app.py

import gradio as gr
import time
from datetime import datetime
import pandas as pd
from sentence_transformers import SentenceTransformer
from qdrant_client import QdrantClient
from qdrant_client.models import Filter, FieldCondition, MatchValue
import os
from pythainlp.tokenize import word_tokenize
from pyairtable import Table
from pyairtable import Api


qdrant_client = QdrantClient(
    url=os.environ.get("Qdrant_url"),
    api_key=os.environ.get("Qdrant_api"),
)

AIRTABLE_API_KEY = os.environ.get("airtable_api")
BASE_ID = os.environ.get("airtable_baseid")
TABLE_NAME = "Feedback_search"  # หรือเปลี่ยนชื่อให้ชัดเช่น 'Feedback'
api = Api(AIRTABLE_API_KEY)
table = api.table(BASE_ID, TABLE_NAME)

# โมเดลที่โหลดล่วงหน้า
models = {
    "E5 (intfloat/multilingual-e5-small)": SentenceTransformer('intfloat/multilingual-e5-small'),
    "E5 large instruct (multilingual-e5-large-instruct)": SentenceTransformer("intfloat/multilingual-e5-large-instruct"),
    "Kalm (KaLM-embedding-multilingual-mini-v1)": SentenceTransformer('HIT-TMG/KaLM-embedding-multilingual-mini-v1')
}

model_config = {
    "E5 (intfloat/multilingual-e5-small)": {
        "func": lambda query: models["E5 (intfloat/multilingual-e5-small)"].encode("query: " + query),
        "collection": "product_E5",
    },
    "E5 large instruct (multilingual-e5-large-instruct)": {
        "func": lambda query: models["E5 large instruct (multilingual-e5-large-instruct)"].encode(
            "Instruct: Given a product search query, retrieve relevant product listings\nQuery: " + query, convert_to_tensor=False, normalize_embeddings=True),
        "collection": "product_E5_large_instruct",
    },
    "Kalm (KaLM-embedding-multilingual-mini-v1)": {
        "func": lambda query: models["Kalm (KaLM-embedding-multilingual-mini-v1)"].encode(query, normalize_embeddings=True),
        "collection": "product_kalm",
    }
}

# Global memory to hold feedback state
latest_query_result = {"query": "", "result": "", "model": "", "raw_query": "", "time": ""}

# 🌟 Main search function
def search_product(query, model_name):
    start_time = time.time()
    if model_name not in model_config:
        return "<p>❌ ไม่พบโมเดล</p>"

    latest_query_result["raw_query"] = query
    corrected_query = query

    query_embed = model_config[model_name]["func"](corrected_query)
    collection_name = model_config[model_name]["collection"]

    try:
        result = qdrant_client.query_points(
            collection_name=collection_name,
            query=query_embed.tolist(),
            with_payload=True,
            query_filter=Filter(must=[FieldCondition(key="type", match=MatchValue(value="product"))]),
            limit=10
        ).points
    except Exception as e:
        return f"<p>❌ Qdrant error: {str(e)}</p>"

    elapsed = time.time() - start_time
    html_output = f"<p>⏱ <strong>{elapsed:.2f} วินาที</strong></p>"
    if corrected_query != query:
        html_output += f"<p>🔧 แก้คำค้นจาก: <code>{query}</code> → <code>{corrected_query}</code></p>"

    html_output += """
    <div style="display: grid; grid-template-columns: repeat(auto-fill, minmax(220px, 1fr)); gap: 20px;">
    """

    result_summary = ""
    for res in result:
        name = res.payload.get("name", "ไม่ทราบชื่อสินค้า")
        score = f"{res.score:.4f}"
        img_url = res.payload.get("imageUrl", "")
        price = res.payload.get("price", "ไม่ระบุ")
        brand = res.payload.get("brand", "")

        html_output += f"""
        <div style="border: 1px solid #ddd; border-radius: 8px; padding: 10px; text-align: center; box-shadow: 1px 1px 5px rgba(0,0,0,0.1); background: #fff;">
            <img src="{img_url}" style="width: 100%; max-height: 150px; object-fit: contain; border-radius: 4px;">
            <div style="margin-top: 10px;">
                <div style="font-weight: bold; font-size: 14px;">{name}</div>
                <div style="color: gray; font-size: 12px;">{brand}</div>
                <div style="color: green; margin: 4px 0;">฿{price}</div>
                <div style="font-size: 12px; color: #555;">score: {score}</div>
            </div>
        </div>
        """
        result_summary += f"{name} (score: {score}) | "

    html_output += "</div>"

    latest_query_result["query"] = corrected_query
    latest_query_result["result"] = result_summary.strip()
    latest_query_result["model"] = model_name
    latest_query_result["time"] = elapsed

    return html_output


# 📝 Logging feedback
def log_feedback(feedback):
    try:
        now = datetime.now().strftime("%Y-%m-%d")
        table.create({
            "timestamp": now,
            "raw_query": latest_query_result["raw_query"],
            "model": latest_query_result["model"],
            "query": latest_query_result["query"],
            "result": latest_query_result["result"],
            "time(second)": latest_query_result["time"],
            "feedback": feedback
        })
        return "✅ Feedback saved to Airtable!"
    except Exception as e:
        return f"❌ Failed to save feedback: {str(e)}"


# 🎨 Gradio UI
with gr.Blocks() as demo:
    gr.Markdown("## 🔎 Product Semantic Search (Vector Search + Qdrant)")

    with gr.Row():
        model_selector = gr.Dropdown(
            choices=list(models.keys()),
            label="เลือกโมเดล",
            value="E5 (intfloat/multilingual-e5-small)"
        )
        query_input = gr.Textbox(label="พิมพ์คำค้นหา")

    result_output = gr.HTML(label="📋 ผลลัพธ์")  # HTML แสดงผลลัพธ์พร้อมรูป

    with gr.Row():
        match_btn = gr.Button("✅ ตรง")
        not_match_btn = gr.Button("❌ ไม่ตรง")

    feedback_status = gr.Textbox(label="📬 สถานะ Feedback")

    query_input.submit(search_product, inputs=[query_input, model_selector], outputs=result_output)
    match_btn.click(lambda: log_feedback("match"), outputs=feedback_status)
    not_match_btn.click(lambda: log_feedback("not_match"), outputs=feedback_status)

# Run app
demo.launch(share=True)