adding online PDF loader

app.py

@@ -2,7 +2,7 @@ import os
 import gradio as gr
 
 from langchain.document_loaders import PDFMinerLoader,CSVLoader ,UnstructuredWordDocumentLoader,TextLoader,OnlinePDFLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.text_splitter import CharacterTextSplitter
 from langchain.embeddings import SentenceTransformerEmbeddings
 from langchain.vectorstores import FAISS
 from langchain import HuggingFaceHub
@@ -27,7 +27,7 @@ def get_openai_chat_model(API_key):
     return llm
 
 def process_documents(documents,data_chunk=1000,chunk_overlap=50):
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=data_chunk, chunk_overlap=chunk_overlap)
+    text_splitter = CharacterTextSplitter(chunk_size=data_chunk, chunk_overlap=chunk_overlap,separator='\n')
     texts = text_splitter.split_documents(documents)
     return texts
 
@@ -56,7 +56,6 @@ def document_loader(file_path,api_key,doc_type='pdf',llm='Huggingface'):
     elif doc_type == 'word':
         document = process_word_document(document_file=file_path)
     if document:
-        print("Document :",document)
         texts = process_documents(documents=document)
         vector_db = FAISS.from_documents(documents=texts, embedding= embedding_model)
         global qa 
@@ -77,7 +76,6 @@ def process_text_document(document_file):
     document = loader.load()
     return document
 
-
 def process_csv_document(document_file):
     loader = CSVLoader(file_path=document_file.name)
     document = loader.load()
@@ -94,7 +92,7 @@ def process_pdf_document(document_file):
     print("Document File Name :",document_file.name)
     loader = PDFMinerLoader(document_file.name)
     document = loader.load()
-    return document[0]
+    return document