Update app.py

app.py

@@ -89,11 +89,7 @@ def get_table_download_link(file_path):
             data = file.read()
         except:
             st.write('')
-            return file_path
-    #import codecs
-    #with codecs.open(file_path, "r", "utf-8") as file:
-    #    data = file.read()
-    
+            return file_path    
     b64 = base64.b64encode(data.encode()).decode()  
     file_name = os.path.basename(file_path)
     ext = os.path.splitext(file_name)[1]  # get the file extension
@@ -148,14 +144,10 @@ def chat_with_model(prompt, document_section, model_choice='gpt-3.5-turbo'):
     conversation.append({'role': 'user', 'content': prompt})
     if len(document_section)>0:
         conversation.append({'role': 'assistant', 'content': document_section})
-
-    # iterate through the stream of events
+        
     start_time = time.time()
-
-    
     report = []
     res_box = st.empty()
-
     collected_chunks = []
     collected_messages = []
 
@@ -182,7 +174,6 @@ def chat_with_model(prompt, document_section, model_choice='gpt-3.5-turbo'):
             st.write('.')
         
     full_reply_content = ''.join([m.get('content', '') for m in collected_messages])
-    #st.write(f"Full conversation received: {full_reply_content}")
     st.write("Elapsed time:")
     st.write(time.time() - start_time)
     return full_reply_content
@@ -195,7 +186,7 @@ def chat_with_file_contents(prompt, file_content, model_choice='gpt-3.5-turbo'):
     response = openai.ChatCompletion.create(model=model_choice, messages=conversation)
     return response['choices'][0]['message']['content']
 
-def extract_text_from_pdfs(pdf_docs):
+def pdf2txt(pdf_docs):
     text = ""
     for pdf in pdf_docs:
         pdf_reader = PdfReader(pdf)
@@ -203,16 +194,16 @@ def extract_text_from_pdfs(pdf_docs):
             text += page.extract_text()
     return text
 
-def split_text_into_chunks(text):
+def txt2chunks(text):
     text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len)
     return text_splitter.split_text(text)
 
-def create_vector_store_from_text_chunks(text_chunks):
+def vector_store(text_chunks):
     key = os.getenv('OPENAI_API_KEY')
     embeddings = OpenAIEmbeddings(openai_api_key=key)
     return FAISS.from_texts(texts=text_chunks, embedding=embeddings)
 
-def create_conversation_chain(vectorstore):
+def get_chain(vectorstore):
     llm = ChatOpenAI()
     memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
     return ConversationalRetrievalChain.from_llm(llm=llm, retriever=vectorstore.as_retriever(), memory=memory)
@@ -338,8 +329,6 @@ def main():
 if __name__ == "__main__":
     main()
 
-
-
 load_dotenv()
 st.write(css, unsafe_allow_html=True)
 
@@ -352,12 +341,12 @@ with st.sidebar:
     st.subheader("Your documents")
     docs = st.file_uploader("Upload your documents", accept_multiple_files=True)
     with st.spinner("Processing"):
-        raw = extract_text_from_pdfs(docs)
+        raw = pdf2txt(docs)
         if len(raw) > 0:
             length = str(len(raw))
-            text_chunks = split_text_into_chunks(raw)
-            vectorstore = create_vector_store_from_text_chunks(text_chunks)
-            st.session_state.conversation = create_conversation_chain(vectorstore)
+            text_chunks = txt2chunks(raw)
+            vectorstore = vector_store(text_chunks)
+            st.session_state.conversation = get_chain(vectorstore)
             st.markdown('# Extracted Text of Length:' + length + ' and Created Search Index')
             filename = generate_filename(raw, 'txt')
             create_file(filename, raw, '')