Update app.py

app.py

@@ -1,127 +1,59 @@
-import os
-import gradio as gr
-import requests
-import pandas as pd
-from dotenv import load_dotenv
+api_key = "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"
 
-from langchain_groq import ChatGroq
-from langchain_community.utilities import ArxivAPIWrapper, WikipediaAPIWrapper
-from langchain_community.tools import ArxivQueryRun, WikipediaQueryRun, DuckDuckGoSearchRun
-from langchain.agents import initialize_agent, AgentType
+import argparse
+import streamlit as st
+from langchain.agents import create_tool_calling_agent, AgentExecutor
+from langchain_core.runnables import Runnable
+from crewai_tools import ScrapeWebsiteTool
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_community.chat_models import ChatLiteLLM
+from litellm import completion
+import importlib
+
+# Define your custom LLM wrapper class
+class CustomLLM(ChatLiteLLM):
+    def __init__(self):
+        super().__init__(model="gpt-4")
 
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+    def _call(self, prompt: str, stop=None):
+        response = completion(model="gpt-4", messages=[{"role": "user", "content": prompt}])
+        return response.choices[0].message["content"]
 
-api_key = "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"
-
-# --- GAIA-compatible Agent Definition ---
+# Define your agent class
 class GaiaAgent:
     def __init__(self):
-        load_dotenv()
-        self.api_key = os.getenv("GROQ_API_KEY") or "your_fallback_key"
-        self.llm = ChatGroq(groq_api_key=self.api_key, model_name="Llama3-8b-8192")
+        self.llm = CustomLLM()
+
+        self.prompt = ChatPromptTemplate.from_messages([
+            ("system", "You are a helpful assistant."),
+            MessagesPlaceholder(variable_name="chat_history"),
+            ("human", "{input}"),
+            MessagesPlaceholder(variable_name="agent_scratchpad"),
+        ])
 
-        # Define tools
         self.tools = [
-            DuckDuckGoSearchRun(name="Search"),
-            ArxivQueryRun(api_wrapper=ArxivAPIWrapper(top_k_results=1, doc_content_chars_max=250)),
-            WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(top_k_results=1, doc_content_chars_max=250))
+            ScrapeWebsiteTool()
         ]
 
-        self.agent = initialize_agent(
-            self.tools,
-            self.llm,
-            agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
-            handle_parsing_errors=True
-        )
-
-    def __call__(self, question: str) -> str:
-        try:
-            return self.agent.run(question)
-        except Exception as e:
-            return f"[ERROR] {str(e)}"
-
-# --- Evaluation Logic ---
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    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
-
-    questions_url = f"{DEFAULT_API_URL}/questions"
-    submit_url = f"{DEFAULT_API_URL}/submit"
+        self.agent: Runnable = create_tool_calling_agent(self.llm, self.tools, self.prompt)
+        self.agent_executor: AgentExecutor = AgentExecutor(agent=self.agent, tools=self.tools, verbose=True)
 
-    try:
-        agent = GaiaAgent()
-    except Exception as e:
-        return f"Error initializing agent: {e}", None
+    def run(self):
+        st.title("🧠 GAIA-compatible Agent")
+        user_input = st.text_input("Enter your query")
+        if user_input:
+            response = self.agent_executor.invoke({"input": user_input})
+            st.write("Response:", response)
 
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(f"Fetching questions from: {questions_url}")
-
-    try:
-        response = requests.get(questions_url, timeout=15)
-        response.raise_for_status()
-        questions_data = response.json()
-    except Exception as e:
-        return f"Error fetching questions: {e}", None
-
-    results_log = []
-    answers_payload = []
-    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:
-            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:
-            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
-
-    if not answers_payload:
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
-
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    print(f"Submitting 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.')}"
-        )
-        return final_status, pd.DataFrame(results_log)
-    except Exception as e:
-        return f"Submission Failed: {e}", pd.DataFrame(results_log)
-
-# --- Gradio UI ---
-with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown("""
-    **Instructions:**
-    1. Modify `GaiaAgent` to implement your logic.
-    2. Log in to your Hugging Face account below.
-    3. Click 'Run Evaluation & Submit All Answers'.
-    """)
-
-    gr.LoginButton()
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+# Main CLI-compatible entry point
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--import", type=str, required=False, help="Module to import (ignored for static agent)")
+    parser.add_argument("--class", type=str, required=False, help="Class name to instantiate (ignored for static agent)")
+    parser.add_argument("--device", type=str, default="cpu", help="Device type (not used in this agent)")
+    args = parser.parse_args()
 
-    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
+    # Directly instantiate and run the predefined GaiaAgent class
+    agent = GaiaAgent()
+    agent.run()
 
-if __name__ == "__main__":
-    print("Launching GAIA-compatible agent...")
-    demo.launch(debug=True, share=False)