Codey models are text-to-code models from Google AI, trained on a massive code related dataset. You can generate code related responses for different scenarios such as writing functions, debugging, explaining code etc. Here is the overview of all the Codey APIs.
We offer a comprehensive set of notebooks that demonstrate how to use Codey APIs to solve various tasks in software development life cycle including code generation, unit test generation, code explanation, comment generation, code refactoring, debugging, migration, codebase chat, Doc search, and JIRA search.
Notebooks:
- Code Gen Example: Create and Deploy a Live Website from a Wireframe with Codey and GCP Services
- Fine Tune Example: Fine Tune Codey to Learn a New API
- Debugging Example: Iteratively Debugging with Code Chat
- Migration Example: Code Migration from COBOL to Java with Code Chat
- RAG Code Chat Example: Talk to Codebase via Codey, Matching Engine and RAG
- RAG Code, JIRA, and Doc Chat Example: Talk to Codebase, JIRA and Docs via Codey, Matching Engine, Vertex AI Search and RAG
- Common Use Cases in One Notebook: Codey E2E Use Cases in Software Development Life Cycle
To run the walkthrough and demonstration in the notebook you'll need access to a Google Cloud project with the Vertex AI API enabled.
If you have any questions or find any problems, please report through GitHub issues.