mirror of
https://github.com/NicolasBohn/NexQuant.git
synced 2026-07-28 07:57:44 +00:00
CI checks that can be automatically repaired (#119)
* fix isort & black & toml-sort & sphinx error * fix ci error * fix ci error * add comments * Update Makefile * change sphinx build command * add auto-lint * add black args * format with black * Auto Linting document * fix ci error --------- Co-authored-by: you-n-g <you-n-g@users.noreply.github.com> Co-authored-by: Young <afe.young@gmail.com>
This commit is contained in:
@@ -1,16 +1,17 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
import fitz
|
||||
from PIL import Image
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
import fitz
|
||||
from azure.ai.formrecognizer import DocumentAnalysisClient
|
||||
from azure.core.credentials import AzureKeyCredential
|
||||
from langchain.document_loaders import PyPDFDirectoryLoader, PyPDFLoader
|
||||
from PIL import Image
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from langchain_core.documents import Document
|
||||
|
||||
from rdagent.core.conf import RD_AGENT_SETTINGS
|
||||
|
||||
|
||||
@@ -99,10 +100,11 @@ def load_and_process_pdfs_by_azure_document_intelligence(path: Path) -> dict[str
|
||||
)
|
||||
return content_dict
|
||||
|
||||
|
||||
def extract_first_page_screenshot_from_pdf(pdf_path: Path) -> Image:
|
||||
doc = fitz.open(pdf_path)
|
||||
page = doc.load_page(0)
|
||||
pix = page.get_pixmap()
|
||||
image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
|
||||
|
||||
return image
|
||||
|
||||
return image
|
||||
|
||||
Reference in New Issue
Block a user