init service

app.py

@@ -0,0 +1,117 @@
+import os
+import json
+import logging
+import typing as t
+
+import gradio as gr
+from huggingface_hub import InferenceClient
+
+logging.basicConfig(
+    level=logging.INFO,
+    format="%(asctime)s - %(levelname)s - %(message)s",
+)
+logger = logging.getLogger(__name__)
+
+
+HF_API_TOKEN = os.getenv("HF_API_TOKEN")
+MODEL_REPO_ID= "google/gemma-2-9b-it"
+
+if HF_API_TOKEN is None:
+    logger.error("HF_API_TOKEN environment variable is not set.")
+    raise ValueError("Error: HF_API_TOKEN environment variable is not set.")
+
+
+def build_messages(input_json: str) -> t.Sequence[t.Mapping[str, str]]:
+    data_structure = (
+        "You are given a restaurant menu in Spanish. You MUST return a single valid JSON in this format:\n"
+        "Menu Format:\n"
+        "<menu> ::= '{' \"restaurant_name\": <string>, \"categories\": [ <category>* ] '}'\n"
+        "<category> ::= '{' \"category\": <string>, \"items\": [ <item>* ] '}'\n"
+        "<item> ::= '{' \"name\": <string>, \"price\": <number>, \"description\": <string> }'\n"
+    )
+
+    instructions = (
+        "Requirements:\n"
+        "1. **Translate ALL Spanish text into English**, including:\n"
+        "   - restaurant_name (only if it's in Spanish).\n"
+        "   - All category names.\n"
+        "   - All item names.\n"
+        "   - Any Spanish words in the final descriptions.\n\n"
+        "2. If an item name is a distinct dish with no direct English equivalent, "
+        "   **still attempt** an English literal translation, or provide a parenthetical explanation if needed.\n\n"
+        "3. For every item, add a new field called description in **concise, appetizing English**.\n\n"
+        "4. **Do not** change or remove existing fields. The only added field is description.\n\n"
+        "5. **Do not** change meaning or make up information."
+        "6. Return **only** the JSON object. **No markdown**, no code fences, no extra text.\n"
+        "7. Ensure the output is **valid JSON** with correct brackets, commas, and quotes.\n\n"
+    )
+
+    system_message = data_structure + instructions
+
+    user_message = (
+        "Process the following menu:\n\n"
+        f"{input_json}"
+    )
+
+    return [
+        {"role": "user", "content": system_message + user_message},
+    ]
+
+
+def process_menu(input_text: str) -> str:
+    client = InferenceClient(model=MODEL_REPO_ID, token=HF_API_TOKEN)
+    messages = build_messages(input_text)
+    
+    logger.info("Generating response from the model.")
+    response = client.chat_completion(
+        messages,
+        max_tokens=2048,
+        temperature=0.1,
+        seed=42,
+    )
+    if response is not None and response.choices is not None:
+        content = response.choices[0].message.content
+    
+    logger.info(response)
+    logger.info(content)
+    
+    parsed = json.loads(content)
+    logger.info("Parsed JSON successfully.")
+    return json.dumps(parsed, indent=2, ensure_ascii=False)
+
+        
+def process_data(data: t.Any) -> str:
+    logger.info("Reading input file: %s", data)
+    input_name = os.path.basename(data)
+    preprocessed_name = "preprocessed_" + input_name
+
+    with open(data, "r", encoding="utf-8") as raw_data:
+        menu = raw_data.read()
+    
+    logger.info("Processing the menu data through the model.")
+    preprocessed_data = process_menu(menu)
+    
+    logger.info("Writing preprocessed data to file: %s", preprocessed_name)
+    with open(preprocessed_name, "w", encoding="utf-8") as temp_data:
+        temp_data.write(preprocessed_data)
+        
+    logger.info("Processing complete. Preprocessed file created: %s", preprocessed_name)
+    return preprocessed_name
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Restaurant Menu Processor")
+    gr.Markdown(
+        "Upload a JSON file containing a restaurant menu in Spanish. "
+        "This tool will translate the menu into English and add descriptions."
+    )
+
+    with gr.Row():
+        input_file = gr.File(label="Upload Restaurant Menu JSON (Spanish)")
+    output_file = gr.File(label="Download Augmented Menu JSON (English)")
+    
+    process_button = gr.Button("Process Menu")
+    process_button.click(process_data, inputs=input_file, outputs=output_file)
+
+        
+demo.launch()