remove unused codes, seperate layout detection out as a new api. Add new rag methed 'table' (#55)

This commit is contained in:
KevinHuSh
2024-02-05 18:08:17 +08:00
committed by GitHub
parent f305776217
commit 407b2523b6
33 changed files with 306 additions and 505 deletions

View File

@ -52,7 +52,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000, callback=None, **k
l = f.readline()
if not l:break
txt += l
sections = txt.split("\n")
sections = txt.split("\n")
sections = [(l,"") for l in sections if l]
callback(0.8, "Finish parsing.")
else: raise NotImplementedError("file type not supported yet(docx, pdf, txt supported)")