mirror of
https://github.com/RYDE-WORK/Langchain-Chatchat.git
synced 2026-01-19 21:37:20 +08:00
* jpg and png ocr * fix * write docs to tmp file * fix * [BUGFIX] local_doc_qa.py line 172: logging have no end args. (#323) * image loader * fix * fix * update api.py * update api.py * update api.py * update README.md * update api.py * add pdf_loader * fix --------- Co-authored-by: RainGather <3255329+RainGather@users.noreply.github.com> Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
13 lines
292 B
Python
13 lines
292 B
Python
from configs.model_config import *
|
|
import nltk
|
|
|
|
nltk.data.path = [NLTK_DATA_PATH] + nltk.data.path
|
|
|
|
filepath = "docs/test.pdf"
|
|
from loader import UnstructuredPaddlePDFLoader
|
|
|
|
loader = UnstructuredPaddlePDFLoader(filepath, mode="elements")
|
|
docs = loader.load()
|
|
for doc in docs:
|
|
print(doc)
|