Add simple tools

.gitignore

@@ -0,0 +1,178 @@
+# 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
+
+.env
+venv/
+graph.png

README.md

@@ -12,4 +12,19 @@ hf_oauth: true
 hf_oauth_expiration_minutes: 480
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+## Environment Configuration
+
+1. Copy the `.env.template` file to `.env`:
+   ```
+   cp .env.template .env
+   ```
+
+2. Edit the `.env` file with your configuration:
+   ```
+   # OpenAI API Configuration
+   OPENAI_API_KEY=your_openai_api_key_here
+   OPENAI_API_BASE=https://api.openai.com/v1
+   OPENAI_PROXY=http://127.0.0.1:7899
+   ```

agent.py

@@ -0,0 +1,79 @@
+import os
+from typing import Annotated, Optional, TypedDict
+from langgraph.graph.message import add_messages
+from langchain_core.messages import AnyMessage, SystemMessage, HumanMessage
+from tool.files import read_file
+from tool.math import divide
+from langchain.chat_models import init_chat_model
+from langgraph.graph import StateGraph, MessagesState, START, END
+from langgraph.prebuilt import ToolNode
+
+from tool.youtube import get_video_id, youtube_transcript
+
+
+
+tools = [
+            get_video_id,
+            youtube_transcript,
+            read_file
+        ]
+
+llm_with_tools = init_chat_model(
+    model="gpt-4o",
+    model_provider="openai",
+    max_retries=2,
+    openai_api_base=os.getenv("OPENAI_API_BASE", "https://api.openai.com/v1"),
+    openai_api_key=os.getenv("OPENAI_API_KEY"),
+    openai_proxy=os.getenv("OPENAI_PROXY"),
+).bind_tools(tools)
+
+
+class State(TypedDict):
+    input_file: Optional[str]
+    messages: Annotated[list[AnyMessage], add_messages]
+
+def should_continue(state: State):
+    messages = state["messages"]
+    last_message = messages[-1]
+    if last_message.tool_calls:
+        return "tools"
+    return END
+
+
+
+def agent(state: State):
+    system_message_content = "You are a helpful assistant that can read files and calling tools to answer questions. You should output results directly, without any additional text or explanation."
+    if state["input_file"]:
+        system_message_content += f"\nYou are given a file: {state['input_file']}"
+    system_message = SystemMessage(content=system_message_content)
+    messages = [system_message] + state["messages"]
+    return {"messages": [llm_with_tools.invoke(messages)]}
+
+
+class Agent:
+    def __init__(self):
+        print("BasicAgent initialized.")
+        
+        tool_node = ToolNode(tools)
+        graph_builder = StateGraph(State)
+        graph_builder.add_node("agent", agent)
+        graph_builder.add_node("tools", tool_node)
+        
+        graph_builder.add_edge(START, "agent")
+        graph_builder.add_conditional_edges("agent", should_continue, ["tools", END])
+        graph_builder.add_edge("tools", "agent")
+        self.graph = graph_builder.compile()
+        try:
+            # Save graph visualization as PNG file
+            graph_viz = self.graph.get_graph()
+            with open("graph.png", "wb") as f:
+                f.write(graph_viz.draw_mermaid_png())
+            print("Graph visualization saved as 'graph.png'")
+        except Exception as e:
+            # Drawing requires graphviz to be installed
+            print(f"Could not save graph visualization: {str(e)}")
+            pass
+
+    def __call__(self, question: str, file_name: str|None) -> str:
+        result = self.graph.invoke({"input_file": file_name, "messages": [HumanMessage(content=question)]})
+        return result["messages"][-1].content

app.py

@@ -1,34 +1,47 @@
 import os
+from dotenv import load_dotenv
 import gradio as gr
 import requests
 import inspect
 import pandas as pd
 
-# (Keep Constants as is)
-# --- Constants ---
+from agent import Agent
+
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+DEFAULT_SPACE_ID = "yplam/Final_Assignment_Template"
 
-# --- 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 download_file(filename: str) -> str:
+    """
+    Downloads a file from the API and returns the path to the local file.
+    """
+    return None
+    if filename is None or filename == "":
+        return None
+    print(f"Downloading file: {filename}")
+    file_url = f"{DEFAULT_API_URL}/files/{filename}"
+    local_path = os.path.join(tempfile.gettempdir(), filename)
+    response = requests.get(file_url, timeout=15)
+    try:
+        with open(local_path, 'wb') as f:
+            f.write(response.content)
+        print(f"Successfully downloaded file to: {local_path}")
+        return local_path
+    except Exception as e:
+        print(f"Error downloading file {filename}: {e}")
+        return None
+    
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+def run_all( username: str|None, submit: bool = True):
     """
     Fetches all questions, runs the BasicAgent 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 not space_id:
+        space_id = DEFAULT_SPACE_ID
 
-    if profile:
-        username= f"{profile.username}"
+    if username:
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -40,7 +53,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = Agent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -76,11 +89,17 @@ 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_name = item.get("file_name") or ""
+        file_path = download_file(file_name)
         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)
+            print("-"*100)
+            print(f"Running agent on task {task_id}: {question_text}")
+            submitted_answer = agent(question_text, "")
+            print(f"Submitted answer: {submitted_answer}")
+            print("-"*100)
             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:
@@ -95,83 +114,107 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     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}."
+    
+    if submit:
+        print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
         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
+            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
+    else:
+        return "Submission skipped.", pd.DataFrame(results_log)
+
+def run_and_submit_all( profile: gr.OAuthProfile | None):
+    username = profile.username if profile else None
+    return run_all(username)
+
+
+def run_local_agent():
+    return run_all('yplam', False)
+
 
+def build_gradio_interface():
+    # --- Build Gradio Interface using Blocks ---
+    with gr.Blocks() as demo:
+        gr.Markdown("# Basic Agent Evaluation Runner")
+        gr.Markdown(
+            """
+            **Instructions:**
 
-# --- 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.
 
-        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()
 
-        ---
-        **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.
-        """
-    )
+        run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    gr.LoginButton()
+        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 = gr.Button("Run Evaluation & Submit All Answers")
+        run_button.click(
+            fn=run_and_submit_all,
+            outputs=[status_output, results_table]
+        )
+    return demo
 
-    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)
+def run_fixed_agent():
+    try:
+        agent = Agent()
+        question_text = "Examine the video at https://www.youtube.com/watch?v=1htKBjuUWec.\n\nWhat does Teal'c say in response to the question \"Isn't that hot?\""
+        answer = agent(question_text, "")
+        print(f"\nQuestion: {question_text}")
+        print(f"Answer: {answer}")
+    except Exception as e:
+        print(f"Error running agent: {e}")
 
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
 
 if __name__ == "__main__":
+    load_dotenv()
     print("\n" + "-"*30 + " App Starting " + "-"*30)
     # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
@@ -192,5 +235,11 @@ if __name__ == "__main__":
 
     print("-"*(60 + len(" App Starting ")) + "\n")
 
+    if not space_id_startup:
+        print("Running locally.")
+        run_local_agent()
+        exit()
+
     print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo = build_gradio_interface()
     demo.launch(debug=True, share=False)

requirements.txt

@@ -1,2 +1,5 @@
 gradio
-requests
+requests
+langgraph
+langchain_openai
+python-dotenv

tool/files.py

@@ -0,0 +1,5 @@
+def read_file(file_path: str) -> str:
+    """Reads the content of a file and returns it as a string."""
+    print(f"Reading file: {file_path}")
+    with open(file_path, 'r') as file:
+        return file.read()

tool/math.py

@@ -0,0 +1,3 @@
+def divide(a: int, b: int) -> float:
+    """Divide a and b - for Master Wayne's occasional calculations."""
+    return a / b

tool/youtube.py

@@ -0,0 +1,30 @@
+import os
+from youtube_transcript_api import YouTubeTranscriptApi
+from youtube_transcript_api.proxies import GenericProxyConfig
+
+def youtube_transcript(video_id: str) -> str:
+    """
+    Extracts the transcript from a YouTube video id
+    """
+    print(f"Extracting transcript from: {video_id}")
+    try:
+        ytt_api = YouTubeTranscriptApi(
+            proxy_config=GenericProxyConfig(
+                http_url=os.getenv("PROXY_URL"),
+                https_url=os.getenv("PROXY_URL"),
+            )
+        )
+        transcript = ytt_api.fetch(video_id)
+        print(f"Transcript: {transcript}")
+        return transcript
+    except Exception as e:
+        print(f"Error extracting transcript: {e}")
+        return ""
+
+def get_video_id(url: str) -> str:
+    """
+    Extracts the video id from a YouTube url
+    """
+    print(f"Extracting video id from: {url}")
+    return url.split("v=")[1]
+