Update app.py

app.py

@@ -41,12 +41,33 @@ if "OPENAI_API_KEY" in os.environ:
         # data = data1 + data2
         st.header('Multiple File Upload')
         uploaded_files = st.file_uploader('Upload your files',accept_multiple_files=True, type=['txt', 'pdf', 'csv', 'ppt', 'doc', 'xls', 'pptx', 'xlsx'])  
-        all_documents = []
-        for file in uploaded_files:
-            documents = load_document(file)
-            all_documents.extend(documents)
+        def load_file(file):
+            file_extension = os.path.splitext(file.name)[1].lower()
+            with tempfile.NamedTemporaryFile(delete=False, suffix=file_extension) as temp_file:
+                temp_file.write(file.getvalue())
+                temp_file_path = temp_file.name
+        
+            if file_extension == '.txt':
+                loader = TextLoader(temp_file_path)
+            elif file_extension == '.pdf':
+                loader = PyPDFLoader(temp_file_path)
+            elif file_extension == '.csv':
+                loader = CSVLoader(temp_file_path)
+            elif file_extension in ['.ppt', '.pptx']:
+                loader = UnstructuredPowerPointLoader(temp_file_path)
+            elif file_extension in ['.doc', '.docx']:
+                loader = UnstructuredWordDocumentLoader(temp_file_path)
+            elif file_extension in ['.xls', '.xlsx']:
+                loader = UnstructuredExcelLoader(temp_file_path)
+            else:
+                os.unlink(temp_file_path)
+                raise ValueError(f"Unsupported file type: {file_extension}")
+        
+            documents = loader.load()
+            os.unlink(temp_file_path)
+            return documents
         text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-        all_splits = text_splitter.split_documents(all_documents)
+        all_splits = text_splitter.split_documents(documents)
         embeddings = OpenAIEmbeddings(model="text-embedding-ada-002")
         vectorstore = Chroma.from_documents(documents=all_splits, embedding=embeddings)
         retriever = vectorstore.as_retriever(k=4)