What advanced RAG patterns are included?

The skill covers sophisticated architectures including Parent-Child retrieval, Hybrid Search (vector + keyword), Re-ranking with cross-encoders, and Query Expansion.

Which RAG framework is best for simple document QA?

LlamaIndex is the recommended choice for simple document QA due to its gentle learning curve and specialized focus on data indexing and retrieval.

How does this skill help with LangChain development?

It provides guidance on core LangChain concepts like LCEL (LangChain Expression Language), agent orchestration, and building complex chains for agentic workflows.

Does this skill support custom embedding models?

Yes, it includes technical details for Sentence Transformers, helping you select and implement models like all-MiniLM-L6-v2 or e5-large-v2 for custom semantic similarity.

RAG Frameworks

Name: RAG Frameworks
Author: eyadsibai

byeyadsibai

Data Science & ML

Architects and implements retrieval-augmented generation applications using LangChain, LlamaIndex, and Sentence Transformers.

About

This skill equips developers with the technical knowledge and implementation patterns required to build robust Retrieval-Augmented Generation (RAG) systems. It provides comparative analysis and decision guidance for the industry's leading frameworks, helping users choose between LangChain for complex agentic workflows, LlamaIndex for efficient document indexing, and Sentence Transformers for custom embedding pipelines. By offering architectural patterns like Hybrid Search and Re-ranking alongside framework-specific best practices, this skill ensures that LLM applications can effectively access and reason over external data sources with high precision.

Key Features

Guidance on LangChain Expression Language (LCEL) and agent orchestration
Comprehensive comparison of LangChain, LlamaIndex, and Sentence Transformers
Implementation patterns for Hybrid Search, Re-ranking, and Parent-Child retrieval
0 GitHub stars
Selection criteria for embedding models and bi-encoder architectures
Expertise in document chunking, indexing, and LlamaIndex query engines

Use Cases

Building complex multi-agent systems using LangChain's orchestration tools
Developing production-grade document QA chatbots with semantic search
Optimizing retrieval accuracy through advanced patterns like query expansion

About

Key Features

Guidance on LangChain Expression Language (LCEL) and agent orchestration
Comprehensive comparison of LangChain, LlamaIndex, and Sentence Transformers
Implementation patterns for Hybrid Search, Re-ranking, and Parent-Child retrieval
0 GitHub stars
Selection criteria for embedding models and bi-encoder architectures
Expertise in document chunking, indexing, and LlamaIndex query engines

Use Cases

Building complex multi-agent systems using LangChain's orchestration tools
Developing production-grade document QA chatbots with semantic search
Optimizing retrieval accuracy through advanced patterns like query expansion