AGENT SKILL

dsl-search

Guide elasticsearch.dsl query and search composition, mappings, typed Documents, aggregations, pagination, persistence, and sync/async DSL workflows.

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

01 前言 Front Matter

name
dsl-search
license
Apache 2.0
metadata
{ "disco-role": "operating" }
description
Guide elasticsearch.dsl query and search composition, mappings, typed Documents, aggregations, pagination, persistence, and sync/async DSL workflows.
disable-model-invocation
true

02 资源文件 5

03 SKILL.md 正文

DSL and search

Use this route when a task asks for Q, Search, aggregations, filters, mappings, Document, Index, FacetedSearch, or a high-level query that should be rendered to the Elasticsearch request body. Use client-operations for client/auth setup and helpers-ingest for bulk/scan/reindex.

Fast route

  1. Build a Q object for reusable query fragments, combining with & (AND), | (OR), and ~ (NOT). Use .to_dict() before sending when debugging.
  2. Build an immutable-style Search(index=...) and chain .query(...), .filter(...), .exclude(...), .sort(...), .source(...), .extra(...), .params(...), .aggs.bucket(...), or .execute().
  3. Define Document/InnerDoc classes and Field objects when the mapping, validation, persistence, and typed result behavior are worth the extra structure. Create the index/mapping before saving documents.
  4. Use async counterparts with AsyncElasticsearch; await execution and close the client. Render queries offline before any cluster call.

Read api-reference.md for the public object model, workflows.md for compositional recipes, data-and-mapping.md for mappings and typed documents, and troubleshooting.md for validation, response, and version failures. Run scripts/dsl_query_smoke.py for an offline check.

Offline-first example

from elasticsearch.dsl import Q, Search

query = Q("bool", must=[Q("match", title="python")], filter=[Q("term", status="published")])
request = Search(index="books").query(query).sort("_score").source(["title"])
assert request.to_dict()["query"]["bool"]["must"][0] == {"match": {"title": "python"}}
# response = request.execute()  # requires a configured live cluster

The DSL is a request builder, not a server-side validator. A rendered request can still fail because the index mapping, Elasticsearch version, privileges, or query feature is incompatible.

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