_agent())
+    print(f"Test result: {result}") 

langraph_agent.py

@@ -19,9 +19,18 @@ from supabase.client import Client, create_client
 from langfuse.langchain import CallbackHandler
 
 # Initialize Langfuse CallbackHandler for LangGraph/Langchain (tracing)
-langfuse_handler = CallbackHandler()
+try:
+    langfuse_handler = CallbackHandler()
+except Exception as e:
+    print(f"Warning: Could not initialize Langfuse handler: {e}")
+    langfuse_handler = None
 
-load_dotenv()
+# Load environment variables - try multiple files
+load_dotenv()  # Try .env first
+load_dotenv("env.local")  # Try env.local as backup
+
+print(f"SUPABASE_URL loaded: {bool(os.environ.get('SUPABASE_URL'))}")
+print(f"GROQ_API_KEY loaded: {bool(os.environ.get('GROQ_API_KEY'))}")
 
 @tool
 def multiply(a: int, b: int) -> int:
@@ -81,13 +90,19 @@ def wiki_search(query: str) -> str:
     
     Args:
         query: The search query."""
-    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
-    formatted_search_docs = "\n\n---\n\n".join(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
-            for doc in search_docs
-        ])
-    return {"wiki_results": formatted_search_docs}
+    try:
+        search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+        if not search_docs:
+            return {"wiki_results": "No Wikipedia results found for the query."}
+        formatted_search_docs = "\n\n---\n\n".join(
+            [
+                f'<Document source="{doc.metadata.get("source", "Unknown")}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+                for doc in search_docs
+            ])
+        return {"wiki_results": formatted_search_docs}
+    except Exception as e:
+        print(f"Error in wiki_search: {e}")
+        return {"wiki_results": f"Error searching Wikipedia: {e}"}
 
 @tool
 def web_search(query: str) -> str:
@@ -95,13 +110,19 @@ def web_search(query: str) -> str:
     
     Args:
         query: The search query."""
-    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
-    formatted_search_docs = "\n\n---\n\n".join(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
-            for doc in search_docs
-        ])
-    return {"web_results": formatted_search_docs}
+    try:
+        search_docs = TavilySearchResults(max_results=3).invoke(query=query)
+        if not search_docs:
+            return {"web_results": "No web search results found for the query."}
+        formatted_search_docs = "\n\n---\n\n".join(
+            [
+                f'<Document source="{doc.get("url", "Unknown")}" />\n{doc.get("content", "No content")}\n</Document>'
+                for doc in search_docs
+            ])
+        return {"web_results": formatted_search_docs}
+    except Exception as e:
+        print(f"Error in web_search: {e}")
+        return {"web_results": f"Error searching web: {e}"}
 
 @tool
 def arvix_search(query: str) -> str:
@@ -109,15 +130,19 @@ def arvix_search(query: str) -> str:
     
     Args:
         query: The search query."""
-    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
-    formatted_search_docs = "\n\n---\n\n".join(
-        [
-            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
-            for doc in search_docs
-        ])
-    return {"arvix_results": formatted_search_docs}
-
-
+    try:
+        search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+        if not search_docs:
+            return {"arvix_results": "No Arxiv results found for the query."}
+        formatted_search_docs = "\n\n---\n\n".join(
+            [
+                f'<Document source="{doc.metadata.get("source", "Unknown")}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+                for doc in search_docs
+            ])
+        return {"arvix_results": formatted_search_docs}
+    except Exception as e:
+        print(f"Error in arvix_search: {e}")
+        return {"arvix_results": f"Error searching Arxiv: {e}"}
 
 # load the system prompt from the file
 with open("system_prompt.txt", "r", encoding="utf-8") as f:
@@ -128,22 +153,33 @@ sys_msg = SystemMessage(content=system_prompt)
 
 # build a retriever
 embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
-supabase: Client = create_client(
-    os.environ.get("SUPABASE_URL"), 
-    os.environ.get("SUPABASE_SERVICE_KEY"))
-vector_store = SupabaseVectorStore(
-    client=supabase,
-    embedding= embeddings,
-    table_name="documents",
-    query_name="match_documents_langchain",
-)
-create_retriever_tool = create_retriever_tool(
-    retriever=vector_store.as_retriever(),
-    name="Question Search",
-    description="A tool to retrieve similar questions from a vector store.",
-)
-
 
+# Try to create Supabase client with error handling
+try:
+    supabase_url = os.environ.get("SUPABASE_URL")
+    supabase_key = os.environ.get("SUPABASE_SERVICE_KEY")
+    
+    if not supabase_url or not supabase_key:
+        print("Warning: Supabase credentials not found, vector store will be disabled")
+        vector_store = None
+        create_retriever_tool = None
+    else:
+        supabase: Client = create_client(supabase_url, supabase_key)
+        vector_store = SupabaseVectorStore(
+            client=supabase,
+            embedding= embeddings,
+            table_name="documents",
+            query_name="match_documents_langchain",
+        )
+        create_retriever_tool = create_retriever_tool(
+            retriever=vector_store.as_retriever(),
+            name="Question Search",
+            description="A tool to retrieve similar questions from a vector store.",
+        )
+except Exception as e:
+    print(f"Warning: Could not initialize Supabase vector store: {e}")
+    vector_store = None
+    create_retriever_tool = None
 
 tools = [
     multiply,
@@ -155,6 +191,8 @@ tools = [
     web_search,
     arvix_search,
 ]
+if create_retriever_tool:
+    tools.append(create_retriever_tool)
 
 # Build graph function
 def build_graph(provider: str = "groq"):
@@ -182,15 +220,42 @@ def build_graph(provider: str = "groq"):
     # Node
     def assistant(state: MessagesState):
         """Assistant node"""
-        return {"messages": [llm_with_tools.invoke(state["messages"])]}
+        try:
+            print(f"Assistant node: Processing {len(state['messages'])} messages")
+            result = llm_with_tools.invoke(state["messages"])
+            print(f"Assistant node: LLM returned result type: {type(result)}")
+            return {"messages": [result]}
+        except Exception as e:
+            print(f"Error in assistant node: {e}")
+            from langchain_core.messages import AIMessage
+            error_msg = AIMessage(content=f"I encountered an error: {e}")
+            return {"messages": [error_msg]}
     
     def retriever(state: MessagesState):
         """Retriever node"""
-        similar_question = vector_store.similarity_search(state["messages"][0].content)
-        example_msg = HumanMessage(
-            content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
-        )
-        return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+        try:
+            print(f"Retriever node: Processing {len(state['messages'])} messages")
+            if not state["messages"]:
+                print("Retriever node: No messages in state")
+                return {"messages": [sys_msg]}
+            if not vector_store:
+                print("Retriever node: Vector store not available, skipping retrieval")
+                return {"messages": [sys_msg] + state["messages"]}
+            query_content = state["messages"][0].content
+            print(f"Retriever node: Searching for similar questions with query: {query_content[:100]}...")
+            similar_question = vector_store.similarity_search(query_content)
+            print(f"Retriever node: Found {len(similar_question)} similar questions")
+            if not similar_question:
+                print("Retriever node: No similar questions found, proceeding without example")
+                return {"messages": [sys_msg] + state["messages"]}
+            example_msg = HumanMessage(
+                content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
+            )
+            print(f"Retriever node: Added example message from similar question")
+            return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+        except Exception as e:
+            print(f"Error in retriever node: {e}")
+            return {"messages": [sys_msg] + state["messages"]}
 
     builder = StateGraph(MessagesState)
     builder.add_node("retriever", retriever)

pyproject.toml

@@ -3,7 +3,7 @@ name = "final-assignment-template"
 version = "0.1.0"
 description = "Add your description here"
 readme = "README.md"
-requires-python = ">=3.10,<3.12"
+requires-python = ">=3.13"
 dependencies = [
     "dotenv>=0.9.9",
     "hf-xet>=1.1.3",

test.py

@@ -6,6 +6,8 @@ import requests
 import pandas as pd
 from langchain_core.messages import HumanMessage
 from agent import build_graph
+import asyncio
+from langraph_agent import build_graph
 
 
 
@@ -184,6 +186,35 @@ with gr.Blocks() as demo:
         outputs=[status_output, results_table]
     )
 
+async def test_agent():
+    """Test the agent with a simple question"""
+    try:
+        print("Building graph...")
+        graph = build_graph(provider="groq")
+        
+        print("Testing with a simple question...")
+        question = "What is 2 + 3?"
+        messages = [HumanMessage(content=question)]
+        
+        print("Invoking agent...")
+        response = await graph.ainvoke({"messages": messages})
+        
+        print(f"Response type: {type(response)}")
+        print(f"Response keys: {response.keys() if isinstance(response, dict) else 'Not a dict'}")
+        
+        if 'messages' in response and response['messages']:
+            print(f"Number of messages: {len(response['messages'])}")
+            print(f"Last message content: {response['messages'][-1].content}")
+            return "SUCCESS"
+        else:
+            print("No messages in response or empty messages")
+            return "FAILED - No messages"
+    except Exception as e:
+        print(f"Error in test: {e}")
+        import traceback
+        traceback.print_exc()
+        return f"FAILED - {e}"
+
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
     # Check for SPACE_HOST and SPACE_ID at startup for information
@@ -206,4 +237,7 @@ if __name__ == "__main__":
     print("-"*(60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)
+
+    result = asyncio.run(test_agent())
+    print(f"Test result: {result}")