gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix package name checks for docx and pptx modules.

Browse Source 
- Added type ignore for package checks
- Corrected docx pptx package name for new version
This commit is contained in:
yangdx
2025-03-04 10:00:07 +08:00
parent fb07bc04a0
commit 61839f311a
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
lightrag/api/routers/document_routes.py
View File

@@ -217,7 +217,7 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool:
): ):
content = file.decode("utf-8") content = file.decode("utf-8")
case ".pdf": case ".pdf":
if not pm.is_installed("pypdf2"): if not pm.is_installed("pypdf2"): # type: ignore
pm.install("pypdf2") pm.install("pypdf2")
from PyPDF2 import PdfReader # type: ignore from PyPDF2 import PdfReader # type: ignore
from io import BytesIO from io import BytesIO
@@ -227,7 +227,7 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool:
for page in reader.pages: for page in reader.pages:
content += page.extract_text() + "\n" content += page.extract_text() + "\n"
case ".docx": case ".docx":
if not pm.is_installed("docx"): if not pm.is_installed("python-docx"): # type: ignore
pm.install("docx") pm.install("docx")
from docx import Document from docx import Document
from io import BytesIO from io import BytesIO
@@ -236,7 +236,7 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool:
doc = Document(docx_file) doc = Document(docx_file)
content = "\n".join([paragraph.text for paragraph in doc.paragraphs]) content = "\n".join([paragraph.text for paragraph in doc.paragraphs])
case ".pptx": case ".pptx":
if not pm.is_installed("pptx"): if not pm.is_installed("python-pptx"): # type: ignore
pm.install("pptx") pm.install("pptx")
from pptx import Presentation from pptx import Presentation
from io import BytesIO from io import BytesIO
@@ -248,7 +248,7 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool:
if hasattr(shape, "text"): if hasattr(shape, "text"):
content += shape.text + "\n" content += shape.text + "\n"
case ".xlsx": case ".xlsx":
if not pm.is_installed("openpyxl"): if not pm.is_installed("openpyxl"): # type: ignore
pm.install("openpyxl") pm.install("openpyxl")
from openpyxl import load_workbook from openpyxl import load_workbook
from io import BytesIO from io import BytesIO