app.py

import gradio as gr
import yake
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

# --- Model (small, CPU-friendly)
MODEL_NAME = "google/flan-t5-small"
tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)

# Keyword extractor
def extract_keywords(text, lang="en", max_kw=8):
    kw_extractor = yake.KeywordExtractor(lan=lang, n=1, top=max_kw)
    kws = kw_extractor.extract_keywords(text)
    return [kw for kw, score in kws]

# Simple SEO scoring
def seo_score(title, description, keywords, tags):
    score = 0
    # Title rules
    if title and title.strip():
        score += 15
        L = len(title)
        if 40 <= L <= 70:
            score += 20
        elif 30 <= L < 40 or 71 <= L <= 90:
            score += 10
    # Keywords in title/description
    kw_in_title = sum(1 for k in keywords if k.lower() in (title or "").lower())
    kw_in_desc = sum(1 for k in keywords if k.lower() in (description or "").lower())
    score += min(20, kw_in_title * 10)
    score += min(15, kw_in_desc * 5)
    # Description length
    dlen = len(description or "")
    if dlen >= 300:
        score += 20
    elif dlen >= 150:
        score += 10
    # Tags
    if tags:
        if 3 <= len(tags) <= 15:
            score += 10
        elif len(tags) > 15:
            score += 5
    return min(100, score)

# Generate titles & description
def gen_suggestions(main_text, keywords, max_titles=3):
    prompt = (
        "You are an assistant that generates catchy YouTube video titles and an SEO-optimized description.\n"
        f"Content: {main_text}\n"
        f"Keywords: {', '.join(keywords)}\n"
        "Produce 3 short titles (<70 chars each) separated by || and one SEO-friendly description after ---"
    )
    inputs = tokenizer(prompt, return_tensors="pt")
    out = model.generate(**inputs, max_new_tokens=300)
    text = tokenizer.decode(out[0], skip_special_tokens=True)
    # Split
    if "||" in text:
        parts = text.split("---")
        titles = parts[0].split("||")
        desc = parts[1].strip() if len(parts) > 1 else ""
    else:
        lines = [l.strip() for l in text.split("\n") if l.strip()]
        titles = lines[:max_titles]
        desc = "\n".join(lines[max_titles:])
    titles = [t.strip() for t in titles if t.strip()]
    return titles[:max_titles], desc

# Main function
def analyze(title, description, lang_choice):_