Upload 3 files

README.md

@@ -1,19 +1,45 @@
 ---
-title: Flykite Hr Bot
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
+title: Flykite Airlines HR Q&A Bot
+emoji: ✈️
+colorFrom: blue
+colorTo: indigo
+sdk: streamlit
+sdk_version: 1.40.0
+app_file: app.py
 pinned: false
-short_description: flykite-hr-bot
+license: mit
 ---
 
-# Welcome to Streamlit!
+# ✈️ Flykite Airlines HR Q&A Bot
 
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+An intelligent HR Policy Q&A Bot powered by RAG (Retrieval-Augmented Generation) and Groq's LLama 3.3 70B model.
 
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+## Features
+
+- 📄 Upload HR Policy PDF documents
+- 💬 Ask questions in natural language
+- 🔍 RAG-based retrieval for accurate answers
+- 📚 View source documents for transparency
+- ⚙️ Configurable parameters (chunk size, k-value, temperature)
+
+## How to Use
+
+1. Get a FREE Groq API key from [console.groq.com](https://console.groq.com/keys)
+2. Enter your API key in the sidebar
+3. Upload the HR Policy PDF
+4. Click "Process Document"
+5. Ask questions!
+
+## Technology Stack
+
+- **LLM**: Groq LLama 3.3 70B (FREE)
+- **Embeddings**: all-MiniLM-L6-v2
+- **Vector Store**: FAISS
+- **Framework**: LangChain + Streamlit
+- **Hosting**: Hugging Face Spaces
+
+## Sample Questions
+
+- What are the effects on benefits if my probation is extended?
+- How do I apply for leave due to a family demise?
+- What should I do if I notice harassment of a colleague?

app.py

@@ -0,0 +1,276 @@
+import streamlit as st
+import os
+import time
+import pdfplumber
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_core.documents import Document
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+from langchain_core.prompts import PromptTemplate
+from langchain_groq import ChatGroq
+
+# Page Configuration
+st.set_page_config(
+    page_title="Flykite Airlines HR Q&A Bot",
+    page_icon="✈️",
+    layout="wide"
+)
+
+# Custom CSS
+st.markdown("""
+<style>
+    .main-header {
+        font-size: 2.5rem;
+        color: #1E88E5;
+        text-align: center;
+        margin-bottom: 1rem;
+    }
+    .sub-header {
+        font-size: 1.2rem;
+        color: #666;
+        text-align: center;
+        margin-bottom: 2rem;
+    }
+    .answer-box {
+        background-color: #E3F2FD;
+        padding: 20px;
+        border-radius: 10px;
+        border-left: 5px solid #1E88E5;
+        margin: 10px 0;
+    }
+    .source-box {
+        background-color: #FFF3E0;
+        padding: 15px;
+        border-radius: 10px;
+        border-left: 5px solid #FF9800;
+        margin: 10px 0;
+        font-size: 0.9rem;
+    }
+    .metric-box {
+        background-color: #E8F5E9;
+        padding: 10px;
+        border-radius: 5px;
+        text-align: center;
+    }
+</style>
+""", unsafe_allow_html=True)
+
+# Header
+st.markdown('<h1 class="main-header">✈️ Flykite Airlines HR Q&A Bot</h1>', unsafe_allow_html=True)
+st.markdown('<p class="sub-header">Ask questions about HR policies and get instant answers powered by RAG</p>', unsafe_allow_html=True)
+
+# Sidebar Configuration
+with st.sidebar:
+    st.header("⚙️ Configuration")
+    
+    # API Key
+    groq_api_key = st.text_input("🔑 Groq API Key", type="password", help="Get free key from console.groq.com")
+    
+    st.divider()
+    
+    # PDF Upload
+    st.header("📄 Upload HR Policy")
+    uploaded_file = st.file_uploader("Upload PDF", type=['pdf'])
+    
+    st.divider()
+    
+    # RAG Parameters
+    st.header("🎛️ RAG Parameters")
+    chunk_size = st.slider("Chunk Size", 500, 1500, 1000, 100)
+    chunk_overlap = st.slider("Chunk Overlap", 50, 300, 200, 50)
+    k_value = st.slider("Top-K Documents", 2, 8, 4)
+    temperature = st.slider("Temperature", 0.0, 1.0, 0.3, 0.1)
+    
+    st.divider()
+    
+    # Process Button
+    process_btn = st.button("🚀 Process Document", type="primary", use_container_width=True)
+
+# Initialize session state
+if 'vector_store' not in st.session_state:
+    st.session_state.vector_store = None
+if 'raw_text' not in st.session_state:
+    st.session_state.raw_text = None
+if 'chat_history' not in st.session_state:
+    st.session_state.chat_history = []
+
+# Functions
+def extract_text_from_pdf(pdf_file):
+    """Extract text from uploaded PDF."""
+    text = ""
+    with pdfplumber.open(pdf_file) as pdf:
+        for page in pdf.pages:
+            page_text = page.extract_text()
+            if page_text:
+                text += page_text + "\n"
+    return text
+
+def create_vector_store(text, chunk_size, chunk_overlap):
+    """Create FAISS vector store from text."""
+    splitter = RecursiveCharacterTextSplitter(
+        chunk_size=chunk_size,
+        chunk_overlap=chunk_overlap,
+        separators=["\n\n", "\n", ". ", " ", ""]
+    )
+    chunks = splitter.split_text(text)
+    documents = [Document(page_content=chunk, metadata={'chunk_id': i}) for i, chunk in enumerate(chunks)]
+    
+    embeddings = HuggingFaceEmbeddings(
+        model_name="all-MiniLM-L6-v2",
+        model_kwargs={'device': 'cpu'}
+    )
+    
+    vector_store = FAISS.from_documents(documents, embeddings)
+    return vector_store, len(chunks)
+
+def get_answer(question, vector_store, api_key, k_value, temperature):
+    """Get answer using RAG."""
+    os.environ["GROQ_API_KEY"] = api_key
+    
+    llm = ChatGroq(
+        model="llama-3.3-70b-versatile",
+        temperature=temperature,
+        max_tokens=2048
+    )
+    
+    retriever = vector_store.as_retriever(search_kwargs={'k': k_value})
+    
+    prompt_template = """You are an expert HR Policy Assistant for Flykite Airlines.
+Use ONLY the following context to answer the question. Be specific and cite policy sections.
+
+CONTEXT:
+{context}
+
+QUESTION: {question}
+
+Provide a helpful, accurate answer with policy references.
+
+ANSWER:"""
+    
+    prompt = PromptTemplate(template=prompt_template, input_variables=['context', 'question'])
+    
+    rag_chain = RetrievalQA.from_chain_type(
+        llm=llm,
+        chain_type='stuff',
+        retriever=retriever,
+        return_source_documents=True,
+        chain_type_kwargs={'prompt': prompt}
+    )
+    
+    start_time = time.time()
+    result = rag_chain.invoke({'query': question})
+    response_time = time.time() - start_time
+    
+    return result['result'], result['source_documents'], response_time
+
+# Process Document
+if process_btn:
+    if not groq_api_key:
+        st.sidebar.error("❌ Please enter Groq API Key")
+    elif not uploaded_file:
+        st.sidebar.error("❌ Please upload a PDF file")
+    else:
+        with st.spinner("Processing document..."):
+            # Extract text
+            st.session_state.raw_text = extract_text_from_pdf(uploaded_file)
+            
+            # Create vector store
+            st.session_state.vector_store, num_chunks = create_vector_store(
+                st.session_state.raw_text, chunk_size, chunk_overlap
+            )
+            
+            st.sidebar.success(f"✅ Document processed! ({num_chunks} chunks created)")
+
+# Main Content
+col1, col2 = st.columns([2, 1])
+
+with col1:
+    st.header("💬 Ask a Question")
+    
+    # Sample Questions
+    st.markdown("**Sample Questions:**")
+    sample_questions = [
+        "What are the effects on benefits if my probation is extended?",
+        "How do I apply for leave due to a family demise?",
+        "What should I do if I notice harassment of a colleague?"
+    ]
+    
+    selected_sample = st.selectbox("Select a sample question:", ["-- Select --"] + sample_questions)
+    
+    # Custom Question
+    question = st.text_area("Or type your own question:", height=100)
+    
+    # Use sample if selected
+    if selected_sample != "-- Select --" and not question:
+        question = selected_sample
+    
+    # Ask Button
+    ask_btn = st.button("🔍 Get Answer", type="primary", use_container_width=True)
+    
+    if ask_btn:
+        if not groq_api_key:
+            st.error("❌ Please enter Groq API Key in sidebar")
+        elif st.session_state.vector_store is None:
+            st.error("❌ Please upload and process a document first")
+        elif not question:
+            st.error("❌ Please enter a question")
+        else:
+            with st.spinner("🤔 Thinking..."):
+                try:
+                    answer, sources, response_time = get_answer(
+                        question, 
+                        st.session_state.vector_store,
+                        groq_api_key,
+                        k_value,
+                        temperature
+                    )
+                    
+                    # Display Answer
+                    st.markdown("### 📝 Answer")
+                    st.markdown(f'<div class="answer-box">{answer}</div>', unsafe_allow_html=True)
+                    
+                    # Metrics
+                    col_a, col_b, col_c = st.columns(3)
+                    col_a.metric("⏱️ Response Time", f"{response_time:.2f}s")
+                    col_b.metric("📚 Sources Used", len(sources))
+                    col_c.metric("🎯 Top-K", k_value)
+                    
+                    # Source Documents
+                    with st.expander("📄 View Source Documents"):
+                        for i, doc in enumerate(sources, 1):
+                            st.markdown(f'<div class="source-box"><strong>Source {i}:</strong><br>{doc.page_content[:500]}...</div>', unsafe_allow_html=True)
+                    
+                    # Add to chat history
+                    st.session_state.chat_history.append({
+                        'question': question,
+                        'answer': answer,
+                        'time': response_time
+                    })
+                    
+                except Exception as e:
+                    st.error(f"❌ Error: {str(e)}")
+
+with col2:
+    st.header("📜 Chat History")
+    
+    if st.session_state.chat_history:
+        for i, chat in enumerate(reversed(st.session_state.chat_history[-5:]), 1):
+            with st.expander(f"Q{len(st.session_state.chat_history) - i + 1}: {chat['question'][:50]}..."):
+                st.write(f"**Answer:** {chat['answer'][:300]}...")
+                st.write(f"**Time:** {chat['time']:.2f}s")
+    else:
+        st.info("No questions asked yet. Start by asking a question!")
+    
+    if st.button("🗑️ Clear History"):
+        st.session_state.chat_history = []
+        st.rerun()
+
+# Footer
+st.divider()
+st.markdown("""
+<div style="text-align: center; color: #666; font-size: 0.9rem;">
+    <p>🛫 Flykite Airlines HR Q&A Bot | Powered by RAG + Groq LLama 3.3 70B</p>
+    <p>Built with Streamlit | Deployed on Hugging Face Spaces</p>
+</div>
+""", unsafe_allow_html=True)

requirements.txt

@@ -1,3 +1,12 @@
-altair
-pandas
-streamlit
+streamlit==1.40.0
+langchain==0.2.16
+langchain-core==0.2.40
+langchain-community==0.2.16
+langchain-text-splitters==0.2.4
+langchain-groq==0.1.9
+groq
+faiss-cpu
+sentence-transformers
+pdfplumber
+tiktoken
+huggingface_hub