Update app.py

app.py

@@ -6,17 +6,18 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import FAISS
 from langchain.chains import RetrievalQA
 from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.llms import HuggingFaceHub
+from langchain_huggingface import HuggingFaceEndpoint
 
 # Fix Streamlit config in Docker
 os.environ["STREAMLIT_HOME"] = "/tmp/.streamlit"
 
+# Get your Hugging Face API token from Secrets
 HF_TOKEN = os.environ.get("HUGGINGFACEHUB_API_TOKEN")
 if HF_TOKEN is None:
     st.error("⚠️ Hugging Face API token not set. Add it in Settings → Secrets.")
     st.stop()
 
-st.title("📄 DocuQuery - Free RAG App")
+st.title("📄 DocuQuery - Free RAG App with HF Models")
 
 # Upload PDF
 uploaded_file = st.file_uploader("Upload your PDF", type="pdf")
@@ -36,20 +37,19 @@ if uploaded_file:
     docs = text_splitter.split_documents(documents)
     st.write(f"Split into {len(docs)} chunks")
 
-    # Embeddings and vectorstore
+    # Create embeddings + vectorstore
     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
     vectorstore = FAISS.from_documents(docs, embeddings)
     retriever = vectorstore.as_retriever()
 
-    # LLM
-    llm = HuggingFaceHub(
-    repo_id="google/flan-t5-small",  # smaller than base
-    huggingfacehub_api_token=HF_TOKEN,
-    task="text2text-generation",
-    model_kwargs={"temperature":0, "max_length":256}
-)
-
+    # Use HuggingFaceEndpoint (replaces deprecated HuggingFaceHub)
+    llm = HuggingFaceEndpoint(
+        endpoint_url="https://api-inference.huggingface.co/models/google/flan-t5-small",
+        huggingfacehub_api_token=HF_TOKEN,
+        task="text2text-generation"
+    )
 
+    # Create QA chain
     qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever)
     st.success("Document processed! You can now ask questions.")