Update app.py

app.py

@@ -1,4 +1,5 @@
-# app.py — Minimal RAG over ./data/insurance.pdf with LlamaIndex + Pinecone
+# app.py — Insurance Q&A (RAG) with Omantel branding, FAQ dropdown, no Top-K control
+# Hugging Face Spaces (Gradio) – uses Pinecone + LlamaIndex + OpenAI
 
 import os
 import logging
@@ -19,10 +20,17 @@ OPENAI_API_KEY   = os.getenv("OPENAI_API_KEY")
 PINECONE_INDEX_NAME = os.getenv("PINECONE_INDEX_NAME", "dds-insurance-index")
 PINECONE_REGION     = os.getenv("PINECONE_REGION", "us-east-1")
 PINECONE_CLOUD      = os.getenv("PINECONE_CLOUD", "aws")
-EMBED_MODEL         = os.getenv("EMBED_MODEL", "text-embedding-3-small")  # 1536 dims
+EMBED_MODEL         = os.getenv("EMBED_MODEL", "text-embedding-3-small")  # 1536-dim
 LLM_MODEL           = os.getenv("LLM_MODEL", "gpt-4o-mini")
 
-DATA_DIR = "data"  # place insurance.pdf inside this folder
+DATA_DIR = "data"                   # Place documents (e.g., insurance.pdf) here
+DEFAULT_TOP_K = 4                   # Internal similarity_top_k (no UI slider)
+
+# Omantel branding (remote image is fine for Spaces UI)
+LOGO_URL = os.getenv(
+    "LOGO_URL",
+    "https://raw.githubusercontent.com/Decoding-Data-Science/Omantel/main/download%20(36).png"
+)
 
 if not PINECONE_API_KEY:
     raise RuntimeError("Missing PINECONE_API_KEY (set it in your Space → Settings → Variables).")
@@ -55,49 +63,113 @@ def ensure_index(name: str, dim: int = 1536):
 pinecone_index = ensure_index(PINECONE_INDEX_NAME, dim=1536)
 vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
 
-# Build once on startup if index is empty (idempotent — safe to re-run)
 def bootstrap_index():
-    # If you want a quick “is empty” check, you can skip or keep this; many set-ups
-    # just upsert blindly (Pinecone dedup keys if you supply your own ids).
-    log.info("Loading documents from ./data ...")
+    """Index all files in ./data into Pinecone (idempotent safe)."""
     if not os.path.isdir(DATA_DIR):
-        raise RuntimeError("No 'data/' directory found. Create it and add insurance.pdf.")
+        raise RuntimeError("No 'data/' directory found. Commit your documents to data/ in the Space repo.")
 
-    # Read everything in ./data (PDF/TXT/DOCX supported by LlamaIndex readers)
+    log.info("Loading documents from ./data ...")
     docs = SimpleDirectoryReader(DATA_DIR).load_data()
+    if not docs:
+        raise RuntimeError("No documents found in data/. Add e.g., data/insurance.pdf")
 
     log.info(f"Docs loaded: {len(docs)}. Upserting into Pinecone…")
     storage_ctx = StorageContext.from_defaults(vector_store=vector_store)
-
-    # Creates a VectorStoreIndex that writes directly to Pinecone
     VectorStoreIndex.from_documents(docs, storage_context=storage_ctx, show_progress=True)
     log.info("Index upsert complete.")
 
-# Initialize the index once at app start
+# Build once at startup
 bootstrap_index()
 
-# Lightweight query function (wraps the existing vector store)
-def answer(query: str, top_k: int = 4) -> str:
-    if not query.strip():
-        return "Please enter a question about the insurance document."
+def answer(query: str) -> str:
+    """Query the existing vector store and return an answer string."""
+    if not query or not query.strip():
+        return "Please enter a question (or select one from the FAQ list)."
     index = VectorStoreIndex.from_vector_store(vector_store)
-    engine = index.as_query_engine(similarity_top_k=top_k)
+    engine = index.as_query_engine(similarity_top_k=DEFAULT_TOP_K)
     resp = engine.query(query)
     return str(resp)
 
+# ---- Frequently Asked Questions (edit to your document) ----
+FAQS = [
+    "",
+    "What benefits are covered under the policy?",
+    "How do I file a claim and what documents are required?",
+    "What are the exclusions and limitations?",
+    "Is pre-authorization needed for hospitalization?",
+    "What is the reimbursement timeline?",
+    "How are outpatient vs inpatient services handled?",
+    "How can I check my network hospitals/clinics?",
+    "What is the co-pay or deductible policy?",
+]
+
+def use_faq(selected_faq: str, free_text: str):
+    """
+    If a FAQ is selected, prefer it; otherwise use free_text.
+    Returns the chosen prompt (echo in UI) and the model answer.
+    """
+    prompt = (selected_faq or "").strip() or (free_text or "").strip()
+    if not prompt:
+        return "", "Please select a FAQ or type your question."
+    return prompt, answer(prompt)
+
 # ========== UI ==========
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("<h1 style='text-align:center;'>Insurance Q&A (RAG)</h1>")
-    gr.Markdown(
-        "This app indexes the file(s) in <code>./data</code> (e.g., <b>insurance.pdf</b>) "
-        "into Pinecone, then answers questions using LlamaIndex + OpenAI."
-    )
-    q = gr.Textbox(label="Ask a question", placeholder="e.g., What is covered under outpatient benefits?")
-    topk = gr.Slider(1, 10, value=4, step=1, label="Top-K matches")
-    btn = gr.Button("Ask")
-    out = gr.Markdown()
-
-    btn.click(answer, inputs=[q, topk], outputs=[out])
+CSS = """
+.header {
+  display: flex;
+  align-items: center;
+  gap: 12px;
+  justify-content: center;
+  margin-top: 8px;
+}
+.header img {
+  height: 42px;
+}
+.header h1 {
+  margin: 0;
+  font-weight: 700;
+  font-size: 1.4rem;
+}
+.subnote {
+  text-align: center;
+  margin-top: -6px;
+  opacity: 0.8;
+}
+"""
+
+with gr.Blocks(css=CSS, theme=gr.themes.Soft()) as demo:
+    # Header with logo + centered title
+    with gr.Row():
+        gr.Markdown(
+            f"""
+<div class="header">
+  <img src="{LOGO_URL}" alt="Omantel logo" />
+  <h1>Omantel Insurance Q&A — RAG Assistant</h1>
+</div>
+<p class="subnote">Ask about coverage, claims, exclusions, and more — powered by LlamaIndex + Pinecone</p>
+""",
+            elem_id="header_md"
+        )
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            gr.Markdown("### Ask from Frequently Asked Questions")
+            faq = gr.Dropdown(choices=FAQS, value=FAQS[0], label="Select a common question")
+
+            gr.Markdown("### Or type your question")
+            user_q = gr.Textbox(
+                label="Your question",
+                placeholder="e.g., What is covered under outpatient benefits?",
+                lines=2
+            )
+
+            ask_btn = gr.Button("Ask", variant="primary")
+
+        with gr.Column(scale=1):
+            chosen_prompt = gr.Textbox(label="Query sent", interactive=False)
+            answer_box = gr.Markdown()
+
+    ask_btn.click(use_faq, inputs=[faq, user_q], outputs=[chosen_prompt, answer_box])
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()