Upload 3 files

agent.py

@@ -0,0 +1,51 @@
+from transformers import pipeline
+from duckduckgo_search import DDGS
+import os
+
+class BasicAgent:
+    def __init__(self):
+        model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+        print(f"Loading model: {model_id}")
+        self.llm = pipeline(
+            "text-generation",
+            model=model_id,
+            token=os.getenv("HF_TOKEN"),
+            model_kwargs={"temperature": 0.2, "max_new_tokens": 200}
+        )
+
+    def search(self, query: str) -> str:
+        try:
+            with DDGS() as ddgs:
+                results = list(ddgs.text(query, max_results=1))
+                if results:
+                    return results[0]["body"]
+        except Exception as e:
+            print(f"Search failed: {e}")
+        return ""
+
+    def __call__(self, question: str) -> str:
+        context = self.search(question)
+        system_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 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 on whether the element to be put in the list is a number or a string."
+        )
+        prompt = f"{system_prompt}
+
+Context: {context}
+
+Question: {question}
+Answer:"
+        try:
+            result = self.llm(prompt)[0]["generated_text"]
+            if "FINAL ANSWER:" in result:
+                answer = result.split("FINAL ANSWER:")[-1].strip().split("\n")[0]
+                return answer.lower().strip(" .")
+            else:
+                return "unknown"
+        except Exception as e:
+            print(f"LLM error: {e}")
+            return "unknown"

app.py

@@ -0,0 +1,90 @@
+import os
+import gradio as gr
+import requests
+import inspect
+import pandas as pd
+from agent import BasicAgent
+
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+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
+
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+
+    try:
+        agent = BasicAgent()
+    except Exception as e:
+        print(f"Error instantiating agent: {e}")
+        return f"Error initializing agent: {e}", None
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
+
+    try:
+        response = requests.get(questions_url, timeout=15)
+        response.raise_for_status()
+        questions_data = response.json()
+        if not questions_data:
+            return "Fetched questions list is empty or invalid format.", None
+        print(f"Fetched {len(questions_data)} questions.")
+    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 {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!
+"
+            f"User: {result_data.get('username')}
+"
+            f"Overall Score: {result_data.get('score', 'N/A')}% "
+            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)
+"
+            f"Message: {result_data.get('message', 'No message received.')}"
+        )
+        results_df = pd.DataFrame(results_log)
+        return final_status, results_df
+    except Exception as e:
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
+
+with gr.Blocks() as demo:
+    gr.Markdown("# GAIA Agent (Transformers + Search)")
+    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)
+
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
+
+if __name__ == "__main__":
+    demo.launch(debug=True)

requirements.txt

@@ -0,0 +1,6 @@
+transformers
+duckduckgo-search
+pandas
+gradio
+torch
+accelerate