So it does what the title says - essentially, it collects a call graph using Roslyn libraries and then passes it to GPT to verify that all business requirements are met. It acts as an additional safeguard for your code.
After you run TestRunner, it returns a result indicating whether your code meets the business requirements using GPT.
Also this package allows you to generate Gherkin tests given code. Uses call graph produced from entrypoint (class -> method) to generate tests cases.
I have been working as a software engineer for 8 years. I have always suffered from bugs, edge cases, performance bottlenecks, and a lack of effort in writing unit tests. You didn't notice that, you missed that, the production server crashed, I triple-checked the code, but I was too tired to find this small bug. I decided to start developing a product to address these issues. This is not just another copilot focused on code writing. Instead, it will focus solely on augmenting humans to improve the quality of the software they write. Future updates will enhance it with context-aware and dependency/call graph-aware inference, and more.
We are building an open-source platform NoLabs, which is designed specifically for running in-silico experiments with bio AI models.
We are building a platform that provides a user-friendly interface, APIs, and an AI copilot agent to streamline work with:
-Biological data access
-Protein folding models
-Protein solubility and function prediction
-Binding site prediction
-Protein-ligand docking
-De-novo molecule design
-Single-cell gene expression prediction
-Various other bioinformatics tools
The aim we have in our minds is for NoLabs to significantly enhance bioinformatics workflows by saving time on repetitive tasks and speeding up experimenting process. Eventually we are aiming to reduce operational costs, simplify bioinformatics pipelines, and offer seamless access to state-of-the-art models without complex setups.
We’re excited to collaborate with pioneering researchers and developers. Right now we are looking for a lab to work closely with to fine-tune the platform for them and see what kind of things it would be cool to add or improve, so if you are doing some bio research and interested in using AI models for biology please feel free to reach out!
After you run TestRunner, it returns a result indicating whether your code meets the business requirements using GPT.
Also this package allows you to generate Gherkin tests given code. Uses call graph produced from entrypoint (class -> method) to generate tests cases.