0.2.0

IMPORTANT: This requires users to delete their embedding files and re-run repo-gpt setup. The embedding file is generally located in <path to your repo root>/.repo_gpt/code_embeddings.pkl

What's Changed

• This update overhauls how repot-gpt query <whatever you want to ask> so it searches your codebase using agents and answers your questions.
• The index now indexes all files that are not in the .gitignore file
• All sizes of functions and files are indexed. (Size was a limiting factor before.)

Full Changelog: 0.1.5...0.2.0

0.1.5

What's Changed

• Move try-catch up a level for error parsing file by @shruti222patel in #24

Full Changelog: 0.1.4...0.1.5

0.1.4

What's Changed

• Don't raise exception when there's an error parsing by @shruti222patel in #23

Full Changelog: 0.1.3...0.1.4

0.1.3

What's Changed

• Fix parsed code bug @shruti222patel in #22

Full Changelog: 0.1.2...0.1.3

0.1.2

• Add global code (i.e. code outside of classes & functions/methods)
• Catch & print parsing errors.

0.1.1

Generate Tests

Autogenrate tests by running

repo-gpt add-test <unique funciton name> --test_save_file_path <absolute filepath to add tests to> --testing_package <testing package to use e.g. pytest>

E.g. repo-got add-test main --test_save_file_path $PWD/test.py --testing_package pytest

New Language Support

Now, .sql and .php code files can be parsed and incorporated into your search.
We also switched to using tree-sitter for code parsing, so it will be very easy to add new languages if folks request.

What's Changed

• Add sql parser by @shruti222patel in #10
• Add tree sitter by @shruti222patel in #13
• Generate tests by @shruti222patel in #9

Full Changelog: 0.1.0...0.1.1

0.1.0

MVP ✨

Repo-GPT is a Python CLI tool designed to utilize the power of OpenAI's GPT-3 model. It facilitates the process of code analysis and search within your repositories.

Features

• Code extraction and processing from your repositories.
• Semantic search within your codebase through natural language queries.
• Response generation to natural language queries about your code.
• Specific file analysis within your codebase.