Create app2.py

app2.py

@@ -0,0 +1,588 @@
+import os
+import time
+import logging
+import sys
+
+import gradio as gr
+from pinecone import Pinecone, ServerlessSpec
+
+from llama_index.core import VectorStoreIndex, SimpleDirectoryReader, StorageContext, Settings
+from llama_index.vector_stores.pinecone import PineconeVectorStore
+from llama_index.readers.file import PDFReader
+from llama_index.llms.openai import OpenAI
+from llama_index.embeddings.openai import OpenAIEmbedding
+
+
+# -----------------------------
+# Logging
+# -----------------------------
+logging.basicConfig(stream=sys.stdout, level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+
+# -----------------------------
+# Environment Variables
+# Add these in Hugging Face Spaces Secrets
+# -----------------------------
+OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
+PINECONE_API_KEY = os.getenv("PINECONE_API_KEY")
+
+PINECONE_INDEX_NAME = os.getenv("PINECONE_INDEX_NAME", "dds-hr-chatbot")
+PINECONE_CLOUD = os.getenv("PINECONE_CLOUD", "aws")
+PINECONE_REGION = os.getenv("PINECONE_REGION", "us-east-1")
+
+REINDEX_ON_STARTUP = os.getenv("REINDEX_ON_STARTUP", "false").lower() == "true"
+
+DATA_DIR = "data"
+
+if not OPENAI_API_KEY:
+    raise ValueError("OPENAI_API_KEY is missing. Please add it in Hugging Face Spaces secrets.")
+
+if not PINECONE_API_KEY:
+    raise ValueError("PINECONE_API_KEY is missing. Please add it in Hugging Face Spaces secrets.")
+
+
+# -----------------------------
+# LlamaIndex Settings
+# -----------------------------
+Settings.llm = OpenAI(
+    model="gpt-4o-mini",
+    temperature=0.2,
+    api_key=OPENAI_API_KEY
+)
+
+Settings.embed_model = OpenAIEmbedding(
+    model="text-embedding-ada-002",
+    api_key=OPENAI_API_KEY
+)
+
+Settings.chunk_size = 600
+Settings.chunk_overlap = 200
+
+
+# -----------------------------
+# System Prompt
+# -----------------------------
+system_prompt = """
+You are Ayesha, the Decoding Data Science (DDS) Enterprise HR Chatbot.
+
+Your role is to answer questions using only the uploaded DDS HR Handbook.
+
+Core rules:
+- Answer only DDS HR policy questions that are supported by the handbook.
+- Do not answer questions outside HR policy scope.
+- Do not answer confidential questions, salary questions, legal questions, or old-policy questions.
+- If the answer is not available in the handbook, politely say that the information is not available and direct the user to connect@decodingdatascience.com.
+- Do not reveal internal reasoning.
+- Keep answers concise, professional, and helpful.
+- Never invent information.
+
+For forbidden, confidential, unsupported, or out-of-scope topics, respond with:
+“I’m sorry, I can only answer questions about the latest DDS HR policies. For confidential or other queries, please email connect@decodingdatascience.com.”
+
+Remember: You are Ayesha, the DDS Enterprise HR Chatbot. You must only answer from the authorized HR handbook content.
+"""
+
+
+# -----------------------------
+# Pinecone Setup
+# -----------------------------
+def get_existing_index_names(pc):
+    """
+    Handles different Pinecone SDK return styles safely.
+    """
+    try:
+        return pc.list_indexes().names()
+    except Exception:
+        indexes = pc.list_indexes()
+        names = []
+
+        for index_info in indexes:
+            if isinstance(index_info, dict):
+                names.append(index_info.get("name"))
+            else:
+                names.append(getattr(index_info, "name", None))
+
+        return [name for name in names if name]
+
+
+def setup_pinecone_index():
+    pc = Pinecone(api_key=PINECONE_API_KEY)
+
+    existing_indexes = get_existing_index_names(pc)
+
+    if PINECONE_INDEX_NAME not in existing_indexes:
+        logger.info(f"Creating Pinecone index: {PINECONE_INDEX_NAME}")
+
+        pc.create_index(
+            name=PINECONE_INDEX_NAME,
+            dimension=1536,
+            metric="cosine",
+            spec=ServerlessSpec(
+                cloud=PINECONE_CLOUD,
+                region=PINECONE_REGION
+            )
+        )
+
+        while True:
+            description = pc.describe_index(PINECONE_INDEX_NAME)
+
+            try:
+                is_ready = description.status["ready"]
+            except Exception:
+                is_ready = getattr(description.status, "ready", False)
+
+            if is_ready:
+                break
+
+            logger.info("Waiting for Pinecone index to be ready...")
+            time.sleep(2)
+
+    else:
+        logger.info(f"Using existing Pinecone index: {PINECONE_INDEX_NAME}")
+
+    return pc.Index(PINECONE_INDEX_NAME)
+
+
+# -----------------------------
+# Load or Create LlamaIndex Query Engine
+# -----------------------------
+def build_query_engine():
+    pinecone_index = setup_pinecone_index()
+
+    vector_store = PineconeVectorStore(
+        pinecone_index=pinecone_index
+    )
+
+    storage_context = StorageContext.from_defaults(
+        vector_store=vector_store
+    )
+
+    index_stats = pinecone_index.describe_index_stats()
+    total_vectors = index_stats.get("total_vector_count", 0)
+
+    if total_vectors == 0 or REINDEX_ON_STARTUP:
+        logger.info("Loading documents and creating vector index...")
+
+        if not os.path.exists(DATA_DIR):
+            raise ValueError(
+                "The 'data' folder is missing. Please create a data folder and upload your PDF file inside it."
+            )
+
+        documents = SimpleDirectoryReader(
+            input_dir=DATA_DIR,
+            required_exts=[".pdf"],
+            file_extractor={".pdf": PDFReader()}
+        ).load_data()
+
+        if not documents:
+            raise ValueError("No PDF documents were loaded from the 'data' folder.")
+
+        index = VectorStoreIndex.from_documents(
+            documents,
+            storage_context=storage_context
+        )
+
+        logger.info("Documents indexed successfully.")
+
+    else:
+        logger.info("Existing Pinecone vectors found. Loading index from vector store.")
+
+        index = VectorStoreIndex.from_vector_store(
+            vector_store=vector_store
+        )
+
+    query_engine = index.as_query_engine(
+        similarity_top_k=5,
+        system_prompt=system_prompt
+    )
+
+    return query_engine
+
+
+query_engine = build_query_engine()
+
+
+# -----------------------------
+# Query Function
+# -----------------------------
+def query_doc(prompt):
+    try:
+        response = query_engine.query(prompt)
+        return str(response)
+
+    except Exception as e:
+        logger.error(f"Error while answering query: {e}")
+        return "Sorry, something went wrong while processing your question. Please try again."
+
+
+# -----------------------------
+# Example Questions
+# -----------------------------
+example_questions = [
+    "What is the leave policy?",
+    "What is the work from home policy?",
+    "What is the probation policy?",
+    "What are the employee code of conduct rules?",
+    "Who should I contact for confidential HR questions?"
+]
+
+
+# -----------------------------
+# Chat Functions
+# -----------------------------
+initial_chat = [
+    {
+        "role": "assistant",
+        "content": "Hello, I am Ayesha, the DDS Enterprise HR Chatbot. Ask me a question about DDS HR policies."
+    }
+]
+
+
+def respond(message, chat_history):
+    if chat_history is None:
+        chat_history = initial_chat.copy()
+
+    if not message or not message.strip():
+        chat_history.append(
+            {
+                "role": "assistant",
+                "content": "Please enter a question about the DDS HR handbook."
+            }
+        )
+        return "", chat_history
+
+    answer = query_doc(message)
+
+    chat_history.append(
+        {
+            "role": "user",
+            "content": message
+        }
+    )
+
+    chat_history.append(
+        {
+            "role": "assistant",
+            "content": answer
+        }
+    )
+
+    return "", chat_history
+
+
+def clear_chat():
+    return initial_chat.copy()
+
+
+def set_example_question(question):
+    return question
+
+
+# -----------------------------
+# Professional Gradio UI
+# -----------------------------
+DDS_LOGO_URL = "https://raw.githubusercontent.com/Decoding-Data-Science/airesidency/main/dds-logo-removebg-preview.png"
+
+custom_css = """
+body {
+    background: linear-gradient(135deg, #f8fafc 0%, #eef2ff 45%, #f8fafc 100%);
+}
+
+.gradio-container {
+    font-family: Inter, system-ui, -apple-system, BlinkMacSystemFont, "Segoe UI", sans-serif;
+}
+
+.main-container {
+    max-width: 1250px;
+    margin: auto;
+}
+
+.header-card {
+    background: rgba(255, 255, 255, 0.95);
+    border-radius: 24px;
+    padding: 26px;
+    box-shadow: 0 16px 40px rgba(15, 23, 42, 0.08);
+    border: 1px solid #e5e7eb;
+    margin-bottom: 20px;
+}
+
+.sidebar-card {
+    background: rgba(255, 255, 255, 0.96);
+    border-radius: 24px;
+    padding: 24px;
+    box-shadow: 0 16px 40px rgba(15, 23, 42, 0.08);
+    border: 1px solid #e5e7eb;
+    height: 100%;
+}
+
+.chat-card {
+    background: rgba(255, 255, 255, 0.96);
+    border-radius: 24px;
+    padding: 22px;
+    box-shadow: 0 16px 40px rgba(15, 23, 42, 0.08);
+    border: 1px solid #e5e7eb;
+}
+
+.logo-img {
+    max-width: 175px;
+    margin-bottom: 8px;
+}
+
+.title-text {
+    font-size: 32px;
+    font-weight: 850;
+    color: #111827;
+    margin-bottom: 8px;
+    letter-spacing: -0.03em;
+}
+
+.subtitle-text {
+    font-size: 16px;
+    color: #4b5563;
+    line-height: 1.65;
+    max-width: 850px;
+}
+
+.badge {
+    display: inline-block;
+    background: #eef2ff;
+    color: #3730a3;
+    padding: 7px 13px;
+    border-radius: 999px;
+    font-size: 13px;
+    font-weight: 650;
+    margin-right: 7px;
+    margin-bottom: 8px;
+}
+
+.status-box {
+    background: #f8fafc;
+    border: 1px solid #e5e7eb;
+    padding: 14px;
+    border-radius: 16px;
+    font-size: 14px;
+    color: #374151;
+    line-height: 1.6;
+}
+
+.small-note {
+    font-size: 13px;
+    color: #6b7280;
+    line-height: 1.55;
+}
+
+.footer-note {
+    font-size: 13px;
+    color: #6b7280;
+    text-align: center;
+    margin-top: 18px;
+}
+
+#chatbot {
+    min-height: 540px;
+    border-radius: 18px;
+    border: 1px solid #e5e7eb;
+}
+
+#question_box textarea {
+    border-radius: 16px !important;
+}
+
+.example-button {
+    margin-bottom: 8px !important;
+    border-radius: 14px !important;
+    white-space: normal !important;
+    text-align: left !important;
+}
+
+.primary-action {
+    border-radius: 14px !important;
+}
+
+.clear-action {
+    border-radius: 14px !important;
+}
+"""
+
+
+with gr.Blocks(
+    title="DDS Enterprise HR Chatbot",
+    css=custom_css,
+    theme=gr.themes.Soft(
+        primary_hue="indigo",
+        neutral_hue="slate"
+    )
+) as demo:
+
+    with gr.Column(elem_classes=["main-container"]):
+
+        # -----------------------------
+        # Header
+        # -----------------------------
+        with gr.Row(elem_classes=["header-card"]):
+            with gr.Column(scale=1, min_width=190):
+                gr.HTML(
+                    f"""
+                    <img src="{DDS_LOGO_URL}" class="logo-img" alt="DDS Logo">
+                    """
+                )
+
+            with gr.Column(scale=5):
+                gr.HTML(
+                    """
+                    <div class="title-text">DDS Enterprise HR Chatbot</div>
+                    <div class="subtitle-text">
+                        A professional HR policy assistant built for Decoding Data Science.
+                        Ask questions from the uploaded DDS HR Handbook and get clear, concise answers
+                        based on the available document content.
+                    </div>
+                    <br>
+                    <span class="badge">HR Handbook Q&A</span>
+                    <span class="badge">LlamaIndex</span>
+                    <span class="badge">Pinecone</span>
+                    <span class="badge">OpenAI</span>
+                    <span class="badge">Gradio</span>
+                    """
+                )
+
+        # -----------------------------
+        # Two Column Layout
+        # -----------------------------
+        with gr.Row():
+
+            # Left Sidebar
+            with gr.Column(scale=1, min_width=300, elem_classes=["sidebar-card"]):
+
+                gr.Markdown(
+                    """
+                    ### What this assistant can help with
+
+                    This chatbot answers questions only from the uploaded DDS HR Handbook.
+
+                    **You can ask about:**
+
+                    - Leave policies  
+                    - Work from home rules  
+                    - Probation guidelines  
+                    - Code of conduct  
+                    - Employee handbook policies  
+                    - HR contact process  
+                    """
+                )
+
+                gr.HTML(
+                    """
+                    <div class="status-box">
+                        <strong>Scope:</strong> DDS HR policies only<br>
+                        <strong>Data source:</strong> Uploaded HR handbook<br>
+                        <strong>Confidential questions:</strong> Redirected to HR email
+                    </div>
+                    """
+                )
+
+                gr.Markdown("### Quick questions")
+
+                example_buttons = []
+
+                for question in example_questions:
+                    btn = gr.Button(
+                        question,
+                        variant="secondary",
+                        size="sm",
+                        elem_classes=["example-button"]
+                    )
+                    example_buttons.append(btn)
+
+                gr.HTML(
+                    """
+                    <hr>
+                    <div class="small-note">
+                    <strong>Important:</strong><br>
+                    This chatbot does not answer salary, confidential, legal, or non-HR questions.
+                    For confidential queries, contact
+                    <strong>connect@decodingdatascience.com</strong>.
+                    </div>
+                    """
+                )
+
+            # Right Chat Area
+            with gr.Column(scale=3, elem_classes=["chat-card"]):
+
+                chatbot = gr.Chatbot(
+                    label="DDS HR Assistant",
+                    type="messages",
+                    elem_id="chatbot",
+                    value=initial_chat.copy(),
+                    height=540
+                )
+
+                user_input = gr.Textbox(
+                    label="Ask your HR policy question",
+                    placeholder="Example: What is the leave policy?",
+                    lines=2,
+                    elem_id="question_box"
+                )
+
+                with gr.Row():
+                    submit_btn = gr.Button(
+                        "Ask Question",
+                        variant="primary",
+                        elem_classes=["primary-action"]
+                    )
+
+                    clear_btn = gr.Button(
+                        "Clear Chat",
+                        variant="secondary",
+                        elem_classes=["clear-action"]
+                    )
+
+                gr.Markdown(
+                    """
+                    **Tip:** Ask specific questions for better answers.  
+                    Example: “What does the handbook say about probation?” instead of “Tell me everything.”
+                    """
+                )
+
+        # -----------------------------
+        # Button Actions
+        # -----------------------------
+        submit_btn.click(
+            fn=respond,
+            inputs=[user_input, chatbot],
+            outputs=[user_input, chatbot]
+        )
+
+        user_input.submit(
+            fn=respond,
+            inputs=[user_input, chatbot],
+            outputs=[user_input, chatbot]
+        )
+
+        clear_btn.click(
+            fn=clear_chat,
+            inputs=None,
+            outputs=chatbot
+        )
+
+        for btn, question in zip(example_buttons, example_questions):
+            btn.click(
+                fn=set_example_question,
+                inputs=gr.State(question),
+                outputs=user_input
+            )
+
+        # -----------------------------
+        # Footer
+        # -----------------------------
+        gr.HTML(
+            """
+            <div class="footer-note">
+                Built by Decoding Data Science | Enterprise HR Chatbot Demo
+            </div>
+            """
+        )
+
+
+if __name__ == "__main__":
+    demo.launch()