File size: 4,852 Bytes
09fd315
 
 
 
 
476b409
 
09fd315
10e9b7d
3c4371f
09fd315
 
 
 
 
476b409
 
10e9b7d
151e8da
09fd315
 
151e8da
09fd315
 
39f4053
09fd315
 
 
39f4053
09fd315
 
4021bf3
b8517f0
 
 
 
 
7e4a06b
b8517f0
 
 
 
324b202
b8517f0
 
 
324b202
476b409
0a8fce8
324b202
b8517f0
64e1e58
324b202
476b409
 
ed82cd0
64e1e58
 
b8517f0
476b409
e80aab9
 
 
 
31243f4
0ee0419
e514fd7
 
 
64e1e58
 
 
e514fd7
 
 
324b202
476b409
324b202
e514fd7
e80aab9
 
7e4a06b
e80aab9
09fd315
64e1e58
 
e80aab9
09fd315
 
 
 
e80aab9
09fd315
324b202
09fd315
 
324b202
09fd315
 
9ff29f9
09fd315
e80aab9
 
 
3c4371f
7d65c66
3c4371f
09fd315
7d65c66
3c4371f
 
09fd315
 
3c4371f
7d65c66
 
09fd315
7d65c66
 
09fd315
 
7d65c66
 
 
3c4371f
 
31243f4
09fd315
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
from opentelemetry.sdk.trace.export import SimpleSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from openinference.instrumentation.smolagents import SmolagentsInstrumentor
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry import trace
from evaluator import Evaluator
from runner import Runner
from settings import Settings
import os
import pandas as pd
import gradio as gr
import logging
logging.basicConfig(level=logging.INFO, force=True)
logger = logging.getLogger(__name__)
settings = Settings()
evaluator = Evaluator(settings)
runner = Runner(settings)


# Create a TracerProvider for OpenTelemetry
trace_provider = TracerProvider()

# Add a SimpleSpanProcessor with the OTLPSpanExporter to send traces
trace_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter()))

# Set the global default tracer provider
trace.set_tracer_provider(trace_provider)
tracer = trace.get_tracer(__name__)

# Instrument smolagents with the configured provider
SmolagentsInstrumentor().instrument(tracer_provider=trace_provider)

def user_logged_in(profile: gr.OAuthProfile):
    if profile:
        username= f"{profile.username}"
        print(f"User logged in: {username}")
        return True
    else:
        print("User not logged in.")
        return False
        
LOGIN_MESSAGE = "Please Login to Hugging Face with the button."
EMPTY_RESULTS_TABLE = pd.DataFrame(columns=['task_id', 'question', 'answer'])

def run_one(profile: gr.OAuthProfile | None) -> pd.DataFrame:
    if not user_logged_in(profile): 
        return LOGIN_MESSAGE, EMPTY_RESULTS_TABLE
    questions = [evaluator.get_one_question()]
    return "Answer one random question...", runner.run_agent(questions)

def run_all(profile: gr.OAuthProfile | None) -> pd.DataFrame:
    if not user_logged_in(profile): 
        return LOGIN_MESSAGE, EMPTY_RESULTS_TABLE
    questions = evaluator.get_questions()
    return "Answer all 20 questions...", runner.run_agent(questions)

def submit(profile: gr.OAuthProfile | None):
    if not user_logged_in(profile): 
        return LOGIN_MESSAGE
    evaluator.submit_answers()


# --- Build Gradio Interface using Blocks ---
with gr.Blocks() as demo:
    gr.Markdown("# Basic Agent Evaluation Runner")
    gr.Markdown(
        """
        **Instructions:**

        1.  Log in to your Hugging Face account using the button below. 
        2.  Click 'Get One Answer' to run the agent on a random question or 'Get All Answers' to run all. 
        3.  Click 'Submit Answers' to submit answers for evaluation. This will NOT submit your HF username.

        ---
        **Disclaimers:**
        Once clicking 'Get All Answers', it can take quite some time (this is the time for the agent to go through all 20 questions).
        The agent(s) will run question tasks in parallel making the logs hard to follow. Langfuse instrumentation has been configured. 
        The 'Submit All Answers' button will use the most recent agent answers cached in the space for your username.
        """
    )

    gr.LoginButton()

    run_one_button = gr.Button("Get One Answer")
    run_all_button = gr.Button("Get All Answers")
    submit_button = gr.Button("Submit 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_one_button.click(
        fn=run_one, outputs=[status_output, results_table]
    )
    run_all_button.click(
        fn=run_all, outputs=[status_output, results_table]
    )
    submit_button.click(
        fn=submit,
        outputs=[status_output]
    )

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)