What are the limitations when creating plugins

You see, I would like to create a very complex plugin that can access a large number of files on my PC that are stored in obsidian, which is basically a text editor that has a lot of information about what I have learned. but then I wonder if there is any limitation when wanting to do that I did not find in the documentation any part where I digest the limitations of the plugins I do not know if this info is at some point to know better until what types of complements I could create

check the doc here OpenAI API ?


We’re currently experimenting with GitHub - openai/chatgpt-retrieval-plugin: The ChatGPT Retrieval Plugin lets you easily search and find personal or work documents by asking questions in everyday language. and believe that additional features could be added. Although VectorDB is useful, it doesn’t address all of our QA needs. Other options to consider are Welcome to LangChain — 🦜🔗 LangChain 0.0.167 and LlamaIndex 🦙 0.6.6. If you have any insights on QA systems, we’d appreciate your input. Please feel free to share your thoughts.

1 Like

ok they just gave me a question how do you get the plugin can you name me a chat that talks about how to install these unverified plugins one like this?

Another is if this plugin can analyze the files that I have the text rather that is in them to answer my questions effectively around that context?