Graph-Native Infrastructure for Context and Accountable AI Systems
Python agent-memoryaiai-governanceai-infrastructureartificial-intelligencecontext-engineeringcontext-graphsdata-engineeringdecision-intelligencedeveloper-toolsexplainable-aigenerative-aigraph-ragknowledge-graphllmontologyprovenancepythonreasoningsemantic-search
fix: make pdfplumber import lazy in pdf_parser to fix CI collection error
KaifAhmad1e18e6d1a0030
diff --git a/semantica/parse/pdf_parser.py b/semantica/parse/pdf_parser.pyindex 4a087304..7ad31ced 100644--- a/semantica/parse/pdf_parser.py+++ b/semantica/parse/pdf_parser.py@@ -33,9 +33,6 @@ from dataclasses import dataclass, fieldfrom pathlib import Pathfrom typing import Any, Dict, List, Optional, Union-import pdfplumber-from PIL import Image-from ..utils.exceptions import ProcessingError, ValidationErrorfrom ..utils.logging import get_loggerfrom ..utils.progress_tracker import get_progress_tracker@@ -119,6 +116,13 @@ class PDFParser:raise ValidationError(f"File is not a PDF: {file_path}")try:+ try:+ import pdfplumber+ except ImportError:+ raise ProcessingError(+ "pdfplumber is required for PDF parsing. "+ "Install with: pip install pdfplumber"+ )with pdfplumber.open(str(file_path)) as pdf:# Extract metadatametadata = self._extract_metadata(pdf)