agents code

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

app.py

@@ -3,36 +3,55 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from agent import build_graph
+from langchain_core.messages import HumanMessage
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
+# --- Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
+class GAIAAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("GAIAAgent initialized - building LangGraph agent...")
+        self.graph = build_graph(provider="vertexai")
+        print("LangGraph agent built successfully.")
+        
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        try:
+            # Invoke the graph with the question
+            result = self.graph.invoke({"messages": [HumanMessage(content=question)]})
+            
+            # Extract the final answer from the last message
+            messages = result.get("messages", [])
+            if messages:
+                last_message = messages[-1].content
+                # Look for FINAL ANSWER in the response
+                if "FINAL ANSWER:" in last_message:
+                    answer = last_message.split("FINAL ANSWER:")[-1].strip()
+                else:
+                    answer = last_message
+                print(f"Agent returning answer: {answer[:100]}...")
+                return answer
+            else:
+                return "No response generated"
+        except Exception as e:
+            print(f"Error running agent: {e}")
+            return f"Error: {str(e)}"
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+def run_and_submit_all():
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Fetches all questions, runs the GAIAAgent on them, submits all answers,
     and displays the results.
     """
     # --- Determine HF Space Runtime URL and Repo URL ---
     space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
 
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+    # For local testing, use a default username
+    username = os.getenv("HF_USERNAME", "local_user")
+    print(f"Running as: {username}")
 
     api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
@@ -40,15 +59,18 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = GAIAAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
     # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
+    if space_id:
+        agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    else:
+        agent_code = "local_development"
+    print(f"Agent code location: {agent_code}")
 
-    # 2. Fetch Questions
+    # 2. Fetch Questions and Download Associated Files
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
@@ -58,6 +80,45 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
              print("Fetched questions list is empty.")
              return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
+        
+        # Download files for questions that have them
+        files_url = f"{api_url}/files"
+        for item in questions_data:
+            task_id = item.get("task_id")
+            file_name = item.get("file_name", "")
+            
+            if file_name:  # If there's a file associated with this question
+                print(f"Downloading file for task {task_id}: {file_name}")
+                try:
+                    file_response = requests.get(f"{files_url}/{task_id}", timeout=30)
+                    file_response.raise_for_status()
+                    
+                    # Determine file extension from content type or file_name
+                    content_type = file_response.headers.get('content-type', '')
+                    if not file_name:
+                        if 'image' in content_type:
+                            file_name = f"{task_id}.png"
+                        elif 'audio' in content_type:
+                            file_name = f"{task_id}.mp3"
+                        elif 'excel' in content_type or 'spreadsheet' in content_type:
+                            file_name = f"{task_id}.xlsx"
+                        elif 'python' in content_type or 'text' in content_type:
+                            file_name = f"{task_id}.py"
+                        else:
+                            file_name = f"{task_id}.bin"
+                    
+                    # Save the file
+                    with open(file_name, 'wb') as f:
+                        f.write(file_response.content)
+                    
+                    # Add file path to the item
+                    item['file_path'] = file_name
+                    print(f"  Downloaded: {file_name} ({len(file_response.content)} bytes)")
+                    
+                except requests.exceptions.RequestException as e:
+                    print(f"  Error downloading file for {task_id}: {e}")
+                    item['file_path'] = None
+                    
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
@@ -76,13 +137,24 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
+        file_path = item.get("file_path", None)
+        
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
+        
+        # Add file path information to the question if a file exists
+        if file_path:
+            enhanced_question = f"{question_text}\n\nFile available at: {file_path}"
+        else:
+            enhanced_question = question_text
+            
         try:
-            submitted_answer = agent(question_text)
+            print(f"Processing task {task_id}...")
+            submitted_answer = agent(enhanced_question)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            print(f"  Answer: {submitted_answer[:100]}..." if len(submitted_answer) > 100 else f"  Answer: {submitted_answer}")
         except Exception as e:
              print(f"Error running agent on task {task_id}: {e}")
              results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
@@ -142,25 +214,24 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# GAIA 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.
+        1. Your agent is configured to use Google VertexAI Gemini model
+        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
+        3. Note: This can take some time as the agent processes all questions.
 
         ---
-        **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.
+        **Setup:**
+        - Model: Gemini 2.5 Pro (VertexAI)
+        - Tools: Wikipedia, Web Search (Tavily), ArXiv, Math operations
+        - Vector Store: ChromaDB (for similar question retrieval)
         """
     )
 
-    gr.LoginButton()
-
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
 
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
     # Removed max_rows=10 from DataFrame constructor
@@ -168,6 +239,7 @@ with gr.Blocks() as demo:
 
     run_button.click(
         fn=run_and_submit_all,
+        inputs=[],
         outputs=[status_output, results_table]
     )
 

requirements.txt

@@ -1,2 +1,24 @@
 gradio
-requests
+requests
+langchain
+langchain-community
+langchain-core
+langchain-google-vertexai
+langchain-huggingface
+langchain-tavily
+langchain-chroma
+langgraph
+huggingface_hub
+sentence-transformers
+arxiv
+pymupdf
+wikipedia
+pgvector
+python-dotenv
+protobuf==3.20.*
+chromadb
+google-cloud-aiplatform
+vertexai
+pandas
+pillow
+openpyxl