wafflecomposite/langchain-ask-pdf-local

Issues

• would like to discuss extending this program's capabilities

  #7 opened a year ago by MacFGalempsy
  1

• Can you make to load multiple files, not only one file?

  #6 opened a year ago by AngelTs
  0

• No file named stable-vicuna-13B.ggml.q4_2.bin in linked Huggingface repo

  #1 opened 2 years ago by uwts
  2

• I have gpu and I expect to run model faster, but your code is only for cpu? how to change it?

  #4 opened 2 years ago by alexhmyang
  2

• use other pdf will raise error

  #5 opened 2 years ago by alexhmyang
  1

• Cannot build wheels

  #3 opened 2 years ago by MoRadwan21
  1

• validation error for LlamaCpp __root__ Could not load Llama model from path: ./models/stable-vicuna-13B.ggml.q4_0.bin

  #2 opened 2 years ago by jimmathew999
  1