most_relevant_entities_aggregator

Official

Extract and sort most relevant entities from documents

Authorcas-bigdatalab
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the challenge of identifying and ranking the most relevant entities from a given document, streamlining the process of entity analysis.

Core Features & Use Cases

  • Entity Extraction: Automatically extract specific types of entities from documents.
  • Entity Ranking: Sort extracted entities based on their relevance to a given query.
  • Use Case: For instance, analyzing a collection of documents to identify the most significant characters in a story or the key entities in a scientific paper.

Quick Start

Run the most_relevant_entities_aggregator skill with the following command:

python scripts/run_most_relevant_entities_aggregator.py \
  --input ./input.json \
  --output ./output.json \
  --api_model qwen2.5-72b-instruct \
  --entity 李莲花 \
  --query_entity_type 人物

Dependency Matrix

Required Modules

data_juicer

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: most_relevant_entities_aggregator
Download link: https://github.com/cas-bigdatalab/piflow/archive/main.zip#most-relevant-entities-aggregator

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.