Update app.py

app.py

@@ -29,52 +29,31 @@ with open(css_file) as f:
     
 HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
 
-#documents=[]
-
 def generate_random_string(length):
     letters = string.ascii_lowercase
     return ''.join(random.choice(letters) for i in range(length))  
 
-#random_string = generate_random_string(20)
-#directory_path=random_string
-
-#if "pdf_files" not in st.session_state:
-    #st.session_state.pdf_files = None
-
-#if "documents" not in st.session_state:
-    #st.session_state.documents = None
-    
-if "new_index" not in st.session_state:
-    st.session_state.new_index = None
-
-if "i_pdf_files" not in st.session_state:
-    st.session_state.i_pdf_files = None    
-
 if "query_engine" not in st.session_state:
     st.session_state.query_engine = None
 
 with st.sidebar:
     st.subheader("Upload your Documents Here: ")
-    pdf_files = st.file_uploader("Choose your PDF Files and Press OK", type=['pdf'], accept_multiple_files=True)
-    st.session_state.i_pdf_files = pdf_files
-    if not st.session_state.i_pdf_files:
+    pdf_files = st.file_uploader("Choose your PDF Files and Press OK", type=['pdf'], accept_multiple_files=True)    
+    if not pdf_files:
         st.warning("请上传文档文件")
         st.stop()      
     else:
-        if "uploadedfile_path" not in st.session_state:
-            st.session_state.uploadedfile_path=generate_random_string(20)
-        if not os.path.exists(st.session_state.uploadedfile_path):
-            os.makedirs(st.session_state.uploadedfile_path)        
-        for pdf_file in st.session_state.i_pdf_files:
-            file_path = os.path.join(st.session_state.uploadedfile_path, pdf_file.name)
+        uploadedfile_path=generate_random_string(20)                
+        for pdf_file in pdf_files:
+            file_path = os.path.join(uploadedfile_path, pdf_file.name)
             with open(file_path, 'wb') as f:
                 f.write(pdf_file.read())
             st.success(f"File '{pdf_file.name}' saved successfully.")
+    if st.button('Process for QA'):        
         try:
             start_1 = timeit.default_timer() # Start timer
             st.write(f"QA文档加载开始：{start_1}")            
-            if "documents" not in st.session_state:
-                st.session_state.documents = SimpleDirectoryReader(st.session_state.uploadedfile_path).load_data()
+            documents = SimpleDirectoryReader(uploadedfile_path).load_data()
             end_1 = timeit.default_timer() # Start timer
             st.write(f"QA文档加载结束：{end_1}")
             st.write(f"QA文档加载耗时：{end_1 - start_1}")
@@ -95,13 +74,13 @@ with st.sidebar:
             st.session_state.service_context = ServiceContext.from_defaults(llm_predictor=st.session_state.llm_predictor, embed_model=st.session_state.embed_model)
         start_3 = timeit.default_timer() # Start timer
         st.write(f"向量库构建开始：{start_3}")
-        st.session_state.new_index = VectorStoreIndex.from_documents(st.session_state.documents, service_context=st.session_state.service_context)
+        new_index = VectorStoreIndex.from_documents(documents, service_context=st.session_state.service_context)
         end_3 = timeit.default_timer() # Start timer
         st.write(f"向量库构建结束：{end_3}")
         st.write(f"向量库构建耗时：{end_3 - start_3}")
         directory_path = generate_random_string(20)
         os.makedirs(directory_path)
-        st.session_state.new_index.storage_context.persist("directory_path")
+        new_index.storage_context.persist("directory_path")
         storage_context = StorageContext.from_defaults(persist_dir="directory_path")
         start_4 = timeit.default_timer() # Start timer
         st.write(f"向量库装载开始：{start_4}")