Update RAG_class.py

RAG_class.py

@@ -8,44 +8,20 @@ class RAG_1177:
     def __init__(self):
         self.db_name = "RAG_1177"
         
-        self.text_splitter =  RecursiveCharacterTextSplitter(chunk_size=2500,chunk_overlap=500,length_function=len)
         self.model = SentenceTransformer('KBLab/sentence-bert-swedish-cased')
         self.client = chromadb.PersistentClient(path="RAG_1177_db")
         self.db = self.client.get_or_create_collection(self.db_name)
 
-        self.url_list_path = "all_urls_list.txt"
-        self.text_folder = "scraped_texts/"
-
-    def chunk_text_file(self, file_name):
-        file_name = self.text_folder + file_name
-        with open(file_name, 'r', encoding='utf-8') as f:
-            text = f.read()
-        chunks = self.text_splitter.create_documents([text])
-        #append chunks as elements in a list
-        chunks = [chunk.page_content for chunk in chunks]
-        return chunks
-    
-    def get_file_names(self, folder_path):
-        doc_list = os.listdir(folder_path)
-        doc_list = sorted(doc_list, key=lambda x: int(x.split('-')[-1].split('.')[0]))
-        return doc_list
     
     def get_embeddings(self, text):
         embeddings = self.model.encode(text)
         return (embeddings.tolist())
     
-    def get_url(self, url_index):
-        with open(self.url_list_path, 'r') as f:
-            urls = f.readlines()
-        return urls[url_index].strip()
     
     def get_ids(self, num_ids):
         ids = [str(uuid.uuid4()) for _ in range(num_ids)]
         return ids
         
-    def get_url_dict(self, url, integer):
-        url_list = [{"url": url} for _ in range(integer)]
-        return url_list
     
     def delete_collection(self):
         self.client.delete_collection(self.db_name)