Contextual code search


A contextual code search of over 1 Billion lines of code in GitHub projects.

IndustryTechnology Platform

Year2014 – Ongoing

RoleBig Data Analytics, NLP

TechnologyApache Spark, Scala, HDFS, ElasticSearch, Web crawlers, Angular JS, Rest API

Search engine indexes over 1 billion lines of open source code

KodeBeagle is an open source software, offering analysis and searches for code references for Engineers. It is a free code search engine indexing over 1 billion lines of open source code from approximately 5,50,000 GitHub project repositories. The requirement was to build the platform from the scratch.

Context sensitive search powered by KodeBeagle

Most code search tools are textual. KodeBeagle on the contrary understands AST, scans thousands of Github projects, to find you the correct usage of classes. For instance, if you want to know how to use FileChannel and ByteBuffer, KodeBeagle will get code snippets from Github projects that use them, score the results for Github watches, relevance, quality, and other parameters. The context is taken from any given code snippet, unlike other text-based search platforms. The code searched is then checked for API specific idiom suggestions without losing the context.


Code search through Natural Language aids quick learning for Engineers

Kode Beagle provides contextual & intelligent code suggestions inside your IDE. Given code snippet, it shows most idiomatic usages. Leverages abundantly available “standard” code corpora to learn interesting and useful patterns. It allows code search through Natural Language queries summarizing new projects and files to aid quick learning.