Update app.py

app.py

@@ -1,43 +1,8 @@
-import os
-os.environ["CHAINLIT_STORAGE_DIR"] = "/app/.chainlit"
+# ✅ OLD (deprecated)
+# from langchain.document_loaders import PyPDFLoader
+# from langchain.llms import OpenAI
 
+# ✅ NEW (correct)
 from langchain_community.document_loaders import PyPDFLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.chains.question_answering import load_qa_chain
-from langchain.llms import OpenAI  # replace with Groq if needed
-
-import chainlit as cl
-
-@cl.on_chat_start
-async def start():
-    await cl.Message("👋 Upload a PDF to ask questions!").send()
-
-@cl.on_message
-async def handle_message(message: cl.Message):
-    files = await cl.AskFileMessage("📎 Upload your PDF", accept=["application/pdf"]).send()
-    if not files:
-        await cl.Message("❌ No file received.").send()
-        return
-
-    file = files[0]
-    file_path = file.path
-
-    loader = PyPDFLoader(file_path)
-    documents = loader.load()
-
-    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    chunks = splitter.split_documents(documents)
-
-    embeddings = HuggingFaceEmbeddings()
-    vectordb = FAISS.from_documents(chunks, embeddings)
-
-    qa_chain = load_qa_chain(OpenAI(temperature=0), chain_type="stuff")  # or Groq
-
-    query = message.content
-    docs = vectordb.similarity_search(query)
-    answer = qa_chain.run(input_documents=docs, question=query)
-
-    await cl.Message(answer).send()
+from langchain_community.llms import OpenAI