Skip to content

https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

1.3 KB
Raw Blame
[project]
name = "pixelrag-repro"
version = "0.1.0"
description = "Self-contained reproduction harness for PixelRAG paper Table 1 — runs retrieval + reader + grader against live serves and prints the score."
requires-python = ">=3.12,<3.13"
# The base harness (run_bench.py + lib/) is a pure HTTP client — retrieval and reader run
# as remote serves, so it needs no torch/vllm. Deps use `>=` floors (like the rest of the
# workspace); uv.lock is the reproducibility contract (`uv sync --frozen`). numpy also
# carries an upper bound (<2.3) so the optional `reader` extra — which adds vLLM, the
# CUDA-fragile piece — can resolve alongside the base.
dependencies = [
    "aiohttp>=3.13.5",
    "datasets>=4.8.5",
    "openai>=2.38.0",
    "tqdm>=4.67.3",
    "pillow>=12.2.0",
    "requests>=2.34.2",
    "numpy>=1.26.0,<2.3",
    "selenium>=4.44.0",
    "webdriver-manager>=4.1.1",
    "beautifulsoup4>=4.14.3",
    "lxml>=6.1.1",
    "tiktoken>=0.13.0",
    "trafilatura>=2.0.0",
    "litellm>=1.89.0,<2.0.0",
    "botocore>=1.43.18",
    "tenacity>=9.1.4",
    "fastmcp>=3.3.1",
    "omegaconf>=2.3.0",
    "retry>=0.9.2",
]

[project.optional-dependencies]
# Self-host the Qwen3.5-4B reader (vLLM 0.19.0) from this package: `uv sync --extra reader`.
reader = ["vllm==0.19.0"]

[tool.uv]
package = false