Easy API use for Generative AI apps

Building Generative AI apps is hard enough when handling LLM peculiarities like hallucinations, latency, and cost. These apps can be increasingly more useful when integrating with enterprise and third-party APIs. However, rapid and scalable API integration with LLMs is even harder. GenAPI is on a mission to enable easy API use for Generative AI apps.

GenAPI has five goals to make this possible:

1. Reusable functions library for popular use cases like checking the weather,
2. Simple helper APIs to make app prototyping as easy as running cells on a notebook,
3. Quickstart cookbook with notebooks for building Generative AI Apps using best practices,
4. Comprehensive documentation with API, LLM, and app design tips, and
5. Efficient workflow and project structure for building scalable Generative AI Apps.

Exploring

We are currently exploring the following topics for addition to the GenAPI roadmap.

1. https://github.com/openai/evals - can we use this to evaluate GenAPI apps?
2. https://arxiv.org/pdf/2310.07343v1.pdf - can we use to enhance knowledge grounding for GenAPI apps.
3. https://github.com/stanfordnlp/dspy - explore once docs are available.
4. Please suggest more topics.