İçeriğe geç
TakoAPI
Becerilere dön

hk101-living-rag

metatronsdoob369 tarafından

Search & Research
758İndirme sayıları clawskills.sh tarafından bildirilir
2Yıldızlar
0Görüntülenmeler
0 beğeniBu beceriyi beğenmek için giriş yapın
—Henüz değerlendirilmedi
Puanınız

Özet

Simple RAG over local text/markdown.

Açıklama

Bu Beceri Ne Yapar

Runs retrieval-augmented generation over a local folder of text or markdown files. Given a query, it finds the most relevant document chunks and returns a synthesized answer with source snippets.

Keeps documents local and avoids uploading sensitive content to external search or indexing services.

Ne Zaman Kullanılır

  • Querying a local knowledge base without a cloud service
  • Searching project documentation by natural language
  • Answering questions from a folder of meeting notes
  • Looking up policies stored as markdown files
  • Finding relevant content across a large docs directory

Örnek İş Akışı

GİRİŞ

User asks: 'What is our refund policy?' with docsPath set to ./company-docs

AJAN
  1. 1

    Scans the target folder for text and markdown files

  2. 2

    Chunks documents into searchable segments

  3. 3

    Embeds the query and document chunks using OpenAI

  4. 4

    Retrieves the top k matching chunks by similarity score

  5. 5

    Synthesizes an answer from the matched content

ÇIKIŞ

A direct answer to the query plus an array of matches with file path, score, and snippet for each

Gereksinimler

  • OPENAI_API_KEY environment variable

Kurulum

clawhub install metatronsdoob369/hk101-living-rag

CLI komutunu çalıştırın ya da istemi Claude Code, Cursor, Codex veya kullandığınız kodlama ajanına yapıştırın.

Bağlantılar