# code search

Published articles for code search.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Building a RAG Pipeline for Semantic Code Search: A Developer Diary and Field Notes

DevFeed: [Building a RAG Pipeline for Semantic Code Search: A Developer Diary and Field Notes](<https://devfeed.tech/articles/building-a-rag-pipeline-for-semantic-code-search-a-developer-diary-and-field-notes-41302.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/ai/2026/09/building-a-rag-pipeline-for-semantic-code-search-a-developer-diary-and-field-notes/>)

Author: Adam Malek

Published: 2026-09-17T12:39:40Z

Content type: article

Language: en

Sources: [The JetBrains Blog](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [code search](<https://devfeed.tech/topics/code-search.md>), [Parsing](<https://devfeed.tech/topics/parsing.md>), [jetbrains](<https://devfeed.tech/topics/jetbrains.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [code-search](<https://devfeed.tech/tags/code-search.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [parsing](<https://devfeed.tech/tags/parsing.md>), [rag](<https://devfeed.tech/tags/rag.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

### AI overview

Part 1 of a developer diary explains how JetBrains built a RAG pipeline for semantic code search, covering parsing, chunking, and vectorization. The pipeline is intended to give LLM agents precise, citable evidence from real repositories and retrieve code by meaning rather than exact keywords.

### Source excerpt

Part 1: Parsing, chunking, and vectorization Some time ago, we set out to build the best semantic code search platform we could: a RAG pipeline that gives LLM agents precise, citable evidence from real repositories instead of whatever grep happens to surface. The eventual solution was JetBrains Context. We got it working, we got it [...]

## Don't stop early: Case-folding source code at memory speed

DevFeed: [Don't stop early: Case-folding source code at memory speed](<https://devfeed.tech/articles/don-t-stop-early-case-folding-source-code-at-memory-speed-19849.md>)

Original publisher: [Read original article](<https://github.blog/engineering/architecture-optimization/dont-stop-early-case-folding-source-code-at-memory-speed/>)

Author: Alexander Neubeck

Published: 2026-07-31T16:00:00Z

Content type: article

Language: en

Sources: [GitHub](<https://devfeed.tech/sources/github.md>)

Topics: [Optimization](<https://devfeed.tech/topics/optimization.md>), [Code](<https://devfeed.tech/topics/code.md>), [FIRST](<https://devfeed.tech/topics/first.md>), [Rust](<https://devfeed.tech/topics/rust.md>)

Tags: [architecture-optimization](<https://devfeed.tech/tags/architecture-optimization.md>), [case-folding](<https://devfeed.tech/tags/case-folding.md>), [code-search](<https://devfeed.tech/tags/code-search.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [github](<https://devfeed.tech/tags/github.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [optimization](<https://devfeed.tech/tags/optimization.md>), [rust](<https://devfeed.tech/tags/rust.md>), [source](<https://devfeed.tech/tags/source.md>), [speed](<https://devfeed.tech/tags/speed.md>)

### AI overview

GitHub explains how it optimized case folding for source-code search. A branch-free ASCII fast path and byte-space arithmetic allow the open-source Rust casefold crate to process code at more than 45 GiB/s on a single core.

### Source excerpt

How a branch-free loop and byte-space arithmetic let GitHub case-fold every byte of code search at >45 GiB/s on a single core. The post Don't stop early: Case-folding source code at memory speed appeared first on The GitHub Blog.

## Codestral Embed

DevFeed: [Codestral Embed](<https://devfeed.tech/articles/codestral-embed-6986.md>)

Original publisher: [Read original article](<https://mistral.ai/news/codestral-embed/>)

Published: 2025-05-28T12:00:00Z

Content type: article

Language: en

Sources: [Mistral AI Blog](<https://devfeed.tech/sources/mistral-ai-blog.md>)

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Retrieval-Augmented Generation](<https://devfeed.tech/topics/retrieval-augmented-generation.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [code-completion](<https://devfeed.tech/topics/code-completion.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>), [coding](<https://devfeed.tech/topics/coding.md>)

Tags: [code-completion](<https://devfeed.tech/tags/code-completion.md>), [code-search](<https://devfeed.tech/tags/code-search.md>), [coding](<https://devfeed.tech/tags/coding.md>), [cost](<https://devfeed.tech/tags/cost.md>), [developer](<https://devfeed.tech/tags/developer.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [performance](<https://devfeed.tech/tags/performance.md>), [retrieval-augmented-generation](<https://devfeed.tech/tags/retrieval-augmented-generation.md>)

### AI overview

Mistral releases Codestral Embed, an embedding model specialized for code retrieval. The article presents benchmark results, configurable embedding dimensions and precisions, and trade-offs between retrieval quality and storage cost. It highlights applications including retrieval-augmented generation, semantic code search, similarity search, duplicate detection, clustering, and code analytics.

### Source excerpt

The most powerful AI platform for enterprises. Customize, fine-tune, and deploy AI assistants, autonomous agents, and multimodal AI with open models.

## Making the most of GitHub Code Search

DevFeed: [Making the most of GitHub Code Search](<https://devfeed.tech/articles/making-the-most-of-github-code-search-37174.md>)

Original publisher: [Read original article](<https://arkadiuszchmura.com/posts/making-the-most-of-github-code-search/>)

Published: 2023-09-30T00:00:00Z

Content type: tutorial

Language: en

Sources: [Arkadiusz Chmura](<https://devfeed.tech/sources/arkadiusz-chmura.md>)

Topics: [code search](<https://devfeed.tech/topics/code-search.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [Code](<https://devfeed.tech/topics/code.md>), [syntax](<https://devfeed.tech/topics/syntax.md>), [Sorting](<https://devfeed.tech/topics/sorting.md>)

Tags: [code-search](<https://devfeed.tech/tags/code-search.md>), [github](<https://devfeed.tech/tags/github.md>), [regular-expressions](<https://devfeed.tech/tags/regular-expressions.md>), [repositories](<https://devfeed.tech/tags/repositories.md>), [search](<https://devfeed.tech/tags/search.md>), [sorting](<https://devfeed.tech/tags/sorting.md>), [syntax](<https://devfeed.tech/tags/syntax.md>)

### AI overview

A practical guide to GitHub Code Search, covering exact-string searches, Boolean expressions, regular expressions, qualifiers, result limits, sorting behavior, and indexing limitations. It also presents the tool as useful for code exploration and learning.

### Source excerpt

The new search engine offers powerful code searching mechanisms we can leverage for quickly finding the code we need, as well as for exploration and learning.

## The legend about AIDL. Part 3. The crucial ingredient

DevFeed: [The legend about AIDL. Part 3. The crucial ingredient](<https://devfeed.tech/articles/the-legend-about-aidl-part-3-the-crucial-ingredient-26014.md>)

Original publisher: [Read original article](<https://unbreakable-titan.medium.com/the-legend-about-aidl-part-3-the-crucial-ingredient-71c5e8eea553?source=rss-e32583ce94d4------2>)

Author: Vladislav Puryev

Published: 2021-01-16T14:50:56Z

Content type: tutorial

Language: en

Sources: [Stories by Vladislav Puryev on Medium](<https://devfeed.tech/sources/stories-by-vladislav-puryev-on-medium.md>)

Topics: [Android](<https://devfeed.tech/topics/android.md>), [Code](<https://devfeed.tech/topics/code.md>)

Tags: [android](<https://devfeed.tech/tags/android.md>), [aosp](<https://devfeed.tech/tags/aosp.md>), [code](<https://devfeed.tech/tags/code.md>), [code-search](<https://devfeed.tech/tags/code-search.md>), [ide](<https://devfeed.tech/tags/ide.md>)

### AI overview

This third installment of a series examines how Android Interface Definition Language (AIDL) is used within Android system code. It traces calls involved in launching an Activity and follows the handling of Bundle and ActivityOptions objects, using shortened code examples from Android 10 sources.

### Source excerpt

Hello everybody. In the previous two parts you could read a lot of things about Android Interface Definition Language. About its origin, theoretical and practical basics, how these basics are implemented in Android system, how AIDL works and how developer can use it (as a result, quite simple) and some other things about Android and computer science. Well now, everything of this is pretty curious, but I would like to tell you about one more interesting thing. You are using AIDL much more, than you suppose. WARNING! This article contains a lot of code that will be provided in shortened form. Full versions you can find in your IDE, in AOSP or Android Code Search. Please be careful, cause most of further code can be changed any time by Google developers, that is why some material can be obsolete and partially or completely wrong in the future, but actual for the moment of publication. All code is retrieved from sources, which actual for Android 10. This series of articles consist of three parts: The legend about AIDL. Part 1. The roots The legend about AIDL. Part 2. In Action The legend about AIDL. Part 3. The crucial ingredient (you are here) The biggest one The statement above is quite brave, isn't it? Let's research the code and see that AIDL is more important, than any Android application component. The first opponent is Activity. Bigger, than Activity This is ridiculous, isn't it? How much times developers (and their users) are using Activity and how much times they need AIDL? It seems that crushing blow is directed to the hero of article. To prove this incredible fact it needs to look at the content of method, which allow to launch activity -- startActivity(). https://medium.com/media/0b4ea8396635cc920b6335a25c0aef13/href This method is calling another one startActivity(), passing null for parameter options. Depending on this value, second startActivity() calls startActivityForResult() with options or not. Let's dig deeper. https://medium.com/media/9855de0e0c3444e

## Regular Expression Search with Suffix Arrays

DevFeed: [Regular Expression Search with Suffix Arrays](<https://devfeed.tech/articles/regular-expression-search-with-suffix-arrays-21935.md>)

Original publisher: [Read original article](<https://blog.nelhage.com/2015/02/regular-expression-search-with-suffix-arrays/>)

Author: Nelson Elhage

Published: 2015-02-01T15:52:43Z

Content type: tutorial

Language: en

Sources: [Nelson Elhage](<https://devfeed.tech/sources/nelson-elhage.md>)

Topics: [Regular expression](<https://devfeed.tech/topics/regular-expression.md>), [Data structures](<https://devfeed.tech/topics/data-structures.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Code](<https://devfeed.tech/topics/code.md>), [Bioinformatics](<https://devfeed.tech/topics/bioinformatics.md>)

Tags: [algorithms](<https://devfeed.tech/tags/algorithms.md>), [arrays](<https://devfeed.tech/tags/arrays.md>), [code-search](<https://devfeed.tech/tags/code-search.md>), [data-structure](<https://devfeed.tech/tags/data-structure.md>), [full-text-search](<https://devfeed.tech/tags/full-text-search.md>), [google](<https://devfeed.tech/tags/google.md>), [library](<https://devfeed.tech/tags/library.md>), [open-source](<https://devfeed.tech/tags/open-source.md>)

### AI overview

This technical writeup explains how livegrep uses suffix arrays for regular-expression search over source code. It introduces suffix arrays, describes substring lookup through binary search, and outlines livegrep's indexing process using a flattened source buffer, a file content map, and libdivsufsort.

### Source excerpt

Back in January of 2012, Russ Cox posted an excellent blog post detailing how Google Code Search had worked, using a trigram index. By that point, I'd already implemented early versions of my own livegrep source-code search engine, using a different indexing approach that I developed independently, with input from a few friends. This post is my long-overdue writeup of how it works. Suffix Arrays A suffix array is a data structure used for full-text search and other applications, primarily these days in the field of bioinformatics.