allow pdfs

app.py

@@ -52,16 +52,33 @@ text_splitter = CharacterTextSplitter()
 
 def process_text_file(file: AskFileResponse):
     import tempfile
+    import fitz 
+    import os
+
+    file_extension = os.path.splitext(file.name)[1].lower()
 
     with tempfile.NamedTemporaryFile(mode="w", delete=False, suffix=".txt") as temp_file:
         temp_file_path = temp_file.name
 
-    with open(temp_file_path, "wb") as f:
-        f.write(file.content)
-
-    text_loader = TextFileLoader(temp_file_path)
-    documents = text_loader.load_documents()
-    texts = text_splitter.split_texts(documents)
+    if file_extension == ".txt":
+        with open(temp_file_path, "wb") as f:
+            f.write(file.content)
+
+        text_loader = TextFileLoader(temp_file_path)
+        documents = text_loader.load_documents()
+        texts = text_splitter.split_texts(documents)
+
+    elif file_extension == ".pdf":
+        pdf_document = fitz.open(temp_file_path)
+        documents = []
+        for page_num in range(len(pdf_document)):
+            page = pdf_document.load_page(page_num)
+            text = page.get_text()
+            documents.append(text)
+        texts = text_splitter.split_texts(documents)
+    else:
+        raise ValueError("Unsupported file type")
+    
     return texts
 
 
@@ -72,8 +89,8 @@ async def on_chat_start():
     # Wait for the user to upload a file
     while files == None:
         files = await cl.AskFileMessage(
-            content="Please upload a .txt or .pdf File file to begin!",
-            accept=["text/plain"],
+            content="Please upload a .txt or .pdf file to begin!",
+            accept=["text/plain", "pdf"],
             max_size_mb=2,
             timeout=180,
         ).send()