Skip to content

Simple Unstructured file processing#

We have a lot of pdf files that contain import information, however, the information are unstructured (text, table, image, etc...). To extract and utilize them in our downstream job, an open source unstructured is helpful to implement what we want

image

Demo App#


%%{init: { 'look':'handDrawn' } }%%

flowchart LR
  A[Gradio UI] --> B(Ollama Server)
  B --> C["
  #bull; Gemma2
  #bull; Llama3
  #bull; Phi3
  #bull; Mistral
  "]
  style C color:#FFFFFF,text-align:left,fill:#D2691E
  style B fill:#FFE4C4