f74f09c191
- Refactor _extract_skills_to_robot to accept bot_id instead of robot_dir - Add multi-directory skill search with priority order - Switch from zip extraction to direct directory copying - Add rag-retrieve skill directory
27 lines
557 B
YAML
27 lines
557 B
YAML
name: rag-retrieve
|
|
version: 1.0.0
|
|
description: RAG retrieval skill for querying and retrieving relevant documents from knowledge base using vector search
|
|
author:
|
|
name: sparticle
|
|
email: support@gbase.ai
|
|
license: MIT
|
|
tags:
|
|
- rag
|
|
- retrieval
|
|
- vector-search
|
|
- knowledge-base
|
|
runtime:
|
|
python: ">=3.7"
|
|
dependencies:
|
|
- requests
|
|
entry_point: scripts/rag_retrieve.py
|
|
config:
|
|
query:
|
|
type: string
|
|
required: true
|
|
description: Search query content
|
|
top_k:
|
|
type: integer
|
|
default: 100
|
|
description: Maximum number of results
|