Optimize retrieval-augmented generation pipelines for LLM-powered tasks.
npx skills add https://github.com/sixscripts-ai/ghostssh --skill rag-engineer-sixscripts-ai
Please help me install this Agent Skill. Skill: rag-engineer Source: https://github.com/sixscripts-ai/ghostssh/tree/main/skills/rag-engineer Command: npx skills add https://github.com/sixscripts-ai/ghostssh --skill rag-engineer-sixscripts-ai
Retrieval quality is the bottleneck in many LLM workflows; this Skill provides a structured approach to design, implement, and operate Retrieval-Augmented Generation systems that fuse embeddings, chunking strategies, and vector databases to deliver accurate, up-to-date results from large document collections.
Configure a base RAG pipeline and perform a first retrieval pass over your document corpus.
High-intent search queries and answers about installing and using this skill.
To build a retrieval-augmented generation pipeline, you need to orchestrate document chunking, generate vector embeddings, and configure a vector database for similarity search. This delivers accurate context to LLMs from large knowledge bases.
Semantic chunking splits documents into meaningful sections before generating vector embeddings. You need it for vector search workflows to preserve context boundaries, ensuring the retrieval pipeline returns highly relevant segments rather than arbitrary text fragments.
The best way to implement hybrid search is to fuse keyword search with semantic vector similarity. This approach optimizes retrieval pipeline design by capturing both exact term matches and conceptual relationships, improving overall document retrieval accuracy.
Implementing semantic search requires a system to store and query vector embeddings. A dedicated vector database or vector search index is necessary to perform similarity searches across large document collections efficiently within the retrieval pipeline.
Poor retrieval results in a RAG pipeline often stem from suboptimal document chunking strategies or inadequate embedding design. Optimizing context window usage and integrating hybrid search can significantly improve semantic search relevance.
patricio0312revAutomate document embedding pipelines for semantic search.
anukkrit149Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.
AlexiosBluffMaraStore and query embeddings with metadata filtering in a local vector database.
MSamiulHasnatIndex embeddings and perform context-aware similarity queries for document retrieval.
