Upload 5 files

.gitattributes

@@ -0,0 +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

.gitignore

@@ -0,0 +1,174 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc

agent.py

@@ -0,0 +1,146 @@
+"""LangGraph Agent"""
+
+import os
+import json
+import getpass
+from dotenv import load_dotenv
+
+from langgraph.graph import START, StateGraph, MessagesState
+from langgraph.prebuilt import tools_condition, ToolNode
+
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_core.vectorstores import InMemoryVectorStore
+from langchain_core.documents import Document
+from langchain_openai import ChatOpenAI, OpenAIEmbeddings
+from langchain_ollama import ChatOllama
+
+from tools.math.multiply import multiply
+from tools.math.add import add
+from tools.math.subtract import subtract
+from tools.math.divide import divide
+from tools.math.modulus import modulus
+from tools.math.power import power
+from tools.math.square_root import square_root
+
+from tools.search.arxiv_search import arxiv_search
+from tools.search.web_search import web_search
+from tools.search.wiki_search import wiki_search
+
+from tools.file.analyze_csv_file import analyze_csv_file
+from tools.file.analyze_excel_file import analyze_excel_file
+from tools.file.analyze_image import analyze_image
+from tools.file.download_file_from_url import download_file_from_url
+from tools.file.save_content_to_file import save_content_to_file
+
+# --- Load environment variables ---
+load_dotenv()
+
+# --- Constants ---
+DATASET_PATH = "dataset/metadata.jsonl"
+SYSTEM_PROMPT_PATH = "prompts/system_prompt.txt"
+TOOLS = [
+    add,
+    subtract,
+    multiply,
+    divide,
+    modulus,
+    power,
+    square_root,
+    web_search,
+    wiki_search,
+    arxiv_search,
+    analyze_csv_file,
+    analyze_excel_file,
+    analyze_image,
+    download_file_from_url,
+    save_content_to_file,
+]
+
+
+def load_vector_store() -> InMemoryVectorStore:
+    """Load vector store with dataset examples."""
+    if not os.path.exists(DATASET_PATH):
+        raise FileNotFoundError(f"Dataset not found at {DATASET_PATH}.")
+    embeddings = OpenAIEmbeddings()
+    vector_store = InMemoryVectorStore(embeddings)
+    documents = []
+    with open(DATASET_PATH, "r", encoding="utf-8") as f:
+        for line in f:
+            entry = json.loads(line)
+            content = (
+                f"Question: {entry['Question']}\nFinal answer: {entry['Final answer']}"
+            )
+            doc = Document(page_content=content, metadata={"source": entry["task_id"]})
+            documents.append(doc)
+    vector_store.add_documents(documents)
+    return vector_store
+
+
+def get_llm(provider: str):
+    """Get LLM instance based on provider."""
+    if provider == "openai":
+        if not os.environ.get("OPENAI_API_KEY"):
+            os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter OpenAI API key: ")
+        return ChatOpenAI(model="gpt-4.1", temperature=0)
+    elif provider == "ollama":
+        return ChatOllama(model="llama3.2", temperature=0)
+    else:
+        raise ValueError("Unsupported provider: choose 'openai' or 'ollama'")
+
+
+def load_system_prompt() -> SystemMessage:
+    """Load system prompt from file."""
+    if not os.path.exists(SYSTEM_PROMPT_PATH):
+        raise FileNotFoundError(f"System prompt not found at {SYSTEM_PROMPT_PATH}.")
+    with open(SYSTEM_PROMPT_PATH, "r", encoding="utf-8") as f:
+        return SystemMessage(content=f.read())
+
+
+def build_graph(provider: str = "openai"):
+    """Build and compile the LangGraph agent."""
+    llm = get_llm(provider).bind_tools(TOOLS)
+    vector_store = load_vector_store()
+    system_msg = load_system_prompt()
+
+    def retriever(state: MessagesState):
+        """Retrieve similar examples based on user query."""
+        query = state["messages"][0].content
+        similar = vector_store.similarity_search(query, k=3)
+        if similar:
+            refs = "\n\n".join(doc.page_content for doc in similar)
+            example_msg = HumanMessage(content=f"Here are similar examples:\n\n{refs}")
+            return {"messages": [system_msg] + state["messages"] + [example_msg]}
+        return {"messages": [system_msg] + state["messages"]}
+
+    def assistant(state: MessagesState):
+        """Call LLM to generate next message."""
+        response = llm.invoke(state["messages"])
+        return {"messages": [response]}
+
+    # --- Build graph ---
+    graph = StateGraph(MessagesState)
+    graph.add_node("retriever", retriever)
+    graph.add_node("assistant", assistant)
+    graph.add_node("tools", ToolNode(TOOLS))
+
+    graph.add_edge(START, "retriever")
+    graph.add_edge("retriever", "assistant")
+    graph.add_conditional_edges("assistant", tools_condition)
+    graph.add_edge("tools", "assistant")
+
+    return graph.compile()
+
+
+def run_agent(query: str, provider: str = "openai"):
+    """Run the agent on a given query."""
+    graph = build_graph(provider)
+    messages = [HumanMessage(content=query)]
+    result = graph.invoke({"messages": messages})
+    for msg in result["messages"]:
+        msg.pretty_print()
+
+
+# --- Run locally ---
+if __name__ == "__main__":
+    user_query = input("Enter your question: ")
+    run_agent(user_query)

app.py

@@ -0,0 +1,232 @@
+import os
+import gradio as gr
+import re
+import requests
+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 ---
+class BasicAgent:
+    def __init__(self):
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        # Wrap the question in a HumanMessage from langchain_core
+        messages = [HumanMessage(content=question)]
+        messages = self.graph.invoke({"messages": messages})
+        answer = messages["messages"][-1].content
+        # Use regex to extract the answer after FINAL ANSWER:
+        match = re.search(r"FINAL ANSWER:\s*(.+)", answer, re.IGNORECASE)
+        if match:
+            final_answer = match.group(1).strip()
+            # Optionally: strip trailing explanations (e.g., if comma-separated and extra stuff is appended)
+            final_answer = (
+                final_answer.split("\n")[0].split(",")[0] if final_answer else ""
+            )
+            return final_answer
+        return 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.
+    """
+    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 ( modify this part to create your agent)
+    try:
+        agent = BasicAgent()
+    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"
+
+    # 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 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
+    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...")
+    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:
+            submitted_answer = agent(question_text)
+            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,
+                }
+            )
+        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}",
+                }
+            )
+
+    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 requests.exceptions.HTTPError as e:
+        error_detail = f"Server responded with status {e.response.status_code}."
+        try:
+            error_json = e.response.json()
+            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}"
+        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."
+        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}"
+        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}"
+        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(
+        """
+        **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

@@ -0,0 +1,20 @@
+gradio
+requests
+langchain
+langchain-community
+langchain_openai
+langchain-ollama
+langchain-core
+langchain-google-genai
+langchain-huggingface
+langchain-groq
+langchain-tavily
+langchain-chroma
+langgraph
+huggingface_hub
+arxiv
+pymupdf
+wikipedia
+pgvector
+python-dotenv
+pinecone-client