41 lines
1.7 KiB
TeX
41 lines
1.7 KiB
TeX
\chapter{Evidencias que alimentan el modelo}
|
|
\label{ch:evidencias}
|
|
|
|
\section{Resumen}
|
|
\begin{table}[ht]
|
|
\centering
|
|
\small
|
|
\begin{tabular}{@{}llp{5.4cm}@{}}
|
|
\toprule
|
|
\textbf{Etapa} & \textbf{Cifra} & \textbf{Origen} \\
|
|
\midrule
|
|
Gateway & no es cuello (p95 41\,ms) & ST-GW-01 (13-jul), 0\,\% fallos \\
|
|
Agent Selenium (1 agent PC) & $\approx$422 fact/h & 633 PDFs / 90\,min \\
|
|
LLM (1 worker) & $\approx$506 fact/h & ST-EXT-02 (17-jul): p50 7{,}114\,s \\
|
|
OCR count-api & $\sim$100--325 fact/h & ST-COUNT-01 (17-jul): p50 35{,}8\,s @3 \\
|
|
Cola ARQ (mock) & $\approx$4\,500 docs/h cola & ST-EXT-01: 30/30 en $\approx$24\,s \\
|
|
Pipeline host actual & $\sim$100--325 fact/h & $=\min$ etapas; cuello OCR (no E2E) \\
|
|
Pipeline dedicado (est.) & $\sim$400 fact/h & $\min$ con OCR $\sim$400 \\
|
|
\bottomrule
|
|
\end{tabular}
|
|
\caption{Medido vs estimado (campa\~na julio 2026).}
|
|
\end{table}
|
|
|
|
\section{Detalle por prueba}
|
|
\begin{description}[style=nextline,leftmargin=0.4cm]
|
|
\item[ST-EXT-02 (LLM)]
|
|
gpt-5.4-mini; 23/23 ok; p50 7{,}114\,s $\Rightarrow$ 506 fact/h (1\,w); 0$\times$429.
|
|
\item[ST-EXT-01 (ARQ mock)]
|
|
30/30 drenados en 22{,}5\,s. Valida cola async; \textbf{no} es capacidad LLM real.
|
|
\item[ST-COUNT-01 (OCR)]
|
|
9/9 ok; p50 35{,}8\,s con 3 concurrentes (vs $\sim$2\,s en serie). Degrada fuerte en shared8g.
|
|
\item[Agent Selenium]
|
|
422 fact/h con 1 agent PC: supera 139/h; no alcanza 570/h sin m\'as agents.
|
|
\item[ST-GW-01 / ST-BOT-01]
|
|
Gateway OK. ST-BOT-01 mide el orquestador \texttt{bot-descarga} (heartbeats): host contendido malo (p95 2{,}28\,s); host m\'as libre OK (86\,ms).
|
|
\end{description}
|
|
|
|
\section{A\'un no medido a escala}
|
|
ST-COUNT-01 lab, ST-EXT-01 lab (100--500), E2E punta a punta a cientos/miles de PDFs,
|
|
ni 100k reales.
|