update file

.env.example

@@ -0,0 +1,17 @@
+# Copy this file to .env and fill in your API keys
+
+# Google AI API Key (for Gemini)
+GOOGLE_API_KEY=your_google_api_key_here
+
+# Groq API Key 
+GROQ_API_KEY=your_groq_api_key_here
+
+# Tavily API Key (for web search)
+TAVILY_API_KEY=your_tavily_api_key_here
+
+# Supabase Configuration (optional - for vector store)
+SUPABASE_URL=your_supabase_url_here
+SUPABASE_SERVICE_KEY=your_supabase_service_key_here
+
+# Hugging Face API Token (optional - for HuggingFace models)
+HUGGINGFACEHUB_API_TOKEN=your_huggingface_token_here

app.py

@@ -14,6 +14,9 @@ from langchain_community.vectorstores import SupabaseVectorStore
 from langchain_core.messages import SystemMessage, HumanMessage
 from langchain_core.tools import tool
 from supabase.client import Client, create_client
+import gradio as gr
+import pandas as pd
+import json
 
 load_dotenv()
 
@@ -120,16 +123,20 @@ with open("system_prompt.txt", "r", encoding="utf-8") as f:
 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",
-)
+try:
+    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",
+    )
+except Exception as e:
+    print(f"Warning: Could not initialize vector store: {e}")
+    vector_store = None
 
 
 
@@ -188,11 +195,15 @@ def build_graph(provider: str = "google"):
     def retriever(state: MessagesState):
         """Retriever node that searches for similar questions"""
         try:
+            if vector_store is None:
+                # If vector store is not available, pass to assistant
+                return {"messages": state["messages"]}
+            
             query = state["messages"][-1].content
             similar_docs = vector_store.similarity_search(query, k=1)
             
             if not similar_docs:
-                return {"messages": [AIMessage(content="No similar questions found. Let me help you with a new response.")]}
+                return {"messages": state["messages"]}
             
             content = similar_docs[0].page_content
             if "Final answer :" in content:
@@ -203,13 +214,13 @@ def build_graph(provider: str = "google"):
             return {"messages": [AIMessage(content=answer)]}
         except Exception as e:
             # If retrieval fails, pass to assistant for a fresh response
-            return {"messages": [sys_msg] + state["messages"]}
+            return {"messages": state["messages"]}
 
     def should_continue(state: MessagesState):
         """Determine whether to continue with assistant or end"""
         last_message = state["messages"][-1]
-        # If retriever found a good answer, end here
-        if isinstance(last_message, AIMessage) and len(last_message.content) > 50:
+        # If retriever found a good answer (AIMessage from retriever), end here
+        if isinstance(last_message, AIMessage) and len(last_message.content) > 50 and not last_message.tool_calls:
             return "end"
         # Otherwise, continue to assistant
         return "assistant"
@@ -240,5 +251,156 @@ def build_graph(provider: str = "google"):
     graph = builder.compile()
     return graph
 
-    # Compile graph
-    return builder.compile()
+# Initialize the graph
+try:
+    graph = build_graph("google")  # You can change this to "groq" or "huggingface"
+except Exception as e:
+    print(f"Warning: Could not initialize graph with Google provider: {e}")
+    try:
+        graph = build_graph("groq")
+        print("Successfully initialized with Groq provider")
+    except Exception as e2:
+        print(f"Warning: Could not initialize graph with Groq provider: {e2}")
+        graph = None
+
+def run_and_submit_all():
+    """Run evaluation on all questions and submit answers"""
+    try:
+        if graph is None:
+            return "❌ Error: Agent is not properly initialized. Please check environment variables and API keys.", pd.DataFrame()
+        
+        # Load questions from questions.json
+        try:
+            with open("questions.json", "r", encoding="utf-8") as f:
+                questions_data = json.load(f)
+        except FileNotFoundError:
+            return "❌ Error: questions.json file not found.", pd.DataFrame()
+        except json.JSONDecodeError as e:
+            return f"❌ Error: Invalid JSON in questions.json: {e}", pd.DataFrame()
+        
+        if not isinstance(questions_data, list):
+            return "❌ Error: questions.json should contain a list of questions.", pd.DataFrame()
+        
+        results = []
+        status_messages = []
+        
+        status_messages.append(f"🚀 Starting evaluation with {len(questions_data)} questions...")
+        
+        for i, question_item in enumerate(questions_data, 1):
+            try:
+                # Handle different question formats
+                if isinstance(question_item, dict):
+                    question = question_item.get("question", str(question_item))
+                    question_id = question_item.get("task_id", question_item.get("id", i))
+                    level = question_item.get("Level", "N/A")
+                    file_name = question_item.get("file_name", "")
+                else:
+                    question = str(question_item)
+                    question_id = i
+                    level = "N/A"
+                    file_name = ""
+                
+                status_messages.append(f"📝 Processing question {i}/{len(questions_data)}: {question[:50]}...")
+                
+                # Convert question to HumanMessage and invoke graph
+                human_msg = HumanMessage(content=question)
+                result = graph.invoke({"messages": [human_msg]})
+                
+                # Extract answer from result
+                if result and "messages" in result and result["messages"]:
+                    answer = result["messages"][-1].content
+                else:
+                    answer = "No response generated"
+                
+                results.append({
+                    "Task ID": question_id,
+                    "Question": question,
+                    "Level": level,
+                    "File Name": file_name,
+                    "Agent Answer": answer
+                })
+                
+                status_messages.append(f"✅ Question {i} completed")
+                
+            except Exception as e:
+                error_msg = f"❌ Error processing question {i}: {str(e)}"
+                status_messages.append(error_msg)
+                results.append({
+                    "Task ID": question_id if 'question_id' in locals() else i,
+                    "Question": question if 'question' in locals() else "Error loading question",
+                    "Level": level if 'level' in locals() else "N/A",
+                    "File Name": file_name if 'file_name' in locals() else "",
+                    "Agent Answer": f"Error: {str(e)}"
+                })
+        
+        # Create DataFrame for results
+        results_df = pd.DataFrame(results)
+        
+        # Prepare final status message
+        successful_answers = len([r for r in results if not r["Agent Answer"].startswith("Error:")])
+        final_status = f"""
+🎯 Evaluation Complete!
+✅ Successfully processed: {successful_answers}/{len(questions_data)} questions
+📊 Results are displayed in the table below.
+
+📝 Detailed Log:
+""" + "\n".join(status_messages)
+        
+        return final_status, results_df
+        
+    except Exception as e:
+        error_msg = f"❌ Critical error during evaluation: {str(e)}"
+        return error_msg, pd.DataFrame()
+
+# --- Build Gradio Interface using Blocks ---
+with gr.Blocks() as demo:
+    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown(
+        """
+        **Instructions:**
+        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
+        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
+        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+        ---
+        **Disclaimers:**
+        Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
+        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
+        """
+    )
+
+    gr.LoginButton()
+
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    # Removed max_rows=10 from DataFrame constructor
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+
+    run_button.click(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
+    )
+
+if __name__ == "__main__":
+    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    # Check for SPACE_HOST and SPACE_ID at startup for information
+    space_host_startup = os.getenv("SPACE_HOST")
+    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+
+    if space_host_startup:
+        print(f"✅ SPACE_HOST found: {space_host_startup}")
+        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
+    else:
+        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
+
+    if space_id_startup: # Print repo URLs if SPACE_ID is found
+        print(f"✅ SPACE_ID found: {space_id_startup}")
+        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
+        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
+    else:
+        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
+
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)

requirements.txt

@@ -9,4 +9,6 @@ langchain-huggingface
 supabase
 sentence-transformers
 tavily-python
-wikipedia
+wikipedia
+gradio
+pandas