Update app.py

app.py

@@ -59,40 +59,57 @@ def process_file(file: cl.AskFileMessage):
     return texts
 
 
+
 @cl.on_chat_start
 async def on_chat_start():
     files = None
 
     # Wait for the user to upload a file
-    while files == None:
+    while files is None:
+        # Note: This now accepts both text/plain and application/pdf files
         files = await cl.AskFileMessage(
-            content="Please upload a PDF file to begin!",
-            accept=["application/pdf"],
-            max_size_mb=20,
+            content="Please upload a text or PDF file to begin!",
+            accept=["text/plain", "application/pdf"],
+            max_size_mb=20,  # Assuming PDFs might be larger
             timeout=180,
         ).send()
 
     file = files[0]
 
-    msg = cl.Message(
-        content=f"Processing `{file.name}`..."
-    )
+    # Notify the user that their file is being processed
+    msg = cl.Message(content=f"Processing `{file.name}`...")
     await msg.send()
 
-    # load the file
-    texts = process_file(file)
-
-    print(texts[0])
+    # Initialize an empty list for texts, this will be populated based on file type
+    texts = []
 
-    # Create a metadata for each chunk
-    metadatas = [{"source": f"{i}-pl"} for i in range(len(texts))]
-
-    # Create a Chroma vector store
-    embeddings = OpenAIEmbeddings()
-    docsearch = await cl.make_async(Chroma.from_texts)(
-        texts, embeddings, metadatas=metadatas
-    )
+    # Check the file type and process accordingly
+    if file.content_type == "text/plain":
+        # Handle text file
+        with open(file.path, "r", encoding="utf-8") as f:
+            text = f.read()
+        texts.append(text)  # Add the text to the texts list
 
+        # Update the user about the text file
+        await cl.Message(
+            content=f"`{file.name}` uploaded, it contains {len(text)} characters!"
+        ).send()
+        
+    elif file.content_type == "application/pdf":
+        # Handle PDF file
+        texts = process_file(file)  # Assuming process_file() is a function you've defined to extract text from PDF
+
+        # Create metadata for each chunk
+        metadatas = [{"source": f"{i}-pl"} for i in range(len(texts))]
+
+        # Create a Chroma vector store
+        embeddings = OpenAIEmbeddings()
+        docsearch = await cl.make_async(Chroma.from_texts)(
+            texts, embeddings, metadatas=metadatas
+        )
+
+    # The rest of your setup, like creating the chain, goes here
+    # This part is unchanged from your second snippet
     message_history = ChatMessageHistory()
 
     memory = ConversationBufferMemory(
@@ -102,7 +119,6 @@ async def on_chat_start():
         return_messages=True,
     )
 
-    # Create a chain that uses the Chroma vector store
     chain = ConversationalRetrievalChain.from_llm(
         ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0, streaming=True),
         chain_type="stuff",