File size: 5,444 Bytes
10e9b7d
 
eccf8e4
ed08848
 
 
fbae0df
ed08848
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10e9b7d
3db6293
e80aab9
fb741d6
 
3c4371f
7e4a06b
fb741d6
3c4371f
7e4a06b
3c4371f
7d65c66
3c4371f
7e4a06b
31243f4
 
e80aab9
d2f6b32
987f2c6
 
 
 
 
 
 
31243f4
7d65c66
31243f4
7d65c66
fb741d6
e80aab9
7d65c66
 
fb741d6
 
31243f4
 
 
 
 
 
fb741d6
987f2c6
 
 
 
 
 
 
 
fb741d6
 
 
 
 
 
 
31243f4
fb741d6
31243f4
 
 
 
fb741d6
 
 
 
 
7b248e2
e80aab9
7d65c66
e80aab9
 
31243f4
e80aab9
 
3c4371f
 
 
e80aab9
987f2c6
 
7d65c66
fb741d6
7b248e2
e80aab9
d3eacbd
987f2c6
 
 
 
 
 
 
 
 
 
 
 
e80aab9
 
3c4371f
 
fb741d6
7d65c66
3c4371f
 
7d65c66
3c4371f
7d65c66
 
fb741d6
7d65c66
 
 
 
987f2c6
7d65c66
3c4371f
 
31243f4
fb741d6
d3eacbd
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
import os
import gradio as gr
import requests
import pandas as pd
import subprocess
import sys # Import sys

# --- START: Force DDGS installation workaround ---
try:
    # Check if duckduckgo_search (provided by ddgs) can be imported
    import duckduckgo_search
    print("duckduckgo_search (via ddgs) is already installed.")
except ImportError:
    print("duckduckgo_search not found. Attempting to install ddgs...")
    try:
        # Use ddgs as it's the updated package name
        subprocess.check_call([sys.executable, "-m", "pip", "install", "ddgs>=4.0.0"])
        print("ddgs installed successfully.")
    except Exception as e:
        print(f"Failed to install ddgs: {e}")
        # Critical error, re-raise to stop startup if essential dependency fails
        raise RuntimeError(f"CRITICAL: Failed to install ddgs: {e}")
# --- END: Force DDGS installation workaround ---

from agent import GaiaAgent # This line should now run after ddgs is confirmed installed

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 = GaiaAgent()
    except Exception as e:
        return f"Error initializing agent: {e}", None

    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"

    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 = []

    print("\n--- STARTING AGENT RUN ---")
    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:
            final_answer, trace = agent(question_text)

            print("\n--- QUESTION ---")
            print(f"Task ID: {task_id}")
            print(f"Question: {question_text}")
            print("\n--- REASONING TRACE ---")
            print(trace)
            print("\n--- FINAL ANSWER (SUBMITTED) ---")
            print(final_answer)

            answers_payload.append({
                "task_id": task_id,
                "submitted_answer": final_answer,
                "reasoning_trace": trace
            })
            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": final_answer})
        except Exception as e:
            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"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
    }

    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.')}"
        )
        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 Submission Interface")
    gr.Markdown("""
        Logga in och kör agenten.\n
        Du behöver INTE en OpenAI API-nyckel längre. Agenten kör en lokal modell.
    """)
    gr.LoginButton()

    run_button = gr.Button("Run Evaluation & Submit All Answers")
    status_output = gr.Textbox(label="Submission Result")
    results_table = gr.DataFrame(label="Answers")

    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])

if __name__ == "__main__":
    print("\n" + "-"*30 + " App Starting " + "-"*30)
    space_host_startup = os.getenv("SPACE_HOST")
    space_id_startup = os.getenv("SPACE_ID")

    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(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)