Update utils.py

utils.py

@@ -128,18 +128,14 @@ RAG_CHAIN_PROMPT = PromptTemplate(input_variables = ["context", "question"],
 #Pfad, wo Docs/Bilder/Filme abgelegt werden können - lokal, also hier im HF Space (sonst auf eigenem Rechner)
 PATH_WORK = "."
 CHROMA_DIR  = "/chroma/kkg"
-#CHROMA_PDF = './chroma/kkg/pdf'
-#CHROMA_WORD = './chroma/kkg/word'
+CHROMA_PDF = './chroma/kkg/pdf'
+CHROMA_WORD = './chroma/kkg/word'
 CHROMA_EXCEL = './chroma/kkg/excel'
 YOUTUBE_DIR = "/youtube"
 HISTORY_PFAD = "/data/history"
-#DOCS_DIR_PDF = "chroma/kkg/pdf"
-#DOCS_DIR_WORD = "chroma/kkg/word"
+DOCS_DIR_PDF = "chroma/kkg/pdf"
+DOCS_DIR_WORD = "chroma/kkg/word"
 
-CHROMA_PDF = './chroma/kkg'
-CHROMA_WORD = './chroma/kkg'
-DOCS_DIR_PDF = "chroma/kkg"
-DOCS_DIR_WORD = "chroma/kkg"
 ###############################################
 #URLs zu Dokumenten oder andere Inhalte, die einbezogen werden sollen
 PDF_URL       = "https://arxiv.org/pdf/2303.08774.pdf"
@@ -331,16 +327,17 @@ def document_loading_splitting():
     print("Directory Loader neu............................")
     # kreiere einen DirectoryLoader für jeden file type
     pdf_loader = create_directory_loader('.pdf', CHROMA_PDF)
-    #word_loader = create_directory_loader('.word', CHROMA_WORD)
+    word_loader = create_directory_loader('.word', CHROMA_WORD)
     
     # Load the files
     pdf_documents = pdf_loader.load()
-    #word_documents = word_loader.load()
+    word_documents = word_loader.load()
 
     #alle zusammen in docs...
     docs.extend(pdf_documents)
-    #docs.extend(word_documents)
-    print("docs???..........."+str(docs[0].metadata["title"]))
+    docs.extend(word_documents)
+    for doc in docs:
+        print("docs???..........."+str(doc.metadata["title"]))
     #andere loader...
     # Load PDF
     #loader = PyPDFLoader(PDF_URL)