AGENT SKILL

interactive-apps-and-api

Guides LaTeX-OCR GUI, FastAPI, Streamlit, and Docker service workflows for interactive or deployed pix2tex OCR.

License 许可
MIT
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
interactive-apps-and-api
license
MIT
metadata
{ "disco-role": "operating" }
description
Guides LaTeX-OCR GUI, FastAPI, Streamlit, and Docker service workflows for interactive or deployed pix2tex OCR.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

Interactive Apps and API

Use this sub-skill when the user wants the latexocr desktop GUI, screenshot capture, formatted output, the FastAPI service, Streamlit demo, Docker API container, or optional dependency troubleshooting for these interactive routes.

Quick Route

API Summary

Install API dependencies:

pip install "pix2tex[api]"

Run the API app directly when model downloads and long-lived processes are allowed:

uvicorn pix2tex.api.app:app --host 0.0.0.0 --port 8502

The app exposes / for health, /predict/ for image uploads, and /bytes/ for raw byte uploads. Both prediction endpoints expect multipart field name file.

GUI Summary

Install GUI dependencies:

pip install "pix2tex[gui]"
latexocr

Use SCREENSHOT_TOOL=grim, SCREENSHOT_TOOL=spectacle, SCREENSHOT_TOOL=gnome-screenshot, or SCREENSHOT_TOOL=pil to override the screenshot backend when auto-detection picks the wrong one.

Boundaries

  • Core model inference and image-quality guidance belongs in ../ocr-inference/SKILL.md.
  • Dataset rendering, scraping, and training belong in sibling sub-skills.
  • Do not launch GUI windows, desktop installers, uvicorn, Streamlit, or Docker unless the user explicitly wants a long-running or desktop-side-effect action.

04 同仓库更多 Skills

VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-triton-opt

Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-solve

END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-skill

PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-pattern-fusion

Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-orchestrate

Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.

★ 351
VectorSpaceLab
VectorSpaceLab/AREX-Skill

passnet-feedback

Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).

★ 351