Create app.py

app.py

@@ -0,0 +1,57 @@
+import os
+import streamlit as st
+from groq import Groq
+from langchain.vectorstores import FAISS
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.chains import RetrievalQA
+from langchain.prompts import PromptTemplate
+
+# Initialize Groq client
+client = Groq(api_key="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")
+
+# Title of the application
+st.title("Public Procurement Rules Assistant")
+
+# Upload PDF
+uploaded_file = st.file_uploader("Upload the PPRA Rules 2004 PDF", type=["pdf"])
+
+if uploaded_file:
+    from PyPDF2 import PdfReader
+
+    # Read and extract text from PDF
+    pdf_reader = PdfReader(uploaded_file)
+    text = ""
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+
+    # Split text into chunks for embedding
+    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+    chunks = text_splitter.split_text(text)
+
+    # Create embeddings and FAISS index
+    embeddings = OpenAIEmbeddings()
+    vectorstore = FAISS.from_texts(chunks, embeddings)
+
+    # Set up retrieval-based QA
+    retriever = vectorstore.as_retriever()
+    qa_chain = RetrievalQA.from_chain_type(
+        llm=lambda query: client.chat.completions.create(
+            messages=[{"role": "user", "content": query}],
+            model="llama-3.3-70b-versatile",
+        ).choices[0].message.content,
+        retriever=retriever,
+        return_source_documents=True,
+    )
+
+    # Input for user query
+    user_query = st.text_input("Ask a question about PPRA Rules 2004:")
+    if user_query:
+        response = qa_chain.run(user_query)
+        st.subheader("Answer:")
+        st.write(response)
+
+        # Optional: Display relevant source documents
+        st.subheader("Relevant Sources:")
+        for doc in response["source_documents"]:
+            st.write(doc.page_content)