[Backend] Try langchain integration of unstructured as is ?

apirrone / Memento

Memento is a Python app that records everything you do on your computer and lets you go back in time, search, and chat with a LLM (Large Language Model) to find back information about what you did.

MIT License

484 stars 39 forks source link

[Backend] Try langchain integration of unstructured as is ? #25

Closed apirrone closed 10 months ago

apirrone commented 10 months ago

https://python.langchain.com/docs/integrations/document_loaders/image

let unstructured do the work
returns a document object with metadata, put this in vectordb as is
see if it is better for the chat
no need for custom json metadata anymore ?

apirrone commented 10 months ago

Not working very well :/ and relies on tesseract in background anyways