LLM

You can run multiple async tasks simultaneously in Python using the asyncio native library. This allows you to create and manage asynchronous tasks, such as coroutines, and run them concurrently. Let’s have the following async method, that counts to the length of the given name and returns the name. import asyncio from typing import Awaitable async def count_word(name: str) -> Awaitable[str]: if len(name) > 8: raise ValueError(f"{name} is too long...") for ii in range(len(name)): print(name, ii) await asyncio.sleep(1) return name Now, running this task twice: await count_word("first"), await count_word("second") first 0 first 1 first 2 first 3 first 4 second 0 second 1 second 2 second 3 second 4 second 5 ('first', 'second') Will not run the two tasks concurrently because it’s using await, which means that it will wait for the first task to complete before starting the second task. If you want to run these tasks concurrently, you should use asyncio.gather(): ...

ChatPDF providers, where you can question large files with large language models (LLM’s), are sprouting like mushrooms. The technique is mainly based on vector embedding with a vector index or vector database; based on the question, semantically relevant chunks from the file are provided to the LLM so it can compose an answer. While this technique is cool, it is limited when you ask a question that spans the entire text, such as generating a summary, since that requires not a couple of chunks, but the full text. ...