Update app.py

app.py

@@ -1,51 +1,57 @@
-import streamlit as st
-from langchain_community.document_loaders import PyPDFLoader
-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
-import tempfile
-import os
-
-# Hugging Face API token (free – just create an account on huggingface.co)
-HF_TOKEN = os.getenv("HuggingfacehubAPIToken")
-
-st.set_page_config(page_title="DocuQuery (Free)", page_icon="📄", layout="wide")
-st.title("📄 DocuQuery - Free RAG App with Hugging Face Models")
-
-# Upload PDF
-uploaded_file = st.file_uploader("Upload your PDF file", type="pdf")
-
-if uploaded_file:
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
-        tmp_file.write(uploaded_file.read())
-        file_path = tmp_file.name
-
-    # Load PDF and split text
-    loader = PyPDFLoader(file_path)
-    documents = loader.load()
-
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
-    docs = text_splitter.split_documents(documents)
-
-    # Create embeddings with free Hugging Face model
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    vectorstore = FAISS.from_documents(docs, embeddings)
-
-    retriever = vectorstore.as_retriever()
-
-    # Use a free Hugging Face LLM (lightweight for Q&A)
-    llm = HuggingFaceHub(
-        repo_id="google/flan-t5-base", 
-        huggingfacehub_api_token=HF_TOKEN,
-        model_kwargs={"temperature":0, "max_length":512}
-    )
-
-    qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever)
-
-    query = st.text_input("🔍 Ask a question about your document:")
-
-    if query:
-        answer = qa.run(query)
-        st.markdown(f"**Answer:** {answer}")
+import streamlit as st
+import os
+import tempfile
+from langchain_community.document_loaders import PyPDFLoader
+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
+
+# Fix Streamlit config in Docker
+os.environ["STREAMLIT_HOME"] = "/tmp/.streamlit"
+
+HF_TOKEN = os.environ.get("HuggingfacehubAPIToken")
+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")
+
+# Upload PDF
+uploaded_file = st.file_uploader("Upload your PDF", type="pdf")
+
+if uploaded_file:
+    st.info("Processing document...")
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
+        tmp_file.write(uploaded_file.read())
+        file_path = tmp_file.name
+
+    # Load and split PDF
+    loader = PyPDFLoader(file_path)
+    documents = loader.load()
+    st.write(f"Loaded {len(documents)} document(s)")
+
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    docs = text_splitter.split_documents(documents)
+    st.write(f"Split into {len(docs)} chunks")
+
+    # Embeddings and 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-base",
+                         huggingfacehub_api_token=HF_TOKEN,
+                         model_kwargs={"temperature": 0, "max_length": 512})
+
+    qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever)
+    st.success("Document processed! You can now ask questions.")
+
+    # Question input
+    query = st.text_input("Ask a question about your document:")
+    if query:
+        with st.spinner("Generating answer..."):
+            answer = qa.run(query)
+        st.markdown(f"**Answer:** {answer}")