Code Embedding

Creator

Creator

Created

Created

2024 Mar 22 9:23

Editor

Editor

Edited

Edited

2025 May 29 20:41

Refs

Refs

Text embedding

Code and natural language are not semantically similar - it is easier to semantic search on code bases if the code is first translated to natural language before generating embedding vectors.

Code Embedding Models

Codestral Embed

Nomic Code Embed

Code search grep.app

Code Search | Grep by Vercel

Search for code, files, and paths across half a million public GitHub repositories.

https://grep.app/

Code Search | Grep by Vercel

Codebases are uniquely hard to search semantically

Cosine similarity in code vs. text.

Codebases are uniquely hard to search semantically

https://www.greptile.com/blog/semantic

Codebases are uniquely hard to search semantically

Generating similarities for code generation

Got it, so maybe a ‘hybrid’ approach? I.e. encode the code snippets as class/function/interface name + parameter_names + docstrings as a ‘syntactic’ embedding, and then use a code2seq or the like to generate embeddings based on their AST paths (and get the ‘semantic’ meaning as well). Then whatever the user prompts, I can generate an embedding based off of his prompt (whether a textual description or code) and see if I get some good similarity results for relevant coding snippets. Does this make...

Generating similarities for code generation

https://community.openai.com/t/generating-similarities-for-code-generation/276894/9

Generating similarities for code generation

Recommendations

//////