Create app.py

app.py

@@ -0,0 +1,87 @@
+import streamlit as st
+from langchain.vectorstores import FAISS
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.document_loaders import PyPDFLoader
+from langchain.llms import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+import groqapi
+
+# Step 1: Initialize Groq API and Llama Model
+def load_llama_model(api_key, model_name):
+    """Load the Llama model using Groq API."""
+    groqapi.set_api_key(api_key)
+    return HuggingFacePipeline.from_pretrained(model_name)
+
+# Step 2: Load and Process PDF
+def process_pdf(pdf_path):
+    """Load and split the PDF into documents."""
+    loader = PyPDFLoader(pdf_path)
+    documents = loader.load_and_split()
+    return documents
+
+# Step 3: Create Vector Database
+def create_vector_db(documents):
+    """Create a FAISS vector database from documents."""
+    embeddings = OpenAIEmbeddings()  # Use OpenAI embeddings for vectorization
+    vector_db = FAISS.from_documents(documents, embeddings)
+    return vector_db
+
+# Step 4: Build RAG Pipeline
+def build_rag_pipeline(vector_db, llama_model):
+    """Build the Retrieval-Augmented Generation (RAG) pipeline."""
+    retriever = vector_db.as_retriever(search_type="similarity", search_kwargs={"k": 5})
+    qa_chain = RetrievalQA.from_chain_type(
+        retriever=retriever,
+        llm=llama_model,
+        return_source_documents=True
+    )
+    return qa_chain
+
+# Streamlit App
+def main():
+    st.title("KP Universities Act 2016 - Query App")
+    st.write("Ask any question about the KP Universities Act 2016.")
+
+    # Step 1: Upload PDF
+    uploaded_pdf = st.file_uploader("Upload the KP Universities Act 2016 PDF", type="pdf")
+    if uploaded_pdf:
+        with open("uploaded_act.pdf", "wb") as f:
+            f.write(uploaded_pdf.read())
+        documents = process_pdf("uploaded_act.pdf")
+        st.success("PDF Loaded and Processed Successfully!")
+
+        # Step 2: Input Groq API Key
+        api_key = st.text_input("Enter your Groq API Key", type="password")
+        model_name = "llama-3.1-8b-instant"
+
+        if api_key and st.button("Load Llama Model"):
+            try:
+                # Load Llama Model
+                llama_model = load_llama_model(api_key, model_name)
+                st.success("Llama Model Loaded Successfully!")
+
+                # Build Vector DB and QA Chain
+                vector_db = create_vector_db(documents)
+                qa_chain = build_rag_pipeline(vector_db, llama_model)
+
+                # Step 3: Ask Questions
+                query = st.text_input("Ask a question:")
+                if query:
+                    with st.spinner("Fetching Answer..."):
+                        response = qa_chain({"query": query})
+                        answer = response["result"]
+                        source_docs = response["source_documents"]
+
+                        # Display Answer and Sources
+                        st.write("### Answer:")
+                        st.write(answer)
+
+                        st.write("### Sources:")
+                        for doc in source_docs:
+                            st.write(f"Source: {doc.metadata.get('source', 'Unknown')}")
+
+            except Exception as e:
+                st.error(f"Error loading model or processing query: {e}")
+
+if __name__ == "__main__":
+    main()