fix

content_analyzer/document_parser.py

@@ -140,11 +140,13 @@ class DocumentProcessor:
         )
         self.gemini_client = None
         self.genai_module = None  # Store the module reference
-        if parameters.ENABLE_CHART_EXTRACTION:
+        # Instance-level flag instead of modifying global parameters
+        self.chart_extraction_enabled = parameters.ENABLE_CHART_EXTRACTION
+        if self.chart_extraction_enabled:
             self._init_gemini_vision()
         logger.debug(f"DocumentProcessor initialized with cache dir: {self.cache_dir}")
         logger.debug(f"Chunk size: {parameters.CHUNK_SIZE}, Chunk overlap: {parameters.CHUNK_OVERLAP}")
-        logger.debug(f"Chart extraction: {'enabled' if parameters.ENABLE_CHART_EXTRACTION else 'disabled'}")
+        logger.debug(f"Chart extraction: {'enabled' if self.chart_extraction_enabled else 'disabled'}")
 
     def _init_gemini_vision(self):
         """Initialize Gemini Vision client for chart analysis."""
@@ -156,7 +158,7 @@ class DocumentProcessor:
         except ImportError as e:
             logger.warning(f"google-genai not installed: {e}")
             logger.info("Install with: pip install google-genai")
-            parameters.ENABLE_CHART_EXTRACTION = False
+            self.chart_extraction_enabled = False  # Instance-level, not global
             return
         self.genai_module = genai
         try:
@@ -165,7 +167,7 @@ class DocumentProcessor:
             logger.info(f"✅ Gemini Vision client initialized")
         except Exception as e:
             logger.error(f"❌ Failed to initialize Gemini Vision client: {e}")
-            parameters.ENABLE_CHART_EXTRACTION = False
+            self.chart_extraction_enabled = False  # Instance-level, not global
 
     def validate_files(self, files: List) -> bool:
         """
@@ -288,8 +290,8 @@ class DocumentProcessor:
                 def run_pdfplumber():
                     return self._load_pdf_with_pdfplumber(file.name)
                 def run_charts():
-                    logger.info(f"ENABLE_CHART_EXTRACTION={parameters.ENABLE_CHART_EXTRACTION}, gemini_client={self.gemini_client is not None}")
-                    if parameters.ENABLE_CHART_EXTRACTION and self.gemini_client:
+                    logger.info(f"chart_extraction_enabled={self.chart_extraction_enabled}, gemini_client={self.gemini_client is not None}")
+                    if self.chart_extraction_enabled and self.gemini_client:
                         return self._extract_charts_from_pdf(file.name)
                     return []
                 try:
@@ -313,7 +315,7 @@ class DocumentProcessor:
                 except MemoryError as e:
                     logger.error(f"Out of memory in parallel PDF processing: {e}. Falling back to sequential.")
                     documents = self._load_pdf_with_pdfplumber(file.name)
-                    if parameters.ENABLE_CHART_EXTRACTION and self.gemini_client:
+                    if self.chart_extraction_enabled and self.gemini_client:
                         chart_docs = self._extract_charts_from_pdf(file.name)
                         if chart_docs:
                             documents.extend(chart_docs)