Update app.py

app.py

@@ -14,6 +14,7 @@ from aimakerspace.openai_utils.embedding import EmbeddingModel
 from aimakerspace.vectordatabase import VectorDatabase
 from aimakerspace.openai_utils.chatmodel import ChatOpenAI
 import chainlit as cl
+from langchain_community.document_loaders import PyPDFLoader
 
 system_template = """\
 Use the following context to answer a users question. If you cannot find the answer in the context, say you don't know the answer."""
@@ -76,6 +77,23 @@ def process_text_file(file: AskFileResponse):
     return texts
 
 
+def process_pdf_file(file: AskFileResponse):
+    import tempfile
+
+    with tempfile.NamedTemporaryFile(
+        mode="w", delete=False, suffix=".pdf"
+    ) as temp_file:
+        temp_file_path = temp_file.name
+
+    with open(temp_file_path, "wb") as f:
+        f.write(file.content)
+
+    pdf_loader = PyPDFLoader(temp_file_path)
+    documents = pdf_loader.load()
+    texts = text_splitter.split_texts(documents)
+    return texts
+
+
 @cl.on_chat_start
 async def on_chat_start():
     files = None
@@ -84,7 +102,7 @@ async def on_chat_start():
     while files == None:
         files = await cl.AskFileMessage(
             content="Please upload a Text File file to begin!",
-            accept=["text/plain"],
+            accept=["text/plain", "application/pdf"],
             max_size_mb=2,
             timeout=180,
         ).send()
@@ -97,7 +115,10 @@ async def on_chat_start():
     await msg.send()
 
     # load the file
-    texts = process_text_file(file)
+    if file.path.endswith(".pdf"):
+        texts = process_pdf_file(file)
+    else:
+        texts = process_text_file(file)
 
     print(f"Processing {len(texts)} text chunks")
 
@@ -129,4 +150,4 @@ async def main(message):
     async for stream_resp in result["response"]:
         await msg.stream_token(stream_resp)
 
-    await msg.send()
+    await msg.send()