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

Sync modifications from main branch

Browse Source
This commit is contained in:
yangdx
2025-02-21 21:07:37 +08:00
parent cff229a806
commit b144e0c3b0
1 changed files with 66 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

67
lightrag/api/routers/document_routes.py
View File

@@ -117,6 +117,37 @@ class DocumentManager:
".docx",
".pptx",
".xlsx",
".rtf", # Rich Text Format
".odt", # OpenDocument Text
".tex", # LaTeX
".epub", # Electronic Publication
".html", # HyperText Markup Language
".htm", # HyperText Markup Language
".csv", # Comma-Separated Values
".json", # JavaScript Object Notation
".xml", # eXtensible Markup Language
".yaml", # YAML Ain't Markup Language
".yml", # YAML
".log", # Log files
".conf", # Configuration files
".ini", # Initialization files
".properties", # Java properties files
".sql", # SQL scripts
".bat", # Batch files
".sh", # Shell scripts
".c", # C source code
".cpp", # C++ source code
".py", # Python source code
".java", # Java source code
".js", # JavaScript source code
".ts", # TypeScript source code
".swift", # Swift source code
".go", # Go source code
".rb", # Ruby source code
".php", # PHP source code
".css", # Cascading Style Sheets
".scss", # Sassy CSS
".less", # LESS CSS
),
):
self.input_dir = Path(input_dir)
@@ -170,7 +201,41 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool:
# Process based on file type
match ext:
case ".txt" | ".md":
case (
".txt"
| ".md"
| ".html"
| ".htm"
| ".tex"
| ".json"
| ".xml"
| ".yaml"
| ".yml"
| ".rtf"
| ".odt"
| ".epub"
| ".csv"
| ".log"
| ".conf"
| ".ini"
| ".properties"
| ".sql"
| ".bat"
| ".sh"
| ".c"
| ".cpp"
| ".py"
| ".java"
| ".js"
| ".ts"
| ".swift"
| ".go"
| ".rb"
| ".php"
| ".css"
| ".scss"
| ".less"
):
content = file.decode("utf-8")
case ".pdf":
if not pm.is_installed("pypdf2"):