Update app.py

app.py

@@ -1,57 +1,127 @@
-import streamlit as st
+import os
+import gradio as gr
+import requests
+import pandas as pd
+from dotenv import load_dotenv
+
 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
-from langchain.callbacks import StreamlitCallbackHandler
-import os
-from dotenv import load_dotenv
 
-# --- Load API keys (optional if you're using a .env) ---
-load_dotenv()
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Tool setup ---
-api_wrapper_arxiv = ArxivAPIWrapper(top_k_results=1, doc_content_chars_max=250)
-arxiv = ArxivQueryRun(api_wrapper=api_wrapper_arxiv)
+api_key = "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"
 
-api_wrapper_wiki = WikipediaAPIWrapper(top_k_results=1, doc_content_chars_max=250)
-wiki = WikipediaQueryRun(api_wrapper=api_wrapper_wiki)
+# --- GAIA-compatible Agent Definition ---
+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")
 
-search = DuckDuckGoSearchRun(name="Search")
-tools = [search, arxiv, wiki]
+        # 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))
+        ]
 
-api_key = "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"
+        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"
+
+    try:
+        agent = GaiaAgent()
+    except Exception as e:
+        return f"Error initializing agent: {e}", None
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(f"Fetching questions from: {questions_url}")
 
-# --- Model setup ---
-llm = ChatGroq(groq_api_key=api_key, model_name="Llama3-8b-8192", streaming=True)
-search_agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, handle_parsing_errors=True)
+    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
 
-# -------- GAIA REQUIRED FUNCTION --------
-def run_agent(query: str) -> str:
-    """GAIA-compatible agent runner."""
-    return search_agent.run(query)
+    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}"})
 
-# -------- Streamlit App --------
-st.title("Langchain - Chat with Search")
+    if not answers_payload:
+        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
 
-st.sidebar.title("Settings")
-user_api_key = st.sidebar.text_input("Enter your Groq API Key:", type="password")
-if user_api_key:
-    llm.groq_api_key = user_api_key
+    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
+    print(f"Submitting answers to: {submit_url}")
 
-if "messages" not in st.session_state:
-    st.session_state["messages"] = [{"role": "assistant", "content": "Hi, I am a Chatbot who can search the web. How can I help you?"}]
+    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)
 
-for msg in st.session_state.messages:
-    st.chat_message(msg["role"]).write(msg["content"])
+# --- 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'.
+    """)
 
-if prompt := st.chat_input(placeholder="What is machine learning?"):
-    st.session_state.messages.append({"role": "user", "content": prompt})
-    st.chat_message("user").write(prompt)
+    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)
 
-    with st.chat_message("assistant"):
-        st_cb = StreamlitCallbackHandler(st.container(), expand_new_thoughts=False)
-        response = run_agent(prompt)
-        st.session_state.messages.append({"role": "assistant", "content": response})
-        st.write(response)
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
+if __name__ == "__main__":
+    print("Launching GAIA-compatible agent...")
+    demo.launch(debug=True, share=False)