Today I’m proud to launch Context, a CLI and open-source corpus for the python ecosystem - 4M quality embeddings of the top 1218 Python Libraries. $ pip install fleet-context or download to get the entire python universe. Here’s why this is game-changing for both Devs and LLMs

(1) We’re giving AI assistants real-time knowledge of python libraries & docs past any training cut-off. Whenever a new update or popular library comes out, your assistant is immediately injected with detailed & relevant knowledge.

(2) RAG over library docs improves LLM code generation and user experience - enabling LLMs to write more relevant and accurate code, while also correctly answering the most specific of user queries.(DocPrompting, Zhou, Alon, et. al)

(3) As developers start increasingly relying on coding assistants, we’re moving into a world where good LLM understanding can determine your project’s adoption. While working with langchain and pydantic, we realized that its no longer just about great devX, its about amazing llmX

We are entering a new world, where parts of the internet are made just for LLMs and entire ecosystems of content will be easily parsed by your AI assistants. We're excited to take a step in that direction. Find at Big thanks to @LangChainAI & @pydantic!

🚀

@cursor_ai and @github you gotta at least try to acquire fleet

@cursor_ai @github Not sure if we are looking for acquistion offers! This is an OS project 😐

nice! any plans to add `llama-index`?

let’s do it! DM’d

let's goooooo!