Update rag.py

rag.py

@@ -41,10 +41,12 @@ def document_loading():
     # PDF
     loader = PyPDFLoader(PDF_URL)
     docs.extend(loader.load())
+    print("### Load PDF")
     
     # Web
     loader = WebBaseLoader(WEB_URL)
     docs.extend(loader.load())
+    print("### Load Web")
     
     # YouTube
     #loader = GenericLoader(YoutubeAudioLoader([YOUTUBE_URL], YOUTUBE_DIR), 
@@ -57,14 +59,17 @@ def document_splitting(config, docs):
     text_splitter = RecursiveCharacterTextSplitter(chunk_overlap = config["chunk_overlap"],
                                                    chunk_size = config["chunk_size"])
     
+    print("### Split")
     return text_splitter.split_documents(docs)
     
 def document_storage_chroma(chunks):
+    print("### Store")
     Chroma.from_documents(documents = chunks, 
                           embedding = OpenAIEmbeddings(disallowed_special = ()), 
                           persist_directory = CHROMA_DIR)
 
 def document_storage_mongodb(chunks):
+    print("### Store")    
     MongoDBAtlasVectorSearch.from_documents(documents = chunks,
                                             embedding = OpenAIEmbeddings(disallowed_special = ()),
                                             collection = collection,