Create app.py

app.py

@@ -0,0 +1,191 @@
+import gradio as gr
+import requests
+import pandas as pd
+import time
+from llama_cpp import Llama
+from huggingface_hub import hf_hub_download
+
+# =========================
+# LOAD GGUF MODEL
+# =========================
+print("Downloading GGUF model...")
+
+model_path = hf_hub_download(
+    repo_id="bartowski/Qwen2.5-1.5B-Instruct-GGUF",
+    filename="qwen2.5-1.5b-instruct-q4_k_m.gguf"
+)
+
+print("Loading model...")
+
+llm = Llama(
+    model_path=model_path,
+    n_ctx=1024,
+    n_threads=4,
+    n_batch=512,
+    verbose=False
+)
+
+# =========================
+# ENV VARIABLES (use HF Secrets ideally)
+# =========================
+client_id = "sb-cap1-3c4588e0trial-dev!t617058"
+client_secret = "acbe78be-ead5-4b12-b3b4-32fdb27d0f5f$hFj-hDXxwHkNHC-CAvv-OKSr3KH96nLL4KqwIg7M8D8="
+token_url = "https://3c4588e0trial.authentication.us10.hana.ondemand.com/oauth/token"
+cap_service_url_customers = "https://3c4588e0trial-dev-cap1-srv.cfapps.us10-001.hana.ondemand.com/odata/v4/sales/Customers?$top=2"
+cap_service_url_products = "https://3c4588e0trial-dev-cap1-srv.cfapps.us10-001.hana.ondemand.com/odata/v4/sales/Products?$top=2"
+cap_service_url_saleorders = "https://3c4588e0trial-dev-cap1-srv.cfapps.us10-001.hana.ondemand.com/odata/v4/sales/SalesOrders?$top=2"
+cap_service_url_saleorderitems = "https://3c4588e0trial-dev-cap1-srv.cfapps.us10-001.hana.ondemand.com/odata/v4/sales/SalesOrderItems?$top=2"
+# =========================
+# GLOBAL CACHE
+# =========================
+access_token = None
+cached_data = None
+last_refresh = 0
+
+# =========================
+# TOKEN FUNCTION
+# =========================
+def generate_token():
+    global access_token
+
+    response = requests.post(
+        token_url,
+        data={"grant_type": "client_credentials"},
+        auth=(client_id, client_secret)
+    )
+
+    if response.status_code != 200:
+        return None
+
+    access_token = response.json().get("access_token")
+    return access_token
+
+# =========================
+# FETCH SAP DATA
+# =========================
+def fetch_sap_data():
+    global access_token
+
+    if not access_token:
+        generate_token()
+
+    headers = {
+        "Authorization": f"Bearer {access_token}",
+        "Accept": "application/json"
+    }
+
+    res1 = requests.get(cap_service_url_customers, headers=headers)
+    res2 = requests.get(cap_service_url_products, headers=headers)
+    res3 = requests.get(cap_service_url_saleorders, headers=headers)
+    res4 = requests.get(cap_service_url_saleorderitems, headers=headers)
+
+    # Retry if token expired
+    if res1.status_code in [401, 403]:
+        access_token = None
+        generate_token()
+        headers["Authorization"] = f"Bearer {access_token}"
+
+        res1 = requests.get(cap_service_url_customers, headers=headers)
+        res2 = requests.get(cap_service_url_products, headers=headers)
+        res3 = requests.get(cap_service_url_saleorders, headers=headers)
+        res4 = requests.get(cap_service_url_saleorderitems, headers=headers)
+
+    df_customers = pd.DataFrame(res1.json()["value"])
+    df_products = pd.DataFrame(res2.json()["value"])
+    df_saleorders = pd.DataFrame(res3.json()["value"])
+    df_saleorderitems = pd.DataFrame(res4.json()["value"])
+
+    # Reduce columns (IMPORTANT for speed)
+    df_customers = df_customers[["ID","name","country","industry"]]
+    df_products = df_products[["ID","name","category","price","currency"]]
+    df_saleorders = df_saleorders[["ID","customer_ID","orderDate","status"]]
+    df_saleorderitems = df_saleorderitems[["ID","parent_ID","product_ID","quantity","netAmount"]]
+
+    return df_customers, df_products, df_saleorders, df_saleorderitems
+
+# =========================
+# CACHE FUNCTION
+# =========================
+def get_cached_data():
+    global cached_data, last_refresh
+
+    # Refresh every 5 minutes
+    if time.time() - last_refresh > 3000 or cached_data is None:
+        cached_data = fetch_sap_data()
+        last_refresh = time.time()
+
+    return cached_data
+
+# =========================
+# MAIN LLM FUNCTION
+# =========================
+def generate_response(user_prompt):
+    try:
+        df_customers, df_products, df_saleorders, df_saleorderitems = get_cached_data()
+
+        # Convert to compact text (IMPORTANT)
+        customers_text = df_customers.to_string(index=False)
+        products_text = df_products.to_string(index=False)
+        saleorders_text = df_saleorders.to_string(index=False)
+        saleorderitems_text = df_saleorderitems.to_string(index=False)
+
+        prompt = f"""
+        You are a Corporate SAP Assistant.
+        
+        Customers:
+        {customers_text}
+        
+        Products:
+        {products_text}
+        
+        Orders:
+        {saleorders_text}
+        
+        Order Items:
+        {saleorderitems_text}
+        
+        Rules:
+        - Answer ONLY using given data
+        - If not found say: "I could not find that information in the current SAP database."
+        - Use bullet points
+        
+        User: {user_prompt}
+        Assistant:
+        """
+
+        output = llm(
+            prompt,
+            max_tokens=100,
+            temperature=0.3,
+            top_p=0.7,
+            stop=["User:", "Assistant:"]
+        )
+
+        response = output["choices"][0]["text"].strip()
+        return response
+
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# =========================
+# GRADIO UI
+# =========================
+with gr.Blocks() as demo:
+
+    user_input = gr.Textbox(label="User Question")
+
+    output = gr.Textbox(label="Response")
+
+    btn = gr.Button("Generate")
+
+    btn.click(
+        fn=generate_response,
+        inputs=[user_input],
+        outputs=output,
+        api_name="predict"
+    )
+
+# REQUIRED for API exposure
+demo.queue()
+
+demo.launch()