AGENT SKILL

querying

Guides paperai semantic and weighted queries, result filtering, article metadata display, interactive shell use, enriched API search, and optional search UI integration.

License 许可
Apache-2.0
最近更新
2026-09-03
Stars
★ 351
Forks
27

01 前言 Front Matter

name
querying
license
Apache 2.0
metadata
{ "disco-role": "operating" }
description
Guides paperai semantic and weighted queries, result filtering, article metadata display, interactive shell use, enriched API search, and optional search UI integration.
disable-model-invocation
true

02 资源文件 4

03 SKILL.md 正文

Querying

Use this route for one-shot paper searches, interactive terminal queries, API integration, or a small application around a saved paperai index. It assumes an articles.sqlite database and compatible txtai model directory already exist; route index construction to indexing. Route multi-query Markdown/CSV/annotation generation to reporting.

Fast route

  1. Confirm the model directory contains both articles.sqlite and a saved embeddings config/model.
  2. Run python -m paperai.query "your query" [topn] [model-dir] [threshold].
  3. Use +token to require a token and -token to exclude matching sections; start with the default threshold of 0.25.
  4. For repeated terminal use, run paperai <model-dir> and enter queries at the (paperai) prompt. For services, configure txtai's API with paperai.api.API and use its enriched article response.

Read api-reference.md for method signatures and response fields, cli-reference.md for command forms, workflows.md for recipes, and troubleshooting.md for failure recovery.

Important behavior

Query.run defaults topn to 10 through Query.query and the search threshold to 0.25. A query of * returns no vector matches in the direct query path; reports use * specially for all articles. A CPU package import or framework availability check does not validate a particular downloaded embedding model.

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