Semantic code search is a debugging project masquerading as a search feature. jetbrains' september…
semantic code search is a debugging project masquerading as a search feature. jetbrains' september 17 developer diary on building context admits the hard part was the rag pipeline giving agents citable evidence instead of whatever grep surfaces.
search was the easy half.
Context
JetBrains published Part 1 of a developer diary on building a RAG pipeline for semantic code search. It says the aim was a platform giving LLM agents precise, citable evidence from real repositories instead of whatever grep happens to surface, and that the eventual solution was JetBrains Context. Part 1 covers parsing, chunking and vectorization, with AST-based chunking, chunk size trade-offs, and a note that thresholding does not survive embedding compression.
Only Part 1 was read. It presents the pipeline as the project and not as an admission of difficulty, and the debugging-project framing in the first line is the author's. The post is dated in the September 2026 path and found by search at September 17, 2026, with no exact publication date read. No retrieval quality numbers appear in Part 1. A related JetBrains post from May on IDE-native search tools carries a July 29, 2026 correction saying part of its experiment was wrong, and it was not read.
Watch next
- Later parts of the diary and JetBrains Context benchmark numbers.
Sources
- JetBrains: Building a RAG pipeline for semantic code search, a developer diaryblog.jetbrains.com
- JetBrains: Introducing JetBrains Context (July 2026)blog.jetbrains.com
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 21 September 2026 at 20:03 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →