# Soba Labs guide shows enterprise RAG on LangChain with retrieval fixes first

> Original title: LangChain Community Spotlight: Enterprise RAG on LangChain 🔎📚

- Source: LangChain
- Published: 2026-10-31T21:00:13.000Z
- Bad Influence: https://badinfluence.news/items/f6wj3w8dsauatyd36dt0ivc3v
- Original: https://x.com/LangChain/status/2116636383829754302

## Summary

Kacper Klusek of Soba Labs recommends fixing retrieval before changing the model when building enterprise RAG on LangChain. He points to a retrieval chain of contextual embeddings, BM25 and a reranker, which Anthropic's published evaluation credits with cutting failed retrievals by 67%. LangSmith online evals are presented as a way to catch quality decay when documents change.

## Post

LangChain Community Spotlight: Enterprise RAG on LangChain 🔎📚

Kacper Klusek of Soba Labs shows how to build enterprise RAG on LangChain by fixing retrieval before you touch the model. In Anthropic's published evaluation, the retrieval chain he recommends (contextual embeddings, BM25 and a reranker) cut failed retrievals by 67%. LangSmith online evals then catch the decay that starts when your documents change.

📖 Read the full guide: https://sobalabs.ai/blog/enterprise-rag-on-langchain/

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHV_NkxIWAAAmy99.jpg&mode=thumb&exp=1793664000&sig=fdd27be52a07cdbb)