Verified:GitHub

langchain-rag

Build RAG workflows with LangChain loaders, splitters, embeddings, and vector stores.

Updated Apr 23, 2026

Search Tags:#embeddings #langchain #rag #retrieval-augmented-generation #vector-stores #text-splitting #document-loaders

Ready to run

npx skills add https://github.com/ladinglogichq/lading-logic-hackathon --skill langchain-rag-ladinglogichq

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: langchain-rag
Source: https://github.com/ladinglogichq/lading-logic-hackathon/tree/main/.claude/skills/langchain-rag
Command: npx skills add https://github.com/ladinglogichq/lading-logic-hackathon --skill langchain-rag-ladinglogichq

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Retrieval-augmented generation (RAG) enables LLMs to access up-to-date or domain-specific information by augmenting prompts with retrieved documents, improving accuracy and relevance across enterprise knowledge bases and developer tooling.

Core Features & Use Cases

Document Loaders: ingest files, web pages, and directories to prepare sources for retrieval.
Text Splitting: shard long documents into context-preserving chunks with RecursiveCharacterTextSplitter.
Embeddings: compute vector representations using OpenAI embeddings for semantic search.
Vector Stores: persist and query via Chroma, FAISS, or Pinecone to support scalable retrieval.
RAG Workflows: index → retrieve → generate, enabling AI assistants that cite sources and justify decisions.

Quick Start

Configure a minimal RAG pipeline that loads documents, splits text, creates embeddings, stores vectors, and answers queries.

Frequently Asked Questions about langchain-rag

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

FAQPage Schema

How do I build a retrieval-augmented generation pipeline with LangChain?▼

To build a retrieval-augmented generation pipeline with LangChain, you load source documents, split text into chunks, compute OpenAI embeddings, persist vectors in Chroma or FAISS, and retrieve relevant context to generate precise answers.

What's the best way to split long documents for semantic search without losing context?▼

Splitting long documents for semantic search requires preserving context, which you achieve by using RecursiveCharacterTextSplitter to shard text into manageable chunks before computing embeddings for your vector store.

Does LangChain RAG work with Pinecone and FAISS for vector storage?▼

LangChain RAG works with Pinecone and FAISS for vector storage, ensuring interoperability across these platforms alongside Chroma to support scalable retrieval and robust query performance.

How do document loaders prepare files and web pages for RAG workflows?▼

Document loaders prepare files and web pages for RAG workflows by ingesting directories and URLs, converting source content into a structured format ready for text splitting and embedding generation.

Why use OpenAI embeddings for retrieval-augmented generation tasks?▼

Using OpenAI embeddings for retrieval-augmented generation tasks ensures accurate vector representations of text chunks, enabling precise semantic search results when querying vector stores for relevant context.

When should I add retrieval-augmented generation to my LLM application?▼

You should add retrieval-augmented generation to your LLM application when you need to access up-to-date or domain-specific information, augmenting prompts with retrieved documents to improve answer accuracy and relevance.