Create app.py

app.py

@@ -0,0 +1,140 @@
+import os
+import streamlit as st
+from sentence_transformers import SentenceTransformer, util
+from groq import Groq
+from PyPDF2 import PdfReader
+from docx import Document
+from pptx import Presentation
+
+# CSS styling for a professional look with black background
+st.markdown("""
+    <style>
+        body {
+            background-color: #121212;
+            color: #ffffff;
+            font-family: Arial, sans-serif;
+        }
+        .title {
+            font-size: 36px;
+            font-weight: bold;
+            color: #e67e22;
+            text-align: center;
+            margin-bottom: 20px;
+        }
+        .subheader {
+            font-size: 24px;
+            color: #f39c12;
+            margin-top: 10px;
+            text-align: center;
+        }
+        .input-area {
+            color: #ecf0f1;
+            font-size: 16px;
+        }
+        .about-app {
+            margin-top: 20px;
+            padding: 15px;
+            background-color: #1e1e1e;
+            border-radius: 8px;
+            color: #bdc3c7;
+        }
+        .footer {
+            background-color: #1c1c1c;
+            color: #bdc3c7;
+            font-size: 14px;
+            text-align: center;
+            padding: 10px;
+            position: fixed;
+            bottom: 0;
+            left: 0;
+            width: 100%;
+            z-index: 1000;
+        }
+        .stTextInput > div > div > input {
+            background-color: #2c3e50;
+            color: #ecf0f1;
+            font-size: 16px;
+            border-radius: 5px;
+            padding: 10px;
+        }
+    </style>
+""", unsafe_allow_html=True)
+
+# Initialize retriever and Groq client
+retriever = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
+api_key = os.getenv("GROQ_API_KEY")
+
+client = Groq(api_key=api_key)
+
+# Knowledge base (documents) and embeddings
+documents = [
+    "Retrieval-Augmented Generation (RAG) is an AI framework that combines the strengths of retrieval-based and generative models.",
+    "The main components of a RAG system are the retriever and the generator.",
+    "A key benefit of Retrieval-Augmented Generation is that it can produce more accurate responses compared to standalone generative models.",
+    "The retrieval process in a RAG system often relies on embedding-based models, like Sentence-BERT or DPR.",
+    "Common use cases of RAG include chatbots, customer support systems, and knowledge retrieval for business intelligence."
+]
+document_embeddings = retriever.encode(documents, convert_to_tensor=True)
+
+def retrieve(query, top_k=1):
+    query_embedding = retriever.encode(query, convert_to_tensor=True)
+    hits = util.semantic_search(query_embedding, document_embeddings, top_k=top_k)
+    top_docs = [documents[hit['corpus_id']] for hit in hits[0]]
+    return top_docs[0] if hits[0] else None
+
+def generate_response(query, context):
+    response = client.chat.completions.create(
+        messages=[{
+            "role": "user",
+            "content": f"Context: {context} Question: {query} Answer:"
+        }],
+        model="gemma2-9b-it"
+    )
+    return response.choices[0].message.content
+
+# Streamlit app layout
+st.markdown('<div class="title">DocumentsReader</div>', unsafe_allow_html=True)
+# About the App section
+with st.expander("About App"):
+    st.write("""
+    ### About the App: Document-Based RAG Question Answering
+    This application, developed by **Hamaad Ayub Khan**, combines state-of-the-art **Retrieval-Augmented Generation (RAG)** technology with powerful AI models to answer questions based on the content of uploaded documents.
+    **Key Features:**
+    - Advanced Retrieval System
+    - Generative Answering Capability
+    - Multi-format Document Support
+    - Seamless Knowledge Base Update
+    - Contextually Rich Answers
+    **Developer Information:** Hamaad Ayub Khan created this application with a commitment to making information retrieval simple, accurate, and accessible.
+    **Social Links:**  
+    - [GitHub](https://github.com/hakgs1234)  
+    - [LinkedIn](https://linkedin.com/in/hamaadayubkhan)  
+    """)
+
+# Document upload and knowledge base update
+uploaded_file = st.file_uploader("Upload a document", type=["pdf", "docx", "pptx", "txt"])
+if uploaded_file:
+    if uploaded_file.type == "application/pdf":
+        file_text = PdfReader(uploaded_file).extract_text()
+    elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+        file_text = "\n".join([para.text for para in Document(uploaded_file).paragraphs])
+    elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.presentationml.presentation":
+        file_text = "\n".join([shape.text for slide in Presentation(uploaded_file).slides for shape in slide.shapes if hasattr(shape, "text")])
+    elif uploaded_file.type == "text/plain":
+        file_text = uploaded_file.read().decode("utf-8")
+    
+    documents.append(file_text)
+    document_embeddings = retriever.encode(documents, convert_to_tensor=True)
+    st.success("Document content successfully added to the knowledge base.")
+
+# Question input and output handling
+question = st.text_input("Enter your question:")
+
+# Check if there is a question and display the answer above the input field
+if question:
+    retrieved_context = retrieve(question)
+    answer = generate_response(question, retrieved_context) if retrieved_context else "I'm unable to find relevant information in the knowledge base."
+    
+    # Display the answer above the input field
+    st.markdown("### Answer:")
+    st.write(answer)