# JetBrains explains storage and search for its Air Context code RAG system

> Original title: Building a RAG Pipeline for Semantic Code Search: A Developer Diary and Field Notes

- Source: JetBrains AI Blog
- Published: 2026-11-05T14:54:27.000Z
- Bad Influence: https://badinfluence.news/items/lv8fz5mia193dwigg4xbzzv89
- Original: https://blog.jetbrains.com/ai/2026/11/building-a-rag-pipeline-for-semantic-code-search-a-developer-diary-and-field-notes-part-2/

## Summary

JetBrains explains how Air Context stores millions of code vectors with approximate nearest-neighbor indexes and retrieves them in milliseconds. The post, the second in a series, compares pre-filtering, filtered ANN and post-filtering for enforcing repository, branch and permission constraints, and describes incremental index updates as commits land. Air Context is in public preview and included with JetBrains AI subscriptions.