Update Sejarah.py

Sejarah.py

@@ -1,14 +1,48 @@
 import langid
+from haystack import Pipeline
+from haystack.nodes import TextConverter, PreProcessor, BM25Retriever, FARMReader
+from haystack.document_stores import InMemoryDocumentStore
     
 class Sejarah:
     def __init__(self):
-        self.name = 'Sejarah'
+        
+        document_store = InMemoryDocumentStore(use_bm25=True)
+
+        # #initialize the pipeline
+        # indexing_pipeline = Pipeline()
+        # text_converter = TextConverter()
+        # preprocessor = PreProcessor(
+        #     clean_whitespace=True,
+        #     clean_header_footer=True,
+        #     clean_empty_lines=True,
+        #     split_by="word",
+        #     split_length=200,
+        #     split_overlap=20,
+        #     split_respect_sentence_boundary=True,
+        # )
+
+        # indexing_pipeline.add_node(component=text_converter, name="TextConverter", inputs=["File"])
+        # indexing_pipeline.add_node(component=preprocessor, name="PreProcessor", inputs=["TextConverter"])
+        # indexing_pipeline.add_node(component=document_store, name="DocumentStore", inputs=["PreProcessor"])
+
+        # doc_dir = "/content/drive/Shareddrives/Natural Language Processing/Dataset/txt files"
+
+        # files_to_index = [doc_dir + "/" + f for f in os.listdir(doc_dir)]
+        # indexing_pipeline.run_batch(file_paths=files_to_index)
+
+        # retriever = BM25Retriever(document_store=document_store)
+        # reader = FARMReader(model_name_or_path="primasr/malaybert-for-eqa-finetuned", use_gpu=True)
+
+        # self.querying_pipeline = Pipeline()
+        # self.querying_pipeline.add_node(component=retriever, name="Retriever", inputs=["Query"])
+        # self.querying_pipeline.add_node(component=reader, name="Reader", inputs=["Retriever"])
 
     def interface(self, question):
         language = self.detect_language(question)
         answer = "Answer of "+question+" is: "+language
         return answer
 
+    
     def detect_language(self, content):
         lang = langid.classify(content)
         return lang