Aller au contenu
TakoAPI
Retour aux skills

ragie-rag

par hatim-be

Search & Research
292Téléchargements rapportés par clawskills.sh
0Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Execute Retrieval-Augmented Generation (RAG) using Ragie.ai.

Description

Ce que fait ce skill

Connects an AI agent to Ragie.ai to perform retrieval-augmented generation. Handles the full lifecycle: ingesting files or URLs, polling until documents are ready, retrieving relevant chunks, and constructing grounded answers that cite source documents.

Ragie offloads chunking, embedding, vector indexing, and optional reranking so the agent only needs to handle ingestion triggers and prompt construction.

Quand l'utiliser

  • Ask questions about uploaded policy or compliance documents
  • Ingest a PDF and query its contents without manual parsing
  • Check which documents are indexed and delete outdated ones
  • Answer support questions grounded in a product knowledge base
  • Retrieve context from partitioned tenant data in a multi-user system

Exemple de workflow

ENTRÉE

User asks: 'What does our refund policy say about digital products?'

AGENT
  1. 1

    Run retrieve.py with the user question and --rerank flag

  2. 2

    Receive scored chunks with document_name and text fields

  3. 3

    Concatenate chunk text into a grounded system prompt

  4. 4

    Generate answer using only the retrieved context

  5. 5

    Cite the document_name for each factual claim in the response

SORTIE

A grounded answer referencing the specific document, or an explicit statement that the information is not in the knowledge base

Prérequis

  • RAGIE_API_KEY environment variable
  • Ragie.ai account at https://app.ragie.ai

Installation

clawhub install hatim-be/ragie-rag

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens