Upload app.py

app.py

@@ -0,0 +1,84 @@
+import streamlit as st
+from PyPDF2 import PdfReader
+from langchain.vectorstores.cassandra import Cassandra
+from langchain.indexes.vectorstore import VectorStoreIndexWrapper
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.llms import HuggingFaceHub
+from langchain.text_splitter import CharacterTextSplitter
+import cassio
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+
+ASTRA_DB_APPLICATION_TOKEN = os.getenv("ASTRA_DB_APPLICATION_TOKEN")
+ASTRA_DB_ID = os.getenv("ASTRA_DB_ID")
+HUGGINGFACEHUB_API_TOKEN = os.getenv("HUGGINGFACEHUB_API_TOKEN")
+
+# === Streamlit UI Setup ===
+st.set_page_config(page_title="Query PDF with Free Hugging Face Models", layout="wide")
+st.title("📄💬 Query PDF using LangChain + AstraDB (Free Hugging Face Models)")
+
+# === File Upload ===
+uploaded_file = st.file_uploader("Upload your PDF", type=["pdf"])
+
+if uploaded_file:
+    st.success("✅ PDF uploaded successfully!")
+    process_button = st.button("🔄 Process PDF")
+
+    if process_button:
+        # Initialize AstraDB
+        cassio.init(token=ASTRA_DB_APPLICATION_TOKEN, database_id=ASTRA_DB_ID)
+
+        # Read PDF contents
+        pdf_reader = PdfReader(uploaded_file)
+        raw_text = ""
+        for page in pdf_reader.pages:
+            content = page.extract_text()
+            if content:
+                raw_text += content
+
+        # Split text into chunks
+        text_splitter = CharacterTextSplitter(
+            separator="\n", chunk_size=800, chunk_overlap=200, length_function=len
+        )
+        texts = text_splitter.split_text(raw_text)
+
+        # === Embeddings ===
+        embedding = HuggingFaceEmbeddings(
+            model_name="sentence-transformers/all-MiniLM-L6-v2"
+        )
+
+        # === Hugging Face LLM ===
+        llm = HuggingFaceHub(
+            repo_id="mistralai/Mistral-7B-Instruct-v0.1",
+            huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
+            model_kwargs={"temperature": 0.5, "max_new_tokens": 512}
+        )
+
+        # === Create vector store and index ===
+        vector_store = Cassandra(
+            embedding=embedding,
+            table_name=TABLE_NAME,
+            session=None,
+            keyspace=None,
+        )
+        vector_store.add_texts(texts[:50])
+        st.success(f"📚 {len(texts[:50])} chunks embedded and stored in AstraDB.")
+
+        astra_vector_index = VectorStoreIndexWrapper(vectorstore=vector_store)
+
+        # === Ask Questions ===
+        st.header("🤖 Ask a question about your PDF")
+        user_question = st.text_input("💬 Type your question here")
+
+        if user_question:
+            with st.spinner("Thinking..."):
+                answer = astra_vector_index.query(user_question, llm=llm).strip()
+                st.markdown(f"### 🧠 Answer:\n{answer}")
+
+                st.markdown("### 🔍 Top Relevant Chunks")
+                docs = vector_store.similarity_search_with_score(user_question, k=4)
+                for i, (doc, score) in enumerate(docs, 1):
+                    st.markdown(f"**Chunk {i}** — Relevance Score: `{score:.4f}`")
+                    st.code(doc.page_content[:500], language="markdown")