skills.rest
fanguyun
fanguyunCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

rag-architect

Design and implement RAG systems with document chunking, embeddings, and hybrid search.

Updated May 31, 2026
Search Tags:#semantic search#RAG#vector search#embedding#document retrieval
One-click install
npx skills add https://github.com/fanguyun/SkillManager --skill rag-architect-fanguyun
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-architect
Source: https://github.com/fanguyun/SkillManager/tree/main/rag-architect
Command: npx skills add https://github.com/fanguyun/SkillManager --skill rag-architect-fanguyun

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires langchain, openai, qdrant_client, sentence_transformers, BM25Okapi, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill empowers users to design and implement robust Retrieval Augmented Generation (RAG) systems, solving the challenge of efficiently retrieving and utilizing information from vast document collections.

Core Features & Use Cases

  • Document Retrieval and Processing: Automates the retrieval and processing of documents for indexing and search.
  • Vector Embeddings and Indexing: Generates embeddings for documents and indexes them for efficient retrieval.
  • Hybrid Search Pipelines: Builds and optimizes search pipelines using both vector and keyword-based methods.
  • Reranking: Enhances search results by reranking based on relevance to the query.
  • Evaluation and Optimization: Provides tools for evaluating the quality of the RAG system and iterating on improvements.
  • Use Case: Ideal for building knowledge-based applications, semantic search engines, and AI-powered information retrieval systems.

Quick Start

Use the rag-architect skill to build a RAG system for document retrieval and semantic search. Start by defining your document collection and index configuration, then execute the search query with the 'search' command.

Frequently Asked Questions about rag-architect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a production-grade RAG system with hybrid search and reranking?▼

To build a production-grade RAG system, configure document chunking, generate embeddings, and construct a hybrid search pipeline using vector and keyword methods. You can then enhance retrieval accuracy by applying reranking based on query relevance.

Can I use Qdrant and LangChain for document retrieval and vector indexing?▼

Yes, you can use Qdrant and LangChain for document retrieval and vector indexing. The system integrates qdrant_client for vector store configuration and langchain to orchestrate the pipeline, generating embeddings for efficient semantic search.

What's the best way to combine semantic and keyword search for AI information retrieval?▼

The best way to combine semantic and keyword search is implementing a hybrid search pipeline. This approach integrates BM25Okapi for keyword matching alongside vector embeddings, reranking the merged results to optimize retrieval quality.

How does document chunking affect embedding and retrieval quality in a RAG pipeline?▼

Document chunking directly impacts embedding and retrieval quality by determining the granularity of indexed information. Proper chunking ensures the vector store contains contextually relevant segments, which improves the accuracy of semantic search results.

Do I need Python and specific libraries to set up a vector database for semantic search?▼

Yes, you need Python and specific libraries like openai, sentence_transformers, and qdrant_client to set up a vector database. These dependencies handle embedding generation and vector store configuration for semantic search.

How do I evaluate and optimize a RAG system's search pipeline?▼

You evaluate and optimize a RAG system by measuring the relevance of retrieved documents against queries. The system provides tools to assess search pipeline quality, allowing you to iterate on chunking, embedding, and reranking improvements.

Related Skills

Explore More Software Engineering Skills→
zechenzhangAGIzechenzhangAGI
11.5k

chroma

Store embeddings and metadata for semantic search and RAG pipelines.

Community
Intermediate
anukkrit149anukkrit149

rag-implementation

Build Retrieval-Augmented Generation systems grounding LLM answers in vector databases.

Community
Advanced
Mercurium-AnalyticsMercurium-Analytics

fastapi-pgsearch-patterns

Combine FastAPI with pgvector and pg_search for hybrid lexical and vector retrieval.

Official
Advanced
zechenzhangAGIzechenzhangAGI
11.5k

pinecone

Manage a serverless vector database with hybrid search and metadata filtering.

Community
Intermediate