Update app.py

app.py

@@ -1,59 +1,50 @@
-# app.py — Omantel Insurance Q&A (RAG) with local logo at top-center
+# app.py — Omantel Insurance Q&A (RAG) with system prompt + simple config
 import os
-import logging
 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.embeddings.openai import OpenAIEmbedding
 from llama_index.llms.openai import OpenAI
 
-# ===== CONFIG =====
+# --- System Prompt (polite + answer-from-document constraint) ---
+SYSTEM_PROMPT = """You are Aisha, a polite and professional Insurance assistant.
+Answer ONLY using the information found in the indexed insurance document(s).
+If the answer is not in the document(s), say: "I couldn’t find that in the document."
+Keep responses concise, helpful, and courteous.
+"""
+
+# ===== Minimal CONFIG (only necessary keys) =====
 PINECONE_API_KEY = os.getenv("PINECONE_API_KEY")
 OPENAI_API_KEY   = os.getenv("OPENAI_API_KEY")
+if not PINECONE_API_KEY or not OPENAI_API_KEY:
+    raise RuntimeError("Missing PINECONE_API_KEY or OPENAI_API_KEY (set them in Space → Settings → Variables).")
 
-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-dim
-LLM_MODEL           = os.getenv("LLM_MODEL", "gpt-4o-mini")
-
-DATA_DIR = "data"
-DEFAULT_TOP_K = 4  # internal similarity_top_k
-
-# ---- Local logo (commit this image to your Space repo) ----
-LOGO_PATH = os.path.join(DATA_DIR, "Omantel_Logo_new.png")
-
-if not PINECONE_API_KEY:
-    raise RuntimeError("Missing PINECONE_API_KEY (Space → Settings → Variables).")
-if not OPENAI_API_KEY:
-    raise RuntimeError("Missing OPENAI_API_KEY (Space → Settings → Variables).")
+DATA_DIR = "data"                         # Put insurance docs here (e.g., data/insurance.pdf)
+LOGO_PATH = os.path.join(DATA_DIR, "Omantel_Logo_new.png")  # Mandatory logo
 if not os.path.exists(LOGO_PATH):
     raise RuntimeError("Logo not found: data/Omantel_Logo_new.png (commit it to your Space repo).")
 
-logging.basicConfig(level=logging.INFO)
-log = logging.getLogger("dds-space")
+EMBED_MODEL = "text-embedding-3-small"    # 1536-dim
+LLM_MODEL   = "gpt-4o-mini"
+TOP_K       = 4                            # internal similarity_top_k
 
-# ===== LlamaIndex / Pinecone =====
+# ===== LlamaIndex / Pinecone (simple, fixed serverless: aws/us-east-1) =====
 Settings.embed_model = OpenAIEmbedding(model=EMBED_MODEL, api_key=OPENAI_API_KEY)
-Settings.llm = OpenAI(model=LLM_MODEL, api_key=OPENAI_API_KEY)
+Settings.llm = OpenAI(model=LLM_MODEL, api_key=OPENAI_API_KEY, system_prompt=SYSTEM_PROMPT)
 
 pc = Pinecone(api_key=PINECONE_API_KEY)
-
 def ensure_index(name: str, dim: int = 1536):
     names = [i["name"] for i in pc.list_indexes()]
     if name not in names:
-        log.info(f"Creating Pinecone index '{name}' (dim={dim})...")
         pc.create_index(
-            name=name,
-            dimension=dim,
-            metric="cosine",
-            spec=ServerlessSpec(cloud=PINECONE_CLOUD, region=PINECONE_REGION),
+            name=name, dimension=dim, metric="cosine",
+            spec=ServerlessSpec(cloud="aws", region="us-east-1"),
         )
     return pc.Index(name)
 
-pinecone_index = ensure_index(PINECONE_INDEX_NAME, dim=1536)
+# Fixed index name for simplicity
+pinecone_index = ensure_index("dds-insurance-index", dim=1536)
 vector_store = PineconeVectorStore(pinecone_index=pinecone_index)
 
 def bootstrap_index():
@@ -68,11 +59,10 @@ def bootstrap_index():
 bootstrap_index()
 
 def answer(query: str) -> str:
-    if not query or not query.strip():
+    if 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=DEFAULT_TOP_K)
-    resp = engine.query(query)
+    resp = index.as_query_engine(similarity_top_k=TOP_K).query(query)
     return str(resp)
 
 FAQS = [
@@ -106,8 +96,10 @@ with gr.Blocks(css=CSS, theme=gr.themes.Soft()) as demo:
         with gr.Column():
             gr.Markdown("<div class='header'>")
             gr.Image(value=LOGO_PATH, show_label=False, elem_classes=["logo"])
-            gr.Markdown("<h1 class='title'>Omantel Insurance Q&A — AI Assistant</h1>"
-                        "<p class='subnote'>Ask about coverage, claims, exclusions, and more — powered by LlamaIndex + Pinecone</p>")
+            gr.Markdown(
+                "<h1 class='title'>Omantel Insurance Q&A — RAG Assistant</h1>"
+                "<p class='subnote'>Answers strictly from your insurance document(s)</p>"
+            )
             gr.Markdown("</div>")
 
     with gr.Row():