RAG Pipeline Builder

Name: OpenModels
Creator: OpenModels
License: https://github.com/openmodelsrun/openmodels

ПродвинутыйdataМинимальный контекст: 32K

Designs and implements retrieval-augmented generation (RAG) pipelines end to end. Covers document chunking strategies, embedding model selection, vector store configuration, hybrid and re-ranking retrieval, prompt construction with grounded citations, and evaluation harnesses for measuring retrieval quality and answer faithfulness.

rag retrieval embeddings vector-database llm grounding

Варианты использования

Building production RAG over internal documentation
Choosing chunking and embedding strategies for a corpus
Adding hybrid search and re-ranking to improve recall
Designing citation-grounded answer prompts
Creating retrieval and faithfulness evaluation suites

Пример промпта

Design a RAG pipeline for a customer support knowledge base of ~50,000 markdown articles.

Requirements:
- Sub-second retrieval latency
- Answers must cite source articles
- Multilingual content (English, Spanish, German)

Provide:
1. Chunking strategy with rationale
2. Embedding model recommendation and vector store choice
3. Hybrid retrieval + re-ranking design
4. Prompt template enforcing grounded citations
5. Evaluation plan (retrieval recall, answer faithfulness)
6. Example implementation code

Совместимые инструменты

claude-codecursorkiroany

Модальности

Вход: text, code

→

Выход: text, code

RAG Pipeline Builder

Варианты использования

Пример промпта

Рекомендуемые модели

Совместимые инструменты

Модальности

Похожие Skills