push changes

.gitignore

@@ -0,0 +1 @@
+.env 

agent_tools.py

@@ -0,0 +1,215 @@
+# %%
+from io import BytesIO
+import requests
+from PIL import Image as PILImage
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from langchain_core.messages import AnyMessage, HumanMessage, AIMessage
+from huggingface_hub import list_models
+import random
+import pprint
+from langchain_community.tools import DuckDuckGoSearchRun
+from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
+from langgraph.prebuilt import tools_condition
+from langgraph.graph import START, StateGraph
+from IPython.display import Image, display
+
+from langgraph.prebuilt import ToolNode
+from langchain_core.messages import AnyMessage, HumanMessage, AIMessage, SystemMessage
+from langgraph.graph.message import add_messages
+from typing import TypedDict, Annotated
+from langchain.tools import Tool
+from langchain_community.retrievers import BM25Retriever
+from langchain.docstore.document import Document
+import datasets
+from langchain_openai import ChatOpenAI
+from dotenv import load_dotenv
+import os
+import torch
+import base64
+
+# Load environment variables
+load_dotenv()
+
+# DEFINE HUB STAT TOOLS
+
+
+def get_hub_stats(author: str) -> str:
+    """Fetches the most downloaded model from a specific author on the Hugging Face Hub."""
+    try:
+        # List models from the specified author, sorted by downloads
+        models = list(list_models(
+            author=author, sort="downloads", direction=-1, limit=1))
+
+        if models:
+            model = models[0]
+            return f"The most downloaded model by {author} is {model.id} with {model.downloads:,} downloads."
+        else:
+            return f"No models found for author {author}."
+    except Exception as e:
+        return f"Error fetching models for {author}: {str(e)}"
+
+
+# Initialize the tool
+hub_stats_tool = Tool(
+    name="get_hub_stats",
+    func=get_hub_stats,
+    description="Search HuggingFace Hub for model statistics, downloads, and author information. Use this when asking about specific models, authors, or HuggingFace Hub data."
+)
+
+# DEFINE WEB SEARCH TOOLS
+web_search_tool = Tool(
+    name="search_tool",
+    func=DuckDuckGoSearchRun(),
+    description="Search the general web for current information, news, and general knowledge. Use this for questions about companies, people, events, etc."
+)
+
+# REVERSE TOOLS
+
+
+def ReverseTextTool(text: str) -> str:
+    """Reverses the order of characters in a given text string."""
+    try:
+        return text[::-1]
+    except Exception as e:
+        return f"Error reversing text: {str(e)}"
+
+
+reverse_text_tool = Tool(
+    name="reverse_text_tool",
+    func=ReverseTextTool,
+    description="Reverses the order of characters in a given text string. Use this when you need to reverse text."
+)
+
+# DOWNLOAD A FILE
+
+
+def download_file(url: str) -> str:
+    """Downloads a file from a given URL and returns the local file path."""
+    try:
+        response = requests.get(url, timeout=30)
+        response.raise_for_status()
+
+        # Define save_path - extract filename from URL
+        filename = url.split(
+            '/')[-1] if url.split('/')[-1] else 'downloaded_file'
+        save_path = f"./{filename}"
+
+        with open(save_path, "wb") as f:
+            f.write(response.content)
+        return save_path
+    except Exception as e:
+        return f"Failed to download: {e}"
+
+
+download_file_tool = Tool(
+    name="download_file_tool",
+    func=download_file,
+    description="Downloads a file from a given URL and returns the local file path."
+)
+
+# DEFINE IMAGE RECOGNITION TOOLS
+
+
+def create_vision_llm():
+    """Creates a vision-capable LLM with proper error handling."""
+    try:
+        # Check if OpenAI API key is available
+        if not os.getenv("OPENAI_API_KEY"):
+            return None, "OpenAI API key not found. Please set OPENAI_API_KEY in your environment variables."
+
+        vision_llm = ChatOpenAI(model="gpt-4o")
+        return vision_llm, None
+    except Exception as e:
+        return None, f"Error creating vision LLM: {str(e)}"
+
+
+def image_recognition(img_path: str) -> str:
+    """Analyzes and describes the content of images using AI vision."""
+    try:
+        # Check if file exists
+        if not os.path.exists(img_path):
+            return f"Error: Image file not found at {img_path}"
+
+        # Create vision LLM
+        vision_llm, error = create_vision_llm()
+        if error:
+            return error
+
+        # Read image and encode as base64
+        with open(img_path, "rb") as image_file:
+            image_bytes = image_file.read()
+
+        image_base64 = base64.b64encode(image_bytes).decode("utf-8")
+
+        # Prepare the prompt including the base64 image data
+        message = [
+            HumanMessage(
+                content=[
+                    {
+                        "type": "text",
+                        "text": (
+                            "Describe the image or extract all the text from this image. "
+                            "Return only the description or extracted text, no explanations."
+                        ),
+                    },
+                    {
+                        "type": "image_url",
+                        "image_url": {
+                            "url": f"data:image/png;base64,{image_base64}"
+                        },
+                    },
+                ]
+            )
+        ]
+
+        # Call the vision-capable model
+        response = vision_llm.invoke(message)
+        return response.content.strip()
+
+    except Exception as e:
+        return f"Error analyzing image: {str(e)}"
+
+
+image_recognition_tool = Tool(
+    name="image_recognition_tool",
+    func=image_recognition,
+    description="Analyzes and describes the content of images using AI vision. Use this when you need to understand what's in an image."
+)
+
+# Test functions (commented out to avoid side effects)
+
+
+def test_tools():
+    """Test all tools to ensure they work properly."""
+    print("Testing Hub Stats Tool:")
+    print(hub_stats_tool.invoke("google"))
+    print("\n" + "="*50 + "\n")
+
+    print("Testing Web Search Tool:")
+    results = web_search_tool.invoke("what is the matrix?")
+    pp = pprint.PrettyPrinter()
+    print(pp.pprint(results))
+    print("\n" + "="*50 + "\n")
+
+    print("Testing Reverse Text Tool:")
+    results = reverse_text_tool.invoke("what is the matrix?")
+    print(results)
+    print("\n" + "="*50 + "\n")
+
+    print("Testing Download File Tool:")
+    test_url = "https://www.google.com"
+    results = download_file_tool.invoke(test_url)
+    print(results)
+    print("\n" + "="*50 + "\n")
+
+    print("Testing Image Recognition Tool:")
+    test_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/1200px-Cat03.jpg"
+    downloaded_file = download_file_tool.invoke(test_url)
+    if not downloaded_file.startswith("Failed"):
+        results = image_recognition_tool.invoke(downloaded_file)
+        print(results)
+    else:
+        print("Skipping image recognition test due to download failure")
+
+# Uncomment the line below to run tests
+# test_tools()

app.py

@@ -3,32 +3,111 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from langchain_openai import ChatOpenAI
+from langchain_core.messages import AnyMessage, HumanMessage, AIMessage, SystemMessage
+from langgraph.graph import START, StateGraph
+from langgraph.prebuilt import ToolNode, tools_condition
+from langgraph.graph.message import add_messages
+from typing import TypedDict, Annotated
+from agent_tools import image_recognition_tool, download_file_tool, reverse_text_tool, hub_stats_tool, web_search_tool
 
 # (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 ------
+# Setting up the llm
+llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
+tools = [web_search_tool, hub_stats_tool, download_file_tool,
+         image_recognition_tool, reverse_text_tool]
+chat_with_tools = llm.bind_tools(tools)
+
+# Defining my agent
+
+
+class MyAgent(TypedDict):
+    messages: Annotated[list[AnyMessage], add_messages]
+
+
 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):
+        # Use the LangGraph agent to process the question
+        try:
+            result = my_agent.invoke(
+                {"messages": [HumanMessage(content=question)]})
+            # Get the last message from the result
+            last_message = result["messages"][-1]
+            answer = last_message.content
+            print(f"Agent returning answer: {answer}")
+            return answer
+        except Exception as e:
+            print(f"Error in agent processing: {e}")
+            return f"Error processing question: {e}"
+
+# set the main system prompt
+
+
+def assistant(state: MyAgent):
+    # Add system message to instruct the agent to use the tool
+    system_message = SystemMessage(content="""You are a general AI assistant. I will ask you a question.
+Report your thoughts, and finish your answer with just the answer — no prefixes like "FINAL ANSWER:".
+Your answer should be a number OR as few words as possible OR a comma-separated list of numbers and/or strings.
+If you're asked for a number, don't use commas or units like $ or %, unless specified.
+If you're asked for a string, don't use articles or abbreviations (e.g. for cities), and write digits in plain text unless told otherwise.
+
+    Tool Use Guidelines:
+    1. Do **not** use any tools outside of the provided tools list.
+    2. Always use **only one tool at a time** in each step of your execution.
+    3. For HuggingFace Hub information (models, authors, downloads), use **get_hub_stats** tool.    
+    4. For web searches and current information, use **web_search_tool** .
+    5. If the question looks reversed (starts with a period or reads backward), first use **reverse_text_tool** to reverse it, then process the question.
+    6. When you need to download files from URLs, use **download_file_tool**.
+    7. For image analysis and description, use **image_recognition_tool** (requires OpenAI API key).
+    8. Even for complex tasks, assume a solution exists. If one method fails, try another approach using different tools.
+    9. Keep responses concise and efficient.""")
+
+    # Combine system message with user messages
+    all_messages = [system_message] + state["messages"]
+
+    return {
+        "messages": [chat_with_tools.invoke(all_messages)],
+    }
+
+
+# define the agent graph
+builder = StateGraph(MyAgent)
+
+# Define nodes: these do the work
+builder.add_node("assistant", assistant)
+builder.add_node("tools", ToolNode(tools))
+
+# Define edges: these determine how the control flow moves
+builder.add_edge(START, "assistant")
+builder.add_conditional_edges(
+    "assistant",
+    tools_condition,
+)
+builder.add_edge("tools", "assistant")
+my_agent = builder.compile()
+
+# submit
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Fetches all questions, runs MyAgent 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
+    # Get the SPACE_ID for sending link to the code
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -55,16 +134,16 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         response.raise_for_status()
         questions_data = response.json()
         if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
+            print("Fetched questions list is empty.")
+            return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
     except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+        return f"Error decoding server response for questions: {e}", None
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
@@ -81,18 +160,22 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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})
+            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}"})
+            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}
+    # 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)
 
@@ -162,9 +245,11 @@ with gr.Blocks() as demo:
 
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    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)
+    results_table = gr.DataFrame(
+        label="Questions and Agent Answers", wrap=True)
 
     run_button.click(
         fn=run_and_submit_all,
@@ -175,22 +260,24 @@ if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
     # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")  # 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")
+        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
+    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")
+        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)
+    demo.launch(debug=True, share=False)

tools.py

@@ -169,4 +169,4 @@ test_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/3/3a/Cat03.jpg/
 results = image_recognition_tool.invoke(download_file_tool.invoke(test_url))
 print(results)
 
-# testing
+