Upload 4 files

.gitattributes

@@ -1,35 +1,35 @@
-*.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
+*.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

.gitignore

@@ -1,116 +1,116 @@
-# Byte-compiled / optimized / DLL files
-__pycache__/
-*.py[cod]
-*$py.class
-*.so
-
-# Distribution / packaging
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-
-# Virtual environments
-venv/
-ENV/
-env/
-.env
-.venv
-env.bak/
-venv.bak/
-.python-version
-
-# Unit test / coverage reports
-htmlcov/
-.tox/
-.nox/
-.coverage
-.coverage.*
-.cache
-nosetests.xml
-coverage.xml
-*.cover
-.hypothesis/
-.pytest_cache/
-pytest-*.xml
-
-# Jupyter Notebook
-.ipynb_checkpoints
-
-# IPython
-profile_default/
-ipython_config.py
-
-# Logs
-*.log
-logs/
-log/
-
-# IDE specific files
-.idea/
-.vscode/
-*.swp
-*.swo
-*~
-.DS_Store
-.project
-.pydevproject
-.settings/
-.vs/
-*.sublime-project
-*.sublime-workspace
-
-# Database
-*.db
-*.rdb
-*.sqlite
-*.sqlite3
-
-# Environment variables
-.env
-.env.local
-.env.development.local
-.env.test.local
-.env.production.local
-
-# macOS specific
-.DS_Store
-.AppleDouble
-.LSOverride
-Icon
-._*
-.DocumentRevisions-V100
-.fseventsd
-.Spotlight-V100
-.TemporaryItems
-.Trashes
-.VolumeIcon.icns
-.com.apple.timemachine.donotpresent
-
-# AI/model files
-*.h5
-*.pb
-*.onnx
-*.tflite
-*.pt
-*.pth
-*.weights
-
-# Temporary files
-tmp/
-temp/
-.tmp
-*.tmp
-
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+venv/
+ENV/
+env/
+.env
+.venv
+env.bak/
+venv.bak/
+.python-version
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+pytest-*.xml
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Logs
+*.log
+logs/
+log/
+
+# IDE specific files
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+.DS_Store
+.project
+.pydevproject
+.settings/
+.vs/
+*.sublime-project
+*.sublime-workspace
+
+# Database
+*.db
+*.rdb
+*.sqlite
+*.sqlite3
+
+# Environment variables
+.env
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+# macOS specific
+.DS_Store
+.AppleDouble
+.LSOverride
+Icon
+._*
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# AI/model files
+*.h5
+*.pb
+*.onnx
+*.tflite
+*.pt
+*.pth
+*.weights
+
+# Temporary files
+tmp/
+temp/
+.tmp
+*.tmp
+

app.py

@@ -1,302 +1,302 @@
-import os
-import gradio as gr
-import requests
-import pandas as pd
-from datetime import datetime
-from transformers import pipeline
-from langchain_community.llms import HuggingFaceTextGenInference
-from langchain.prompts import SystemMessagePromptTemplate, HumanMessagePromptTemplate, ChatPromptTemplate
-from langchain.chains import LLMChain
-from langchain.agents import Tool
-from langchain_community.utilities import DuckDuckGoSearchAPIWrapper
-from langchain_community.utilities import TextRequestsWrapper
-from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.vectorstores import Chroma
-
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-MAX_ANSWER_LENGTH = 50
-
-# --- LLM Setup ---
-# Using Hugging Face Text Generation Inference API instead of loading model locally
-# This connects to a more powerful open source model through HF's inference API
-llm = HuggingFaceTextGenInference(
-    inference_server_url="https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2",
-    max_new_tokens=256,
-    temperature=0.1,
-    repetition_penalty=1.03,
-    top_k=10,
-    top_p=0.95,
-    timeout=120,
-    streaming=False,
-    huggingface_api_key=os.getenv("HF_API_TOKEN", None),  # Set your HF API token in environment variables
-)
-
-# --- System Message ---
-system_prompt = """You are a helpful assistant tasked with answering questions using a set of tools.
-Now, 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, 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."""
-system_message_prompt = SystemMessagePromptTemplate.from_template(system_prompt)
-
-# --- Tools ---
-ddg = DuckDuckGoSearchAPIWrapper()
-requests_wrapper = TextRequestsWrapper()
-
-def wiki_search(query):
-    """Search Wikipedia for a query and return maximum 2 results."""
-    search_results = ddg.run(query)
-    return f"Wikipedia search results for '{query}': {search_results}"
-
-def web_search(query):
-    """Search DuckDuckGo for a query and return maximum 3 results."""
-    search_results = ddg.run(query)
-    return f"Web search results for '{query}': {search_results}"
-
-def arxiv_search(query):
-    """Search Arxiv for a query and return maximum 3 results."""
-    try:
-        url = f"https://export.arxiv.org/api/query?search_query=all:{query}&start=0&max_results=3"
-        response = requests_wrapper.get(url)
-        return f"Arxiv search results for '{query}': {response.text[:500]}..."  # Truncate for readability
-    except Exception as e:
-        return f"Error searching Arxiv: {str(e)}"
-
-# --- Fallback for Chroma DB if not initialized ---
-try:
-    # --- Chroma DB Setup ---
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
-    vector_store = Chroma(
-        embedding_function=embeddings,
-        persist_directory="./chroma_db"
-    )
-
-    def create_retriever_tool(query):
-        """A tool to retrieve similar questions from a vector store."""
-        try:
-            similar_question = vector_store.similarity_search(query)
-            if similar_question and len(similar_question) > 0:
-                return f"Similar question found: {similar_question[0].page_content}"
-            return "No similar questions found in the database."
-        except Exception as e:
-            return f"Error using retriever: {str(e)}"
-except Exception as e:
-    print(f"Warning: Could not initialize Chroma DB: {e}")
-    def create_retriever_tool(query):
-        return "Retriever tool is not available."
-
-# Define the tools
-tools = [
-    Tool(
-        name="Wikipedia Search",
-        func=wiki_search,
-        description="Search Wikipedia for a query and return maximum 2 results."
-    ),
-    Tool(
-        name="Web Search",
-        func=web_search,
-        description="Search DuckDuckGo for a query and return maximum 3 results."
-    ),
-    Tool(
-        name="Arxiv Search",
-        func=arxiv_search,
-        description="Search Arxiv for a query and return maximum 3 results."
-    ),
-    Tool(
-        name="Retriever",
-        func=create_retriever_tool,
-        description="A tool to retrieve similar questions from a vector store."
-    )
-]
-
-def create_agent(llm, tools):
-    """Create an agent with the specified tools."""
-    prompt = ChatPromptTemplate.from_messages([
-        system_message_prompt,
-        HumanMessagePromptTemplate.from_template("{input}")
-    ])
-    llm_chain = LLMChain(llm=llm, prompt=prompt)
-    return llm_chain
-
-def extract_final_answer(full_response):
-    """Extract only the final answer from the agent's response."""
-    if "FINAL ANSWER:" in full_response:
-        return full_response.split("FINAL ANSWER:")[1].strip()
-    return full_response.strip()
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the EnhancedAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID")
-
-    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
-
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
-
-    # 1. Instantiate Agent
-    try:
-        agent = create_agent(llm, tools)
-    except Exception as e:
-        print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
-
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
-    try:
-        response = requests.get(questions_url, timeout=15)
-        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(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 Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
-
-    # 3. Run your Agent
-    results_log = []
-    answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
-    
-    # Define a fallback answer function in case the main agent fails
-    def get_simple_answer(question):
-        """Provide a simple answer when the main agent fails"""
-        # Very basic responses for common question types
-        if "capital" in question.lower():
-            return "Unknown"
-        elif "population" in question.lower() or "how many" in question.lower():
-            return "0"
-        elif "when" in question.lower():
-            return "Unknown"
-        elif "where" in question.lower():
-            return "Unknown"
-        elif "who" in question.lower():
-            return "Unknown"
-        elif "true or false" in question.lower():
-            return "True"
-        else:
-            return "Unknown"
-    
-    for item in questions_data:
-        task_id = item.get("task_id")
-        question_text = item.get("question")
-        if not task_id or question_text is None:
-            print(f"Skipping item with missing task_id or question: {item}")
-            continue
-        
-        try:
-            print(f"Processing question: {question_text}")
-            # Get the response from the agent
-            agent_response = agent.run(question_text)
-            print(f"Agent response: {agent_response}")
-            
-            # Extract just the final answer part
-            final_answer = extract_final_answer(agent_response)
-            
-            # Make sure the answer isn't too long - truncate if needed
-            if len(final_answer) > MAX_ANSWER_LENGTH:
-                final_answer = final_answer[:MAX_ANSWER_LENGTH]
-                print(f"Warning: Answer truncated to {MAX_ANSWER_LENGTH} characters")
-            
-            # Add to payload for submission
-            answers_payload.append({"task_id": task_id, "submitted_answer": final_answer})
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": final_answer})
-            print(f"Task {task_id}: Processed answer: {final_answer}")
-        
-        except Exception as e:
-            print(f"Error running agent on task {task_id}: {e}")
-            
-            # Use fallback strategy
-            fallback_answer = get_simple_answer(question_text)
-            answers_payload.append({"task_id": task_id, "submitted_answer": fallback_answer})
-            results_log.append({
-                "Task ID": task_id, 
-                "Question": question_text, 
-                "Submitted Answer": f"{fallback_answer} (FALLBACK)"
-            })
-            print(f"Task {task_id}: Used fallback answer: {fallback_answer}")
-
-    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)
-
-    # 4. Prepare Submission
-    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)
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
-    try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
-        result_data = response.json()
-        final_status = (
-            f"Submission Successful!\n"
-            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"Message: {result_data.get('message', 'No message received.')}"
-        )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    except Exception as e:
-        status_message = f"Submission Failed: {e}"
-        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("# GAIA Evaluation Agent using Multiple Search Tools")
-    gr.Markdown(
-        """
-        **Instructions:**
-        1. Clone this space and modify the agent's logic and tools as needed.
-        2. Log in with your Hugging Face account.
-        3. Click 'Run Evaluation & Submit All Answers' to test your agent.
-        """
-    )
-
-    gr.LoginButton()
-
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    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)
-    space_id_startup = os.getenv("SPACE_ID")
-
-    if space_id_startup:
-        print(f"✅ SPACE_ID found: {space_id_startup}")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?).")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-    print("Launching Gradio Interface...")
-    demo.launch(debug=True, share=False)
+import os
+import gradio as gr
+import requests
+import pandas as pd
+from datetime import datetime
+from transformers import pipeline
+from langchain_community.llms import HuggingFaceTextGenInference
+from langchain.prompts import SystemMessagePromptTemplate, HumanMessagePromptTemplate, ChatPromptTemplate
+from langchain.chains import LLMChain
+from langchain.agents import Tool
+from langchain_community.utilities import DuckDuckGoSearchAPIWrapper
+from langchain_community.utilities import TextRequestsWrapper
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import Chroma
+
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+MAX_ANSWER_LENGTH = 50
+
+# --- LLM Setup ---
+# Using Hugging Face Text Generation Inference API instead of loading model locally
+# This connects to a more powerful open source model through HF's inference API
+llm = HuggingFaceTextGenInference(
+    inference_server_url="https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2",
+    max_new_tokens=256,
+    temperature=0.1,
+    repetition_penalty=1.03,
+    top_k=10,
+    top_p=0.95,
+    timeout=120,
+    streaming=False,
+    huggingface_api_key=os.getenv("HF_API_TOKEN", None),  # Set your HF API token in environment variables
+)
+
+# --- System Message ---
+system_prompt = """You are a helpful assistant tasked with answering questions using a set of tools.
+Now, 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, 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."""
+system_message_prompt = SystemMessagePromptTemplate.from_template(system_prompt)
+
+# --- Tools ---
+ddg = DuckDuckGoSearchAPIWrapper()
+requests_wrapper = TextRequestsWrapper()
+
+def wiki_search(query):
+    """Search Wikipedia for a query and return maximum 2 results."""
+    search_results = ddg.run(query)
+    return f"Wikipedia search results for '{query}': {search_results}"
+
+def web_search(query):
+    """Search DuckDuckGo for a query and return maximum 3 results."""
+    search_results = ddg.run(query)
+    return f"Web search results for '{query}': {search_results}"
+
+def arxiv_search(query):
+    """Search Arxiv for a query and return maximum 3 results."""
+    try:
+        url = f"https://export.arxiv.org/api/query?search_query=all:{query}&start=0&max_results=3"
+        response = requests_wrapper.get(url)
+        return f"Arxiv search results for '{query}': {response.text[:500]}..."  # Truncate for readability
+    except Exception as e:
+        return f"Error searching Arxiv: {str(e)}"
+
+# --- Fallback for Chroma DB if not initialized ---
+try:
+    # --- Chroma DB Setup ---
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+    vector_store = Chroma(
+        embedding_function=embeddings,
+        persist_directory="./chroma_db"
+    )
+
+    def create_retriever_tool(query):
+        """A tool to retrieve similar questions from a vector store."""
+        try:
+            similar_question = vector_store.similarity_search(query)
+            if similar_question and len(similar_question) > 0:
+                return f"Similar question found: {similar_question[0].page_content}"
+            return "No similar questions found in the database."
+        except Exception as e:
+            return f"Error using retriever: {str(e)}"
+except Exception as e:
+    print(f"Warning: Could not initialize Chroma DB: {e}")
+    def create_retriever_tool(query):
+        return "Retriever tool is not available."
+
+# Define the tools
+tools = [
+    Tool(
+        name="Wikipedia Search",
+        func=wiki_search,
+        description="Search Wikipedia for a query and return maximum 2 results."
+    ),
+    Tool(
+        name="Web Search",
+        func=web_search,
+        description="Search DuckDuckGo for a query and return maximum 3 results."
+    ),
+    Tool(
+        name="Arxiv Search",
+        func=arxiv_search,
+        description="Search Arxiv for a query and return maximum 3 results."
+    ),
+    Tool(
+        name="Retriever",
+        func=create_retriever_tool,
+        description="A tool to retrieve similar questions from a vector store."
+    )
+]
+
+def create_agent(llm, tools):
+    """Create an agent with the specified tools."""
+    prompt = ChatPromptTemplate.from_messages([
+        system_message_prompt,
+        HumanMessagePromptTemplate.from_template("{input}")
+    ])
+    llm_chain = LLMChain(llm=llm, prompt=prompt)
+    return llm_chain
+
+def extract_final_answer(full_response):
+    """Extract only the final answer from the agent's response."""
+    if "FINAL ANSWER:" in full_response:
+        return full_response.split("FINAL ANSWER:")[1].strip()
+    return full_response.strip()
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the EnhancedAgent on them, submits all answers,
+    and displays the results.
+    """
+    # --- Determine HF Space Runtime URL and Repo URL ---
+    space_id = os.getenv("SPACE_ID")
+
+    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
+
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+
+    # 1. Instantiate Agent
+    try:
+        agent = create_agent(llm, tools)
+    except Exception as e:
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
+
+    # 2. Fetch Questions
+    print(f"Fetching questions from: {questions_url}")
+    try:
+        response = requests.get(questions_url, timeout=15)
+        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(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 Exception as e:
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return f"An unexpected error occurred fetching questions: {e}", None
+
+    # 3. Run your Agent
+    results_log = []
+    answers_payload = []
+    print(f"Running agent on {len(questions_data)} questions...")
+    
+    # Define a fallback answer function in case the main agent fails
+    def get_simple_answer(question):
+        """Provide a simple answer when the main agent fails"""
+        # Very basic responses for common question types
+        if "capital" in question.lower():
+            return "Unknown"
+        elif "population" in question.lower() or "how many" in question.lower():
+            return "0"
+        elif "when" in question.lower():
+            return "Unknown"
+        elif "where" in question.lower():
+            return "Unknown"
+        elif "who" in question.lower():
+            return "Unknown"
+        elif "true or false" in question.lower():
+            return "True"
+        else:
+            return "Unknown"
+    
+    for item in questions_data:
+        task_id = item.get("task_id")
+        question_text = item.get("question")
+        if not task_id or question_text is None:
+            print(f"Skipping item with missing task_id or question: {item}")
+            continue
+        
+        try:
+            print(f"Processing question: {question_text}")
+            # Get the response from the agent
+            agent_response = agent.run(question_text)
+            print(f"Agent response: {agent_response}")
+            
+            # Extract just the final answer part
+            final_answer = extract_final_answer(agent_response)
+            
+            # Make sure the answer isn't too long - truncate if needed
+            if len(final_answer) > MAX_ANSWER_LENGTH:
+                final_answer = final_answer[:MAX_ANSWER_LENGTH]
+                print(f"Warning: Answer truncated to {MAX_ANSWER_LENGTH} characters")
+            
+            # Add to payload for submission
+            answers_payload.append({"task_id": task_id, "submitted_answer": final_answer})
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": final_answer})
+            print(f"Task {task_id}: Processed answer: {final_answer}")
+        
+        except Exception as e:
+            print(f"Error running agent on task {task_id}: {e}")
+            
+            # Use fallback strategy
+            fallback_answer = get_simple_answer(question_text)
+            answers_payload.append({"task_id": task_id, "submitted_answer": fallback_answer})
+            results_log.append({
+                "Task ID": task_id, 
+                "Question": question_text, 
+                "Submitted Answer": f"{fallback_answer} (FALLBACK)"
+            })
+            print(f"Task {task_id}: Used fallback answer: {fallback_answer}")
+
+    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)
+
+    # 4. Prepare Submission
+    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)
+
+    # 5. Submit
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+    try:
+        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response.raise_for_status()
+        result_data = response.json()
+        final_status = (
+            f"Submission Successful!\n"
+            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"Message: {result_data.get('message', 'No message received.')}"
+        )
+        print("Submission successful.")
+        results_df = pd.DataFrame(results_log)
+        return final_status, results_df
+    except Exception as e:
+        status_message = f"Submission Failed: {e}"
+        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("# GAIA Evaluation Agent using Multiple Search Tools")
+    gr.Markdown(
+        """
+        **Instructions:**
+        1. Clone this space and modify the agent's logic and tools as needed.
+        2. Log in with your Hugging Face account.
+        3. Click 'Run Evaluation & Submit All Answers' to test your agent.
+        """
+    )
+
+    gr.LoginButton()
+
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    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)
+    space_id_startup = os.getenv("SPACE_ID")
+
+    if space_id_startup:
+        print(f"✅ SPACE_ID found: {space_id_startup}")
+    else:
+        print("ℹ️  SPACE_ID environment variable not found (running locally?).")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("Launching Gradio Interface...")
+    demo.launch(debug=True, share=True)

main.py

@@ -0,0 +1,185 @@
+import os
+import gradio as gr
+import requests
+import pandas as pd
+from datetime import datetime
+from transformers import pipeline
+from langchain_community.llms import HuggingFaceTextGenInference
+from langchain.prompts import SystemMessagePromptTemplate, HumanMessagePromptTemplate, ChatPromptTemplate
+from langchain.chains import LLMChain
+from langchain.agents import Tool, initialize_agent, AgentType
+from langchain_community.utilities import DuckDuckGoSearchAPIWrapper
+from langchain_community.utilities import TextRequestsWrapper
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import Chroma
+
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+MAX_ANSWER_LENGTH = 50
+
+# --- LLM Setup ---
+llm = HuggingFaceTextGenInference(
+    inference_server_url="https://api-inference.huggingface.co/models/mistralai/Mistral-7B-Instruct-v0.2",
+    max_new_tokens=256,
+    temperature=0.1,
+    repetition_penalty=1.03,
+    top_k=10,
+    top_p=0.95,
+    timeout=120,
+    streaming=False,
+    huggingface_api_key=os.getenv("HF_API_TOKEN"),  # Required environment variable
+)
+
+# --- System Message ---
+system_prompt = """You are a helpful assistant tasked with answering questions using a set of tools.
+Now, 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, 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."""
+system_message_prompt = SystemMessagePromptTemplate.from_template(system_prompt)
+
+# --- Tools ---
+ddg = DuckDuckGoSearchAPIWrapper()
+requests_wrapper = TextRequestsWrapper()
+
+def wiki_search(query):
+    search_results = ddg.run(query)
+    return f"Wikipedia search results: {search_results[:2]}"  # Return max 2 results
+
+def web_search(query):
+    search_results = ddg.run(query)
+    return f"Web search results: {search_results[:3]}"  # Return max 3 results
+
+def arxiv_search(query):
+    try:
+        url = f"https://export.arxiv.org/api/query?search_query=all:{query}&start=0&max_results=3"
+        response = requests_wrapper.get(url)
+        return f"Arxiv search results: {response.text[:500]}..."  # Truncate for readability
+    except Exception as e:
+        return f"Arxiv search error: {str(e)}"
+
+# --- Chroma DB Fallback ---
+try:
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+    vector_store = Chroma(
+        embedding_function=embeddings,
+        persist_directory="./chroma_db"
+    )
+
+    def create_retriever_tool(query):
+        try:
+            similar_question = vector_store.similarity_search(query)
+            return f"Similar question: {similar_question[0].page_content}" if similar_question else "No similar questions"
+        except:
+            return "Retriever unavailable"
+except:
+    def create_retriever_tool(query):
+        return "Retriever unavailable"
+
+tools = [
+    Tool(name="Wikipedia Search", func=wiki_search, description="Search Wikipedia (max 2 results)"),
+    Tool(name="Web Search", func=web_search, description="General web search (max 3 results)"),
+    Tool(name="Arxiv Search", func=arxiv_search, description="Academic paper search"),
+    Tool(name="Retriever", func=create_retriever_tool, description="Find similar previous questions")
+]
+
+def create_agent(llm, tools):
+    """Create an agent that can use tools"""
+    return initialize_agent(
+        tools,
+        llm,
+        agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
+        verbose=True,
+        max_iterations=3,
+        handle_parsing_errors=True,
+    )
+
+def extract_final_answer(response):
+    return response.split("FINAL ANSWER:")[-1].strip() if "FINAL ANSWER:" in response else response.strip()
+
+def run_and_submit_all(profile):
+    if not profile:
+        return "Please login to Hugging Face", None
+    
+    username = profile.username
+    space_id = os.getenv("SPACE_ID", "local-test")
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    
+    try:
+        agent = create_agent(llm, tools)
+    except Exception as e:
+        return f"Agent initialization failed: {str(e)}", None
+
+    try:
+        response = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15)
+        response.raise_for_status()
+        questions = response.json()
+    except:
+        return "Failed to fetch questions", None
+
+    results = []
+    answers = []
+    
+    for q in questions:
+        task_id = q.get("task_id")
+        question = q.get("question", "")
+        
+        try:
+            answer = agent.run(question)
+            final_answer = extract_final_answer(answer)[:MAX_ANSWER_LENGTH]
+            results.append({"Task ID": task_id, "Question": question, "Answer": final_answer})
+            answers.append({"task_id": task_id, "submitted_answer": final_answer})
+        except:
+            results.append({"Task ID": task_id, "Question": question, "Answer": "ERROR"})
+            answers.append({"task_id": task_id, "submitted_answer": "ERROR"})
+
+    try:
+        submission = {
+            "username": username,
+            "agent_code": agent_code,
+            "answers": answers
+        }
+        response = requests.post(f"{DEFAULT_API_URL}/submit", json=submission, timeout=60)
+        response.raise_for_status()
+        result_data = response.json()
+        status = f"Score: {result_data.get('score', 'N/A')}% ({result_data.get('correct_count', 0)}/{len(answers)})"
+    except:
+        status = "Submission failed"
+
+    return status, pd.DataFrame(results)
+
+# --- Build Gradio Interface using Blocks ---
+with gr.Blocks() as demo:
+    gr.Markdown("# GAIA Evaluation Agent using Multiple Search Tools")
+    gr.Markdown(
+        """
+        **Instructions:**
+        1. Clone this space and modify the agent's logic and tools as needed.
+        2. Log in with your Hugging Face account.
+        3. Click 'Run Evaluation & Submit All Answers' to test your agent.
+        """
+    )
+
+    gr.LoginButton()
+
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    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)
+    space_id_startup = os.getenv("SPACE_ID")
+
+    if space_id_startup:
+        print(f"✅ SPACE_ID found: {space_id_startup}")
+    else:
+        print("ℹ️  SPACE_ID environment variable not found (running locally?).")
+
+    print("-"*(60 + len(" App Starting ")) + "\n")
+    print("Launching Gradio Interface...")
+    demo.launch(debug=True, share=True)