app.py

import gradio as gr
import pandas as pd
from sentence_transformers import SentenceTransformer, util

# Load files
df = pd.read_excel("IslamWeb_output.xlsx")
df2 = pd.read_excel("JordanFatwas_all.xlsx")

# Validate
for d, name in [(df, "IslamWeb"), (df2, "JordanFatwas")]:
    if not {"question", "link"}.issubset(d.columns):
        raise ValueError(f"❌ Missing required columns in {name}")

# Load model + encode
model = SentenceTransformer("paraphrase-multilingual-MiniLM-L12-v2")
embeddings = model.encode(df["question"].fillna('').tolist(), convert_to_tensor=True)
embeddings2 = model.encode(df2["question"].fillna('').tolist(), convert_to_tensor=True)

# Define function
def search_fatwa(query):
    query_embedding = model.encode(query, convert_to_tensor=True)

    scores = util.pytorch_cos_sim(query_embedding, embeddings)[0]
    top_idx = int(scores.argmax())

    scores2 = util.pytorch_cos_sim(query_embedding, embeddings2)[0]
    top_idx2 = int(scores2.argmax())

    return {
        "question1": df.iloc[top_idx]["question"],
        "link1": df.iloc[top_idx]["link"],
        "question2": df2.iloc[top_idx2]["question"],
        "link2": df2.iloc[top_idx2]["link"],
    }

# Interface
iface = gr.Interface(
    fn=search_fatwa,
    inputs="text",
    outputs="json",
    allow_flagging="never",
    title="Fatwa Search (Dual Source)",
    description="Get the most relevant fatwas from both datasets"
)

iface.launch()