change method to import from folder

app.py

@@ -202,26 +202,27 @@ def load_embeddings():
     return embeddings
 
 def main():
-    # msgs = StreamlitChatMessageHistory(key="langchain_messages")
-    # print(msgs)
-    # if "messages" not in st.session_state:
-    #     st.session_state.messages = []
+    data = []
+    msgs = StreamlitChatMessageHistory(key="langchain_messages")
+    print(msgs)
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
 
     # DB_FAISS_UPLOAD_PATH = "vectorstores/db_faiss"
     st.header("DOCUMENT QUESTION ANSWERING IS2")
-    # directory = "data"
-    # data_dir = UploadDoc(directory).create_document()
-    # data.extend(data_dir)
+    directory = "data"
+    data_dir = UploadDoc(directory).create_document()
+    data.extend(data_dir)
 
-    # #create vector from upload 
-    # if len(data) > 0 :
-    #     sp_docs = split_docs(documents = data)
-    #     st.write(f"This document have {len(sp_docs)} chunks")
-    #     embeddings = load_embeddings()
-    #     with st.spinner('Wait for create vector'):
-    #         db = FAISS.from_documents(sp_docs, embeddings)
-    #         # db.save_local(DB_FAISS_UPLOAD_PATH)
-    #         # st.write(f"Your model is already store in {DB_FAISS_UPLOAD_PATH}")
+    #create vector from upload 
+    if len(data) > 0 :
+        sp_docs = split_docs(documents = data)
+        st.write(f"This document have {len(sp_docs)} chunks")
+        embeddings = load_embeddings()
+        with st.spinner('Wait for create vector'):
+            db = FAISS.from_documents(sp_docs, embeddings)
+            # db.save_local(DB_FAISS_UPLOAD_PATH)
+            # st.write(f"Your model is already store in {DB_FAISS_UPLOAD_PATH}")
 
     llm = load_llama2_llamaCpp()
     qa_prompt = set_custom_prompt()
@@ -229,38 +230,31 @@ def main():
     #memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
     #doc_chain = load_qa_chain(llm, chain_type="stuff", prompt = qa_prompt)
     #question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)
-    embeddings = load_embeddings()
+    #embeddings = load_embeddings()
 
     
-    uploaded_file = st.file_uploader('Choose your .pdf file', type="pdf")
-    print(uploaded_file)
-    if uploaded_file is not None:
-        pdf_reader = PdfReader(uploaded_file)
-        text = ""
-        for page in pdf_reader.pages:
-            text += page.extract_text()
-        print(text)
-        db = FAISS.from_texts(text, embeddings)
+    # uploaded_file = st.file_uploader('Choose your .pdf file', type="pdf")
+    # print(uploaded_file)
+    # if uploaded_file is not None:
+    #     pdf_reader = PdfReader(uploaded_file)
+    #     text = ""
+    #     for page in pdf_reader.pages:
+    #         text += page.extract_text()
+    #     print(text)
+    #     db = FAISS.from_texts(text, embeddings)
 
-        memory = ConversationBufferMemory(memory_key="chat_history", 
-                                  return_messages=True, 
-                                  input_key="query", 
-                                  output_key="result")
-        qa_chain = RetrievalQA.from_chain_type(
-            llm = llm,
-            chain_type = "stuff",
-            retriever = db.as_retriever(search_kwargs = {'k':3}), 
-            return_source_documents = True,
-            memory = memory,
-            chain_type_kwargs = {"prompt":qa_prompt}) 
+    memory = ConversationBufferMemory(memory_key="chat_history", 
+                              return_messages=True, 
+                              input_key="query", 
+                              output_key="result")
+    qa_chain = RetrievalQA.from_chain_type(
+        llm = llm,
+        chain_type = "stuff",
+        retriever = db.as_retriever(search_kwargs = {'k':3}), 
+        return_source_documents = True,
+        memory = memory,
+        chain_type_kwargs = {"prompt":qa_prompt}) 
 
-        query = st.text_input("ASK ABOUT THE DOCS:")        
-        if query:
-            start = time.time()
-            response = qa_chain({'query': query})
-            st.write(response["result"])
-            end = time.time()
-            st.write("Respone time:",int(end-start),"sec")
     
         # qa_chain = ConversationalRetrievalChain(
         #     retriever =db.as_retriever(search_kwargs={'k':2}), 
@@ -272,44 +266,44 @@ def main():
         #     #get_chat_history=lambda h :h
         # )
 
-        # for message in st.session_state.messages:
-        #     with st.chat_message(message["role"]):
-        #         st.markdown(message["content"])
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
 
-        #     # Accept user input
-        # if query := st.chat_input("What is up?"):
-        #     # Display user message in chat message container
-        #     with st.chat_message("user"):
-        #         st.markdown(query)
-        #     # Add user message to chat history
-        #     st.session_state.messages.append({"role": "user", "content": query})
+        # Accept user input
+    if query := st.chat_input("What is up?"):
+        # Display user message in chat message container
+        with st.chat_message("user"):
+            st.markdown(query)
+        # Add user message to chat history
+        st.session_state.messages.append({"role": "user", "content": query})
 
-        #     start = time.time()
+        start = time.time()
 
-        #     response = qa_chain({'query': query})
+        response = qa_chain({'query': query})
 
-        #     # url_list = set([i.metadata['source']  for i in response['source_documents']])
-        #     #print(f"condensed quesion : {question_generator.run({'chat_history': response['chat_history'], 'question' : query})}")
-            
-        #     with st.chat_message("assistant"):
-        #         st.markdown(response['result'])
-            
-        #     end = time.time()
-        #     st.write("Respone time:",int(end-start),"sec")
-        #     print(response)
-                    
-        #     # Add assistant response to chat history
-        #     st.session_state.messages.append({"role": "assistant", "content": response['result']})
+        # url_list = set([i.metadata['source']  for i in response['source_documents']])
+        #print(f"condensed quesion : {question_generator.run({'chat_history': response['chat_history'], 'question' : query})}")
+        
+        with st.chat_message("assistant"):
+            st.markdown(response['result'])
+        
+        end = time.time()
+        st.write("Respone time:",int(end-start),"sec")
+        print(response)
+                
+        # Add assistant response to chat history
+        st.session_state.messages.append({"role": "assistant", "content": response['result']})
 
-        #     # with st.expander("See the related documents"):
-        #     #     for count, url in enumerate(url_list):
-        #     #         #url_reg = regex_source(url)
-        #     #         st.write(str(count+1)+":", url)
+        # with st.expander("See the related documents"):
+        #     for count, url in enumerate(url_list):
+        #         #url_reg = regex_source(url)
+        #         st.write(str(count+1)+":", url)
 
-        # clear_button = st.button("Start new convo")
-        # if clear_button :
-        #     st.session_state.messages = []
-        #     qa_chain.memory.chat_memory.clear() 
+    clear_button = st.button("Start new convo")
+    if clear_button :
+        st.session_state.messages = []
+        qa_chain.memory.chat_memory.clear() 
             
   
 if __name__ == '__main__':