upload my tools and updata the app.py

app.py

@@ -1,34 +1,25 @@
 import os
+import json
 import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from agent import SmoalAgent
+from tools import search_tool, rag_chain, extract_final_answer
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+SUBMISSION_FILE = "submission.jsonl"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    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
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """Fetches all questions, runs the SmoalAgent 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}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -38,13 +29,13 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent
     try:
-        agent = BasicAgent()
+        agent = SmoalAgent()
     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)
 
@@ -55,16 +46,16 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
+            print("Fetched questions list is empty.")
+            return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
     except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+        return f"Error decoding server response for questions: {e}", None
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
@@ -80,19 +71,49 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            submitted_answer = agent(question_text)
-            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
+            # 使用导入的搜索工具和RAG链
+            search_result = search_tool.run(question_text)
+            if rag_chain:
+                response = rag_chain.run(f"{question_text}\nSearch result: {search_result}")
+                submitted_answer = extract_final_answer(response)
+                # Format answer according to JSON-line submission requirements
+                answers_payload.append({
+                    "task_id": task_id,
+                    "model_answer": submitted_answer,
+                    "reasoning_trace": response
+                })
+            else:
+                submitted_answer = agent(question_text)
+                answers_payload.append({
+                    "task_id": task_id,
+                    "model_answer": submitted_answer
+                })
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted 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}"})
+            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}"})
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
         return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
+    # Generate JSON-line submission file
+    try:
+        with open(SUBMISSION_FILE, "w") as f:
+            for entry in answers_payload:
+                json.dump(entry, f)
+                f.write("\n")
+        print(f"Successfully generated submission file: {SUBMISSION_FILE}")
+    except Exception as e:
+        print(f"Error generating submission file: {e}")
+        return f"Error generating submission file: {e}", pd.DataFrame(results_log)
+
     # 4. Prepare Submission 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
+    submission_data = {
+        "username": username.strip(), 
+        "agent_code": agent_code, 
+        "answers": answers_payload
+    }
     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
     print(status_update)
 
@@ -107,6 +128,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             f"User: {result_data.get('username')}\n"
             f"Overall Score: {result_data.get('score', 'N/A')}% "
             f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
+            f"Submission file generated: {SUBMISSION_FILE}\n"
             f"Message: {result_data.get('message', 'No message received.')}"
         )
         print("Submission successful.")
@@ -119,51 +141,51 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
         except requests.exceptions.JSONDecodeError:
             error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
+        status_message = f"Submission Failed: {error_detail}\nSubmission file generated: {SUBMISSION_FILE}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
     except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
+        status_message = f"Submission Failed: The request timed out.\nSubmission file generated: {SUBMISSION_FILE}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
     except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
+        status_message = f"Submission Failed: Network error - {e}\nSubmission file generated: {SUBMISSION_FILE}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
+        status_message = f"An unexpected error occurred during submission: {e}\nSubmission file generated: {SUBMISSION_FILE}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
         return status_message, results_df
 
-
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# Smoal 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.
+        1. Log in to your Hugging Face account using the button below.
+        2. Make sure you have set up the required environment variables:
+           - BING_API_KEY: For web search functionality
+           - OPENAI_API_KEY: For GPT-3.5 model access
+           - HUGGINGFACE_HUB_TOKEN: For GAIA dataset access
+        3. Click 'Run Evaluation & Submit All Answers' to start the evaluation.
+
+        The agent will:
+        - Search the web for relevant information
+        - Use RAG to process and retrieve context from GAIA dataset
+        - Generate comprehensive answers
+        - Create JSON-line submission file: submission.jsonl
         """
     )
 
     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(
@@ -173,9 +195,8 @@ with gr.Blocks() as demo:
 
 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
+    space_id_startup = os.getenv("SPACE_ID")
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -183,7 +204,7 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    if space_id_startup:
         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")
@@ -192,5 +213,5 @@ if __name__ == "__main__":
 
     print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("Launching Gradio Interface for Smoal Agent Evaluation...")
     demo.launch(debug=True, share=False)

tools.py

@@ -0,0 +1,61 @@
+import os
+import re
+from langchain.tools import DuckDuckGoSearchRun
+from langchain.chains import RetrievalQA
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.prompts import PromptTemplate
+from datasets import load_dataset
+from agent import SmoalAgent
+
+# System prompt for formatting answers
+SYSTEM_PROMPT = """
+You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.
+"""
+
+# Initialize web search tool
+search_tool = DuckDuckGoSearchRun()
+
+# Create custom prompt template with system instructions
+prompt_template = SYSTEM_PROMPT + "\n\nContext: {context}\nQuestion: {question}\n"
+PROMPT = PromptTemplate(
+    template=prompt_template,
+    input_variables=["context", "question"]
+)
+
+# Load GAIA dataset and setup RAG components
+def load_gaia_and_setup_rag():
+    try:
+        # Load GAIA dataset (requires HUGGINGFACE_HUB_TOKEN)
+        dataset = load_dataset("GAIA", split="train")
+        texts = [item['text'] for item in dataset if 'text' in item]
+        
+        # Create embeddings and vector store
+        embeddings = OpenAIEmbeddings()
+        vectorstore = FAISS.from_texts(texts, embeddings)
+        
+        # Create retriever and QA chain with custom prompt
+        retriever = vectorstore.as_retriever()
+        qa_chain = RetrievalQA.from_chain_type(
+            llm=SmoalAgent(),
+            chain_type="stuff",
+            retriever=retriever,
+            chain_type_kwargs={"prompt": PROMPT}
+        )
+        return qa_chain
+    except Exception as e:
+        print(f"RAG initialization error: {str(e)}")
+        return None
+
+# Extract final answer from model response
+def extract_final_answer(response):
+    """Extracts the final answer using the specified template format"""
+    match = re.search(r"FINAL ANSWER: (.*)", response, re.IGNORECASE)
+    if match:
+        return match.group(1).strip()
+    # Fallback to return full response if pattern not found
+    return response
+
+# Initialize RAG chain
+global rag_chain
+rag_chain = load_gaia_and_setup_rag()