Jack Hopkins

Working on adding support for streamed responses, which can be handled one by one as they are recieved.

Now loading in previously run iPython cells if it is not possible to access the source using inspect. This is necessary because of the way Colab / Jupyter handle code.

Demonstrate how to [build an app](https://dev.to/abdadeel/deploying-fastapi-app-on-vercel-serverless-18b1) using Vercel with FastAPI+MonkeyPatch deployed onto Vercel serverless. Make sure to document your process and write some written content to accompany it.

Pydantic fields include constraints on the content, e.g a character limit: ```python from pydantic import BaseModel, Field from typing import Optional class MyPydanticModel(BaseModel): title: Optional[str] = Field(None, max_length=10) ``` We...

LLM providers, specifically OpenAI, support streamed responses. We should support this. Requirements: - Iterator typed outputs should be streamable by default. - Support 1000s of streamed outputs through last-n context...

We should support asynchronous processing of patched function like as follows: ``` @monkey.patch async def iterate_presidents() -> Iterable[str]: """"List the presidents of the United States"""" @monkey.patch async def tell_me_more_about(topic: str)...

Currently only Uvicorn is supported, and therefore this project doesn't support multiple worker threads. We should add support for Gunicorn to support that popular usecase.