assigned

app.py

@@ -171,7 +171,8 @@ def webpage_to_json(content: str, is_url: bool, schema: BaseModel) -> Dict[str,
     - Return the extracted data in the format specified by the schema"""
     
     # Initialize pipeline components
-    preprocessor = BasicPreprocessor(config={'keep_tags': False})
+    # TODO: improve the RAG system and optimize (don't instantiate every time)
+    preprocessor = BasicPreprocessor(config={'keep_tags': False}) 
     try:
         llm = GeminiLLMClient(config={'api_key': os.getenv('GEMINI_API_KEY')})
     except Exception as e:

web2json/ai_extractor.py

@@ -123,4 +123,6 @@ class AIExtractor:
         response = self.llm_client.call_api(prompt)
         return response
 
-        
+# TODO: RAGExtractor class
+class RAGExtractor(AIExtractor):
+    pass