app.py

import pandas as pd
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import gradio as gr

# -------------------------------
# 🔹 Load TinyLlama once (outside the function)
# -------------------------------

model_id = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto"
)

# -------------------------------
# 🔹 Define the main function
# -------------------------------

def generate_insights(file):
    try:
        # 🔸 Load Excel file
        df = pd.read_excel(file.name, engine="openpyxl")

        # 🔸 Summarize data (first 3 rows or stats)
        table_text = df.head(3).to_markdown(index=False)
        summary = df.describe().to_markdown()

        # 🔸 Prepare prompt for TinyLlama
        prompt = f"""<|user|>
You are a professional data analyst. Here is a sample of the dataset:

{table_text}

And here are the summary statistics:

{summary}

Give exactly 3 clear, concise bullet-point insights based on the data. Focus only on notable patterns, trends, or anomalies.
<|assistant|>
"""

        # 🔸 Tokenize and generate
        inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
        outputs = model.generate(
            **inputs,
            max_new_tokens=256,
            temperature=0.7,
            top_p=0.9,
            do_sample=True,
            pad_token_id=tokenizer.eos_token_id
        )

        # 🔸 Decode response
        response = tokenizer.decode(outputs[0], skip_special_tokens=True)

        # Remove prompt from output if needed
        if "<|assistant|>" in response:
            response = response.split("<|assistant|>")[-1].strip()

        return response

    except Exception as e:
        return f"❌ Error processing file: {str(e)}"

# -------------------------------
# 🔹 Gradio UI
# -------------------------------

gr.Interface(
    fn=generate_insights,
    inputs=gr.File(label="Upload Excel File (.xlsx)"),
    outputs=gr.Textbox(label="Generated Insights",lines=15),
    title="Insights Generator",
 description="Upload an Excel file and get data insights."
).launch()