File size: 10,332 Bytes
6933ba4 2a82ad6 6933ba4 2a82ad6 6933ba4 2a82ad6 6933ba4 2a82ad6 6933ba4 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | from __future__ import annotations
import time
from datetime import datetime, timezone
from pathlib import Path
from typing import Any
import gradio as gr
import pandas as pd
import predictors
from tracker import RunTracker, hash_image, hash_text
LOG_PATH = Path(__file__).parent / "runs.jsonl"
tracker = RunTracker(LOG_PATH)
def _client_meta(request: gr.Request | None) -> dict[str, Any]:
if request is None:
return {}
headers = getattr(request, "headers", {}) or {}
user_agent = ""
try:
user_agent = headers.get("user-agent", "")
except AttributeError:
user_agent = dict(headers).get("user-agent", "")
return {"user_agent": user_agent}
def predict_text(text: str, model_version: str, request: gr.Request):
if not text or not text.strip():
gr.Warning("Empty text — nothing to predict.")
return None, ""
input_hash, input_meta = hash_text(text)
t0 = time.perf_counter()
result = predictors.predict(model_version, "text", text)
latency_ms = (time.perf_counter() - t0) * 1000.0
run_id = tracker.record(
model_version=model_version,
input_kind="text",
input_hash=input_hash,
input_meta=input_meta,
output=result["output"],
latency_ms=latency_ms,
client_meta=_client_meta(request),
)
return result, f"**Run ID:** `{run_id}` · {latency_ms:.1f} ms"
def predict_image(image, model_version: str, request: gr.Request):
if image is None:
gr.Warning("No image uploaded.")
return None, ""
input_hash, input_meta = hash_image(image)
t0 = time.perf_counter()
result = predictors.predict(model_version, "image", image)
latency_ms = (time.perf_counter() - t0) * 1000.0
run_id = tracker.record(
model_version=model_version,
input_kind="image",
input_hash=input_hash,
input_meta=input_meta,
output=result["output"],
latency_ms=latency_ms,
client_meta=_client_meta(request),
)
return result, f"**Run ID:** `{run_id}` · {latency_ms:.1f} ms"
def _parse_date(value: str) -> datetime | None:
if not value or not value.strip():
return None
try:
return datetime.fromisoformat(value).replace(tzinfo=timezone.utc)
except ValueError:
return None
def load_history(model_filter: str, since_str: str, until_str: str):
model = None if (not model_filter or model_filter == "All") else model_filter
since = _parse_date(since_str)
until = _parse_date(until_str)
rows = list(
tracker.iter_runs(
model_version=model,
since=since,
until=until,
limit=500,
)
)
if not rows:
return pd.DataFrame(
columns=["run_id", "timestamp", "model_version", "input_kind", "latency_ms"]
)
df = pd.DataFrame(
[
{
"run_id": r.get("run_id"),
"timestamp": r.get("timestamp"),
"model_version": r.get("model_version"),
"input_kind": r.get("input_kind"),
"latency_ms": round(float(r.get("latency_ms", 0.0)), 2),
}
for r in rows
]
)
return df
def show_detail(evt: gr.SelectData, df: pd.DataFrame):
if df is None or df.empty or evt is None:
return {}
try:
row_idx = evt.index[0] if isinstance(evt.index, (list, tuple)) else evt.index
except Exception:
return {}
if row_idx is None or row_idx >= len(df):
return {}
run_id = df.iloc[row_idx]["run_id"]
for row in tracker.iter_runs(limit=10_000):
if row.get("run_id") == run_id:
return row
return {}
def load_stats():
stats = tracker.stats()
per_model_rows = [
{
"model_version": model,
"count": data["count"],
"p50_ms": None if data["p50_ms"] is None else round(data["p50_ms"], 2),
"p95_ms": None if data["p95_ms"] is None else round(data["p95_ms"], 2),
}
for model, data in stats["per_model"].items()
]
per_model_df = pd.DataFrame(
per_model_rows, columns=["model_version", "count", "p50_ms", "p95_ms"]
)
per_day = stats["per_day"]
if not per_day:
empty_df = pd.DataFrame({"date": [], "runs": []})
return per_model_df, empty_df
plot_df = pd.DataFrame(
[{"date": day, "runs": count} for day, count in per_day.items()]
)
return per_model_df, plot_df
def refresh_download():
if LOG_PATH.exists() and LOG_PATH.stat().st_size > 0:
return str(LOG_PATH)
return None
def clear_log(confirm: bool):
if not confirm:
gr.Warning("Tick the confirm box to clear the log.")
return refresh_download(), "Not cleared."
dropped = tracker.clear()
return refresh_download(), f"Cleared {dropped} run(s)."
def build_app() -> gr.Blocks:
models = predictors.list_models()
model_choices_with_all = ["All", *models]
with gr.Blocks(title="Model Prediction Tracker") as demo:
gr.Markdown("# Model Prediction Tracker")
gr.Markdown(
"Every prediction gets a unique run ID and is appended to "
"`runs.jsonl`. Hugging Face Spaces have an **ephemeral filesystem** — "
"use the Download tab to save the log before the Space rebuilds."
)
with gr.Tabs():
with gr.Tab("Predict"):
with gr.Row():
model_dd = gr.Dropdown(
choices=models,
value=models[0],
label="Model version",
)
with gr.Tabs():
with gr.Tab("Text"):
text_in = gr.Textbox(label="Text input", lines=3)
text_btn = gr.Button("Predict", variant="primary")
text_run = gr.Markdown()
text_out = gr.JSON(label="Prediction")
text_btn.click(
predict_text,
inputs=[text_in, model_dd],
outputs=[text_out, text_run],
)
with gr.Tab("Image"):
img_in = gr.Image(type="pil", label="Image input")
img_btn = gr.Button("Predict", variant="primary")
img_run = gr.Markdown()
img_out = gr.JSON(label="Prediction")
img_btn.click(
predict_image,
inputs=[img_in, model_dd],
outputs=[img_out, img_run],
)
with gr.Tab("History") as history_tab:
with gr.Row():
hist_model = gr.Dropdown(
choices=model_choices_with_all,
value="All",
label="Filter by model",
)
hist_since = gr.Textbox(
label="Since (YYYY-MM-DD)", placeholder="2026-01-01"
)
hist_until = gr.Textbox(
label="Until (YYYY-MM-DD)", placeholder="2026-12-31"
)
hist_refresh = gr.Button("Refresh")
hist_df = gr.Dataframe(
headers=[
"run_id",
"timestamp",
"model_version",
"input_kind",
"latency_ms",
],
interactive=False,
wrap=True,
label="Runs (newest first)",
)
hist_detail = gr.JSON(label="Selected run detail")
hist_refresh.click(
load_history,
inputs=[hist_model, hist_since, hist_until],
outputs=[hist_df],
)
hist_model.change(
load_history,
inputs=[hist_model, hist_since, hist_until],
outputs=[hist_df],
)
hist_df.select(show_detail, inputs=[hist_df], outputs=[hist_detail])
history_tab.select(
load_history,
inputs=[hist_model, hist_since, hist_until],
outputs=[hist_df],
)
with gr.Tab("Stats") as stats_tab:
stats_refresh = gr.Button("Refresh")
stats_per_model = gr.Dataframe(
headers=["model_version", "count", "p50_ms", "p95_ms"],
interactive=False,
label="Per-model latency",
)
stats_per_day = gr.BarPlot(
x="date",
y="runs",
title="Runs per day",
label="Runs per day",
)
stats_refresh.click(
load_stats, outputs=[stats_per_model, stats_per_day]
)
stats_tab.select(load_stats, outputs=[stats_per_model, stats_per_day])
with gr.Tab("Download") as download_tab:
gr.Markdown(
"Download the raw JSONL log. Clearing the log is "
"**irreversible** — tick the confirm box first."
)
dl_file = gr.File(label="runs.jsonl", value=refresh_download())
dl_refresh = gr.Button("Refresh file")
clear_confirm = gr.Checkbox(
label="I want to clear the log", value=False
)
clear_btn = gr.Button("Clear log", variant="stop")
clear_status = gr.Markdown()
dl_refresh.click(refresh_download, outputs=[dl_file])
download_tab.select(refresh_download, outputs=[dl_file])
clear_btn.click(
clear_log,
inputs=[clear_confirm],
outputs=[dl_file, clear_status],
)
return demo
demo = build_app()
if __name__ == "__main__":
demo.launch()
|