Update app.py

app.py

@@ -20,7 +20,7 @@ from htmlTemplates import css, bot_template, user_template
 from langchain.llms import HuggingFaceHub
 
 
-def get_pdf_text(pdf_docs):
+def get_pdf_pages(pdf_docs):
     """
     Extract text from a list of PDF documents.
 
@@ -35,16 +35,15 @@ def get_pdf_text(pdf_docs):
         Extracted text from all the PDF documents.
 
     """
-    text = ""
+    pages = []
     for pdf in pdf_docs:
         pdf_loader = UnstructuredPDFLoader(pdf)
         pdf_pages = pdf_loader.load_and_split()
-        for page in pdf_pages:
-            text += page.extract_text()
-    return text
+        pages=paegs+pdf_pages
+    return pages
 
 
-def get_text_chunks(text):
+def get_text_chunks(pages):
     """
     Split the input text into chunks.
 
@@ -62,7 +61,7 @@ def get_text_chunks(text):
     text_splitter = RecursiveCharacterTextSplitter(
         chunk_size=1024, chunk_overlap=64
     )
-    texts = text_splitter.split_text(text)
+    texts = text_splitter.split_documents(pages)
     return texts
 
 
@@ -173,10 +172,10 @@ def main():
         if st.button("Process"):
             with st.spinner("Processing"):
                 # get the raw text
-                text = get_pdf_text(pdf_docs)
+                pages = get_pdf_pages(pdf_docs)
 
                 # get the text chunks
-                text_chunks = get_text_chunks(text)
+                text_chunks = get_text_chunks(pages)
 
                 # create vector store
                 vectorstore = get_vectorstore(text_chunks)