Added first PoC with basic Tools

.gitignore

@@ -0,0 +1,212 @@
+# 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
+
+# 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/#use-with-ide
+.pdm.toml
+
+# 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/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be added to the global gitignore or merged into this project gitignore.  For a PyCharm
+#  project, it is recommended to include the following files:
+#*.iws
+#*.iml
+#*.ipr
+
+# IntelliJ
+.idea/
+
+# VSCode
+.vscode/
+
+# Vim
+*.swp
+*.swo
+*~
+
+# Emacs
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# OS generated files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# AI/ML specific
+*.h5
+*.hdf5
+*.pkl
+*.pickle
+*.joblib
+*.model
+*.weights
+models/
+checkpoints/
+logs/
+tensorboard_logs/
+wandb/
+mlruns/
+
+# Data files
+data/
+datasets/
+*.csv
+*.json
+*.parquet
+*.feather
+*.xlsx
+*.xls
+
+# API keys and secrets
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+secrets.json
+config.json
+credentials.json
+
+# LangGraph specific
+.langgraph/
+langgraph_data/
+.langgraph_api/
+
+# Temporary files
+tmp/
+temp/
+*.tmp
+*.temp

app.py

@@ -3,22 +3,11 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
-
+from agent.basic_agent import BasicAgent
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- 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,

requirements.txt

@@ -1,2 +1,25 @@
 gradio
-requests
+requests
+langgraph
+langchain_core
+pandas
+langchain_community
+pydantic
+langchain-openai
+python-dotenv
+langgraph-prebuilt
+langgraph-sdk
+langgraph-checkpoint-sqlite
+langsmith
+notebook
+tavily-python
+wikipedia
+trustcall
+langgraph-cli[inmem]
+duckduckgo-search
+debugpy
+arxiv
+pymupdf
+smolagents
+datetime
+python-chess

src/__init__.py

@@ -0,0 +1 @@
+# src package 

src/agent/__init__.py

@@ -0,0 +1 @@
+# agent package 

src/agent/basic_agent.py

@@ -0,0 +1,59 @@
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+from langchain_openai import ChatOpenAI
+from langgraph.graph import StateGraph, START, MessagesState
+import requests
+from langgraph.prebuilt import ToolNode, tools_condition
+from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
+import os
+from dotenv import load_dotenv
+from .tools import tools
+from typing import Any
+
+load_dotenv() 
+
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+class BasicAgent:
+    def __init__(self):
+         # Load environment variables from .env file
+        self.model = ChatOpenAI(model_name="gpt-4o", temperature=0.0, api_key=os.getenv("OPENAI_API_KEY"))
+        with open("src/prompts/system.txt", "r") as file:
+            self.system_prompt = file.read()
+
+        builder = StateGraph(MessagesState)
+        builder.add_node("assistant", self.assistant)
+        builder.add_node("tools", ToolNode(tools=tools))
+        builder.add_edge(START, "assistant")
+        builder.add_conditional_edges("assistant", tools_condition)
+        builder.add_edge("tools", "assistant")
+        self.graph = builder.compile()
+        print("BasicAgent initialized.")
+    
+    def __call__(self, question: str) -> MessagesState:
+        print(f"Agent received question...")
+        message = HumanMessage(content=question)
+        answer = self.graph.invoke({"messages": [message]})
+        last_message = answer["messages"][-1]
+        if isinstance(last_message, AIMessage) and "FINAL ANSWER:" in last_message.content:
+            content = last_message.content
+            # Find the position after "FINAL ANSWER: " and return only the text after it
+            final_answer_pos = content.find("FINAL ANSWER:") + len("FINAL ANSWER:")
+            return content[final_answer_pos:].strip()
+            
+        return "I'm sorry, I can't answer that question."
+    
+    def download_file(self, task_id: str) -> Any:
+        api_url = DEFAULT_API_URL
+        file_url = f"{api_url}/files/{task_id}"
+        response = requests.get(file_url)
+        return response.content
+    
+    def assistant(self, state: MessagesState):
+        """
+        This function takes a question and returns a list of sub-tasks.
+        """
+        sys_msg = SystemMessage(content=self.system_prompt)
+        llm_with_tools = self.model.bind_tools(tools, parallel_tool_calls=False)
+        state["messages"] = [sys_msg] + state["messages"]
+        return { "messages": [llm_with_tools.invoke(state["messages"])] }

src/agent/tools.py

@@ -0,0 +1,4 @@
+from .tools import tools, math_tools, web_tools, coding_tools
+
+# Re-export for backward compatibility
+__all__ = ['tools', 'math_tools', 'web_tools', 'coding_tools']

src/agent/tools/__init__.py

@@ -0,0 +1,8 @@
+from .math_tools import math_tools
+from .web_tools import web_tools
+
+# Consolidate all tools into a single exportable array
+tools = web_tools + math_tools
+
+# For backward compatibility, also export individual tool categories
+__all__ = ['tools', 'math_tools', 'web_tools'] 

src/agent/tools/coding_tools.py

@@ -0,0 +1,15 @@
+from langchain_core.tools import tool
+from smolagents import CodeAgent, HfApiModel
+
+
+imports = ['datetime', 'pandas', 'numpy', 'python-chess', 'set', 'math']
+agent = CodeAgent(tools=[], model=HfApiModel(), additional_authorized_imports=imports, max_steps=10,)
+
+@tool
+def code_agent(question: str) -> str:
+    """
+    A tool that can be used to code a solution to a problem.
+    Args:
+        question (str): The question to code a solution to.
+    """
+    return agent.run(question)

src/agent/tools/math_tools.py

@@ -0,0 +1,86 @@
+import cmath
+from langchain_core.tools import tool
+
+
+@tool
+def multiply(a: float, b: float) -> float:
+    """
+    Multiplies two numbers.
+    Args:
+        a (float): the first number
+        b (float): the second number
+    """
+    return a * b
+
+
+@tool
+def add(a: float, b: float) -> float:
+    """
+    Adds two numbers.
+    Args:
+        a (float): the first number
+        b (float): the second number
+    """
+    return a + b
+
+
+@tool
+def subtract(a: float, b: float) -> int:
+    """
+    Subtracts two numbers.
+    Args:
+        a (float): the first number
+        b (float): the second number
+    """
+    return a - b
+
+
+@tool
+def divide(a: float, b: float) -> float:
+    """
+    Divides two numbers.
+    Args:
+        a (float): the first float number
+        b (float): the second float number
+    """
+    if b == 0:
+        raise ValueError("Cannot divided by zero.")
+    return a / b
+
+
+@tool
+def modulus(a: int, b: int) -> int:
+    """
+    Get the modulus of two numbers.
+    Args:
+        a (int): the first number
+        b (int): the second number
+    """
+    return a % b
+
+
+@tool
+def power(a: float, b: float) -> float:
+    """
+    Get the power of two numbers.
+    Args:
+        a (float): the first number
+        b (float): the second number
+    """
+    return a**b
+
+
+@tool
+def square_root(a: float) -> float | complex:
+    """
+    Get the square root of a number.
+    Args:
+        a (float): the number to get the square root of
+    """
+    if a >= 0:
+        return a**0.5
+    return cmath.sqrt(a)
+
+
+# Export all math tools
+math_tools = [multiply, add, subtract, divide, modulus, power, square_root] 

src/agent/tools/web_tools.py

@@ -0,0 +1,52 @@
+from langchain_core.tools import tool
+from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
+from langchain_community.tools import TavilySearchResults
+
+
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for a query and return maximum 2 results.
+    Args:
+        query: The search query."""
+    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+            for doc in search_docs
+        ]
+    )
+    return formatted_search_docs
+
+
+@tool
+def web_search(query: str) -> str:
+    """Search Tavily for a query and return maximum 3 results.
+    Args:
+        query: The search query."""
+    search_docs = TavilySearchResults(max_results=3).invoke({"query": query})
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.get("url", "Unknown")}" title="{doc.get("title", "")}"/>\n{doc.get("content", "")}\n</Document>'
+            for doc in search_docs
+        ]
+    )
+    return formatted_search_docs
+
+
+@tool
+def scientific_paper_search(query: str) -> str:
+    """Search Arxiv for scientific papers and publications and return maximum 3 results.
+    Args:
+        query: The search query."""
+    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document title="{doc.metadata.get("Title", "")}" authors="{doc.metadata.get("Authors", "")}" published="{doc.metadata.get("Published", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in search_docs
+        ]
+    )
+    return formatted_search_docs
+
+
+# Export all web tools
+web_tools = [web_search, scientific_paper_search] 

src/prompts/system.txt

@@ -0,0 +1,19 @@
+You are a helpful assistant that answers questions that requires one or multiple tools to answer.
+You are given a question and sometimes a file. You will finish your answer with the following template:
+<template>
+FINAL ANSWER: <your final answer>
+</template>
+You need to use the file to answer the question if it is provided.
+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.
+Your answer should only start with "FINAL ANSWER: ", then follows with the answer.
+
+Before selecting a tool, ALWAYS plan and decompose the question into sub-tasks. This will help you to select all the tools necessary to give a more accurate answer.
+
+You have a suite of tools available:
+<tools>
+- `web_tools`:
+    - web_search: For searching the web
+    - scientific_paper_search: For searching for scientific papers or articles
+- `math_tools`: Contains a suite of basic algebraic tools
+- `coding_tools`: For executing especific code. This is general purpose but also useful for analyzing .xlsx or .csv data, and also it has a chess engine.
+</tools>

test_agent.py

@@ -0,0 +1,31 @@
+#!/usr/bin/env python3
+"""
+Test script for the BasicAgent
+"""
+import sys
+import os
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Add the project root to the Python path
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+
+from src.agent.basic_agent import BasicAgent
+
+agent = BasicAgent()
+graph = agent.graph
+
+def main():
+    print("Testing BasicAgent...")
+    
+    # Create the agent
+    agent = BasicAgent()
+    
+    # Run the agent
+    answer = agent("On June 6, 2023, an article by Carolyn Collins Petersen was published in Universe Today. This article mentions a team that produced a paper about their observations, linked at the bottom of the article. Find this paper. Under what NASA award number was the work performed by R. G. Arendt supported by?")
+    print(f"Final answer: {answer}")
+
+if __name__ == "__main__":
+    main()