Can I use this with LangChain or LangGraph?

Absolutely, the skill includes detailed code examples for building modular and stateful RAG graphs using the LangGraph and LangChain ecosystems.

How does this help reduce LLM hallucinations?

By forcing the model to answer based on specific retrieved context and providing source citations, it significantly improves accuracy and prevents the model from generating plausible-sounding but false information.

Does it support hybrid search?

Yes, it includes advanced patterns for combining semantic (dense) search with traditional keyword (sparse/BM25) search using Reciprocal Rank Fusion for superior retrieval quality.

Which vector databases are supported by this skill?

This skill provides implementation patterns for major providers including Pinecone, Weaviate, Chroma, Milvus, Qdrant, and pgvector (PostgreSQL).

What is RAG in the context of LLMs?

RAG (Retrieval-Augmented Generation) is a technique that provides an LLM with specific, retrieved documents to ensure its answers are grounded in factual, external data rather than just its training set.

RAG Implementation & AI Knowledge Systems

Name: RAG Implementation & AI Knowledge Systems
Author: sla-te

bysla-te

0•

データサイエンスとML

Implements Retrieval-Augmented Generation (RAG) architectures to ground LLM responses in proprietary data using vector databases and semantic search.

This skill provides a comprehensive framework for building production-ready RAG systems, enabling AI applications to reason over external knowledge bases with high accuracy. It covers the complete lifecycle of knowledge integration, from sophisticated document chunking and multi-model embedding selection to advanced retrieval patterns like hybrid search, HyDE, and reranking. By utilizing these patterns, developers can eliminate hallucinations and create specialized tools such as documentation assistants, research platforms, and enterprise-grade Q&A systems that provide verifiable source citations.

主な機能

01Hybrid search implementation combining semantic and keyword-based retrieval.

02Multi-vector retrieval patterns including Parent Document and Contextual Compression.

03Advanced document chunking including semantic, recursive, and markdown splitting.

04Native support for leading vector databases like Pinecone, Weaviate, and pgvector.

05Stateful RAG workflow orchestration using LangGraph and Anthropic models.

060 GitHub stars

ユースケース

01Developing enterprise chatbots with secure access to internal company information.

02Building a documentation assistant for private or proprietary software repositories.

03Creating research tools that cite specific sources from a large PDF or knowledge library.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sla-te/copilot-converter rag-implementation

For use in Claude.ai and ChatGPT

Download Skill