skills.rest
eyadsibai
eyadsibaiCOMMUNITY
Explore all skills by this author →
Website𝕏@eyadsibaiGitHub

rag-frameworks

Compare RAG frameworks like LangChain and LlamaIndex for document QA.

7|1|Updated Jan 14, 2026
Search Tags:#semantic search#embeddings#langchain#llm#rag#chatbot#llamaindex
One-click install
npx skills add https://github.com/eyadsibai/ltk --skill rag-frameworks
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-frameworks
Source: https://github.com/eyadsibai/ltk/tree/main/plugins/ltk-data/skills/rag-frameworks
Command: npx skills add https://github.com/eyadsibai/ltk --skill rag-frameworks

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps developers choose and understand the best frameworks for building retrieval-augmented generation (RAG) applications, simplifying the process of connecting LLMs to external data.

Core Features & Use Cases

  • Framework Comparison: Provides a clear comparison of LangChain, LlamaIndex, and Sentence Transformers based on use cases, learning curve, and flexibility.
  • RAG Architecture Patterns: Explains various patterns like Naive RAG, Parent-Child, and Hybrid Search.
  • Decision Guide: Offers recommendations based on specific scenarios, from simple document QA to complex agent workflows.
  • Use Case: When starting a new project that requires a chatbot to answer questions based on a large set of internal documents, this Skill helps you decide whether LlamaIndex or LangChain is a better fit.

Quick Start

Use the rag-frameworks skill to compare LangChain and LlamaIndex for document QA.

Frequently Asked Questions about rag-frameworks

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

FAQPage Schema
How do I choose between LangChain and LlamaIndex for a RAG application?▼

Choosing between LangChain and LlamaIndex for a RAG application depends on your use case, with LangChain offering flexibility for complex agent workflows and LlamaIndex excelling at data indexing and document QA.

What are common retrieval-augmented generation architecture patterns?▼

Common retrieval-augmented generation architecture patterns include Naive RAG, Parent-Child, and Hybrid Search, which define how data is indexed and retrieved to connect external documents to LLMs.

How do I build custom embedding pipelines with Sentence Transformers?▼

To build custom embedding pipelines with Sentence Transformers, you utilize the framework to generate embeddings from your internal documents, facilitating semantic search and query engines within RAG architectures.

When should I use Naive RAG versus Hybrid Search for document QA?▼

Use Naive RAG for simple document QA scenarios requiring basic retrieval, whereas Hybrid Search is suited for complex query engines needing more advanced architecture patterns to connect LLMs to external data.

Does this guide cover decision-making criteria for LLM chatbot development?▼

Yes, this guide covers decision-making criteria for LLM chatbot development by providing framework comparisons and recommendations based on learning curve, flexibility, and specific scenarios like internal document processing.

Related Skills

Explore More Software Engineering Skills→
raphaelchristiraphaelchristi
43

harness:setup

Configure Harness Evolver, LangSmith, and baseline evaluations for Python projects.

Community
Advanced
twjarviszyra-webtwjarviszyra-web
3

pinecone

Build production vector search indexes for semantic retrieval workloads.

Community
Intermediate
KappTech88KappTech88

sentence-transformers

Generate embeddings for semantic similarity, retrieval, and clustering tasks.

Community
Advanced
trueratruera
3.5k

trulens-instrumentation

Instrument LLM apps to capture traces for evaluation and debugging.

Official
Advanced