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

Update document_routes.py

Browse Source
This commit is contained in:
Saifeddine ALOUI
2025-03-05 15:32:39 +01:00
committed by GitHub
parent 20f2e57260
commit aaa8194423
1 changed files with 73 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
lightrag/api/routers/document_routes.py
View File

@@ -16,7 +16,7 @@ from pydantic import BaseModel, Field, field_validator
from lightrag import LightRAG from lightrag import LightRAG
from lightrag.base import DocProcessingStatus, DocStatus from lightrag.base import DocProcessingStatus, DocStatus
from ..utils_api import get_api_key_dependency from lightrag.api.utils_api import get_api_key_dependency, global_args
router = APIRouter(prefix="/documents", tags=["documents"]) router = APIRouter(prefix="/documents", tags=["documents"])
@@ -237,6 +237,14 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool:
) )
return False return False
case ".pdf": case ".pdf":
if global_args["main_args"].document_loading_tool=="DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter
converter = DocumentConverter()
result = converter.convert(file_path)
content = result.document.export_to_markdown()
else:
if not pm.is_installed("pypdf2"): # type: ignore 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
@@ -247,6 +255,14 @@ 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 global_args["main_args"].document_loading_tool=="DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter
converter = DocumentConverter()
result = converter.convert(file_path)
content = result.document.export_to_markdown()
else:
if not pm.is_installed("python-docx"): # type: ignore if not pm.is_installed("python-docx"): # type: ignore
pm.install("docx") pm.install("docx")
from docx import Document # type: ignore from docx import Document # type: ignore
@@ -256,6 +272,14 @@ 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 global_args["main_args"].document_loading_tool=="DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter
converter = DocumentConverter()
result = converter.convert(file_path)
content = result.document.export_to_markdown()
else:
if not pm.is_installed("python-pptx"): # type: ignore if not pm.is_installed("python-pptx"): # type: ignore
pm.install("pptx") pm.install("pptx")
from pptx import Presentation # type: ignore from pptx import Presentation # type: ignore
@@ -268,6 +292,14 @@ 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 global_args["main_args"].document_loading_tool=="DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter
converter = DocumentConverter()
result = converter.convert(file_path)
content = result.document.export_to_markdown()
else:
if not pm.is_installed("openpyxl"): # type: ignore if not pm.is_installed("openpyxl"): # type: ignore
pm.install("openpyxl") pm.install("openpyxl")
from openpyxl import load_workbook # type: ignore from openpyxl import load_workbook # type: ignore