replace Claude Model with Gemini

app.py

@@ -1,208 +1,138 @@
 import os
-import gradio as gr
+from typing import TypedDict, List, Dict, Any, Optional
+from langgraph.graph import StateGraph, START, END
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_core.tools import tool
+from langchain_core.messages import HumanMessage
+from langchain_core.prompts import ChatPromptTemplate
+
+# %pip install -qU duckduckgo-search langchain-community
+# pip install requests
+# pip install pandas
+# pip install pypdf
+
+
+class AgentState(TypedDict):
+    messages: List
+    current_question: str
+    final_answer: str
+
+# 1. Web Browsing
+from langchain_community.tools import DuckDuckGoSearchRun
+from langchain_community.document_loaders import ImageCaptionLoader
 import requests
-import inspect
 import pandas as pd
+from pypdf import PdfReader
 
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+@tool
+def web_search(query: str) -> str:
+    """Allows search through DuckDuckGo.
+    Args:
+        query: what you want to search
+    """
+    search = DuckDuckGoSearchRun()
+    results = search.invoke(query)
+    return "\n".join(results)
+
+@tool
+def visit_webpage(url: str) -> str:
+    """Fetches raw HTML content of a web page.
+    Args:
+        url: the webpage url
+    """
+    try:
+        response = requests.get(url, timeout=5)
+        return response.text
+    except Exception as e:
+        return f"[ERROR fetching {url}]: {str(e)}"
+
+# 4. File Reading
+@tool
+def read_file(dir: str) -> str:
+    """Read the content of the provided file
+    Args:
+        dir: the filepath
+    """
+    extension = dir.split['.'][-1]
+    if extension == 'xlsx':
+        dataframe = pd.read_excel(dir)
+        return dataframe.to_string()
+    elif extension == 'pdf':
+        reader = PdfReader(dir)
+        contents = [p.extract_text() for p in reader.pages]
+        return "\n".join(contents)
+    else:
+        with open(dir) as f:
+            return f.read()
+
+# 5. Image Open
+@tool
+def image_caption(dir: str) -> str:
+    """Understand the content of the provided image
+    Args:
+        dir: the image url link
+    """
+    loader = ImageCaptionLoader(images=[dir])
+    metadata = loader.load()
+    return metadata[0].page_content
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-from smolagents import CodeAgent, DuckDuckGoSearchTool, OpenAIServerModel, VLLMModel, HfApiModel, LiteLLMModel
+# 2. Coding
+# 3. Multi-Modality
 
+# GEMINI API Key: AIzaSyAxVUPaGJIgdxB46ZR0RWPKSjB9a63Z80o
 
+# ("human", f"Question: {question}\nReport to validate: {final_answer}")
 class BasicAgent:
     def __init__(self):
-        # model = OpenAIServerModel(model_id="gpt-4o")
-        # model = VLLMModel(model_id="HuggingFaceTB/SmolLM-135M-Instruct")
-        model = LiteLLMModel(
-            model_id="Qwen/Qwen2.5-Coder-32B-Instruct",
-            num_ctx=8192,
+        model = ChatGoogleGenerativeAI(
+            model="gemini-2.0-flash",
+            temperature=0,
+            max_tokens=None,
+            timeout=None,
+            max_retries=2,
+            google_api_key=os.getenv("GEMINI_API_KEY"),
+            # other params...
         )
-        # model = HfApiModel("Qwen/Qwen2.5-Coder-32B-Instruct")
-        self.agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=model)
+        # model = ChatAnthropic(
+        #     model="claude-3-5-sonnet-20240620",
+        #     temperature=0,
+        #     max_tokens=20000,
+        #     timeout=None,
+        #     max_retries=2,
+        #     api_key=os.getenv("ANTHROPIC_API_KEY"),
+        #     # other params...
+        # )
+        # System Prompt for few shot prompting
+        self.sys_prompt = """"
+                You are a general AI assistant. 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 separared 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 (eg. 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 put in the list is a number or a string.
+
+                There are few tools provided: web_search, visit_webpage, read_file and image_caption. 
+                Here are few examples demonstrating how to call and use the tools.
+        """
+        self.app = self.__graph_compile__()
+        tools = [web_search, visit_webpage, read_file, image_caption]
+        self.model = model.bind_tools(tools) # LLM with tools
+        # self.agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=model)
         print("BasicAgent initialized.")
+    
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = self.agent.run(question)
+        prompt_msg = [
+            ("system", self.sys_prompt),
+            ("human", f"Question: {question}")
+        ]
+        response = self.model.invoke(prompt_msg)
+        fixed_answer = response.content
         # fixed_answer = "This is a default answer."
         print(f"Agent returning fixed answer: {fixed_answer}")
         return fixed_answer
+    
+    # Maybe we no need this one
+    def __graph_compile__(self):
+        graph = StateGraph(AgentState)
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    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 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"
-    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 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)
+        pass