app.py

import gradio as gr
import requests
from transformers import Pix2StructForConditionalGeneration, Pix2StructProcessor
import os 

##Bloom
API_URL = "https://api-inference.huggingface.co/models/bigscience/bloom"
HF_API_TOKEN = os.getenv("HF_API_TOKEN")
headers = {"Authorization": f"Bearer {HF_API_TOKEN}"}

def _add_markup(table):
    parts = [p.strip() for p in table.splitlines(keepends=False)]
    if parts[0].startswith('TITLE'):
        result = f"Title: {parts[0].split(' | ')[1].strip()}\n"
        rows = parts[1:]
    else:
        result = ''
        rows = parts
    prefixes = ['Header: '] + [f'Row {i+1}: ' for i in range(len(rows) - 1)]
    return result + '\n'.join(prefix + row for prefix, row in zip(prefixes, rows))


_TABLE = """Year | Democrats | Republicans | Independents
2004 | 68.1% | 45.0% | 53.0%
2006 | 58.0% | 42.0% | 53.0%
2007 | 59.0% | 38.0% | 45.0%
2009 | 72.0% | 49.0% | 60.0%
2011 | 71.0% | 51.2% | 58.0%
2012 | 70.0% | 48.0% | 53.0%
2013 | 72.0% | 41.0% | 60.0%"""

_INSTRUCTION = 'Read the table below to answer the following questions.'


_TEMPLATE = f"""{_INSTRUCTION}
{_add_markup(_TABLE)}
Q: In which year republicans have the lowest favor rate?
A: Let's find the column of republicans. Then let's extract the favor rates, they [45.0, 42.0, 38.0, 49.0, 51.2, 48.0, 41.0]. The smallest number is 38.0, that's Row 3.  Row 3 is year 2007. The answer is 2007.
Q: What is the sum of Democrats' favor rates of 2004, 2012, and 2013?
A: Let's find the rows of years 2004, 2012, and 2013. We find Row 1, 6, 7. The favor dates of Demoncrats on that 3 rows are 68.1, 70.0, and 72.0. 68.1+70.0+72=210.1. The answer is 210.1.
Q: By how many points do Independents surpass Republicans in the year of 2011?
A: Let's find the row with year = 2011. We find Row 5. We extract Independents and Republicans' numbers. They are 58.0 and 51.2. 58.0-51.2=6.8. The answer is 6.8.
Q: Which group has the overall worst performance?
A: Let's sample a couple of years. In Row 1, year 2004, we find Republicans having the lowest favor rate 45.0 (since 45.0<68.1, 45.0<53.0). In year 2006, Row 2, we find Republicans having the lowest favor rate 42.0 (42.0<58.0, 42.0<53.0). The trend continues to other years. The answer is Republicans.
Q: Which party has the second highest favor rates in 2007?
A: Let's find the row of year 2007, that's Row 3. Let's extract the numbers on Row 3: [59.0, 38.0, 45.0]. 45.0 is the second highest. 45.0 is the number of Independents. The answer is Independents.
{_INSTRUCTION}"""


import torch
from peft import PeftModel
import transformers
import gradio as gr

assert (
    "LlamaTokenizer" in transformers._import_structure["models.llama"]
), "LLaMA is now in HuggingFace's main branch.\nPlease reinstall it: pip uninstall transformers && pip install git+https://github.com/huggingface/transformers.git"
from transformers import LlamaTokenizer, LlamaForCausalLM, GenerationConfig

tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/llama-7b-hf")

BASE_MODEL = "decapoda-research/llama-7b-hf"
LORA_WEIGHTS = "tloen/alpaca-lora-7b"

if torch.cuda.is_available():
    device = "cuda"
else:
    device = "cpu"

try:
    if torch.backends.mps.is_available():
        device = "mps"
except:
    pass

if device == "cuda":
    model = LlamaForCausalLM.from_pretrained(
        BASE_MODEL,
        load_in_8bit=False,
        torch_dtype=torch.float16,
        device_map="auto",
    )
    model = PeftModel.from_pretrained(
        model, LORA_WEIGHTS, torch_dtype=torch.float16, force_download=True
    )
elif device == "mps":
    model = LlamaForCausalLM.from_pretrained(
        BASE_MODEL,
        device_map={"": device},
        torch_dtype=torch.float16,
    )
    model = PeftModel.from_pretrained(
        model,
        LORA_WEIGHTS,
        device_map={"": device},
        torch_dtype=torch.float16,
    )
else:
    model = LlamaForCausalLM.from_pretrained(
        BASE_MODEL, device_map={"": device}, low_cpu_mem_usage=True
    )
    model = PeftModel.from_pretrained(
        model,
        LORA_WEIGHTS,
        device_map={"": device},
    )


if device != "cpu":
    model.half()
model.eval()
if torch.__version__ >= "2":
    model = torch.compile(model)


def evaluate(
    table,
    question,
    input=None,
    temperature=0.1,
    top_p=0.75,
    top_k=40,
    num_beams=4,
    max_new_tokens=128,
    **kwargs,
):
    prompt = _TEMPLATE + "\n" + table + "\n" + "Q: " + question
    inputs = tokenizer(prompt, return_tensors="pt")
    input_ids = inputs["input_ids"].to(device)
    generation_config = GenerationConfig(
        temperature=temperature,
        top_p=top_p,
        top_k=top_k,
        num_beams=num_beams,
        **kwargs,
    )
    with torch.no_grad():
        generation_output = model.generate(
            input_ids=input_ids,
            generation_config=generation_config,
            return_dict_in_generate=True,
            output_scores=True,
            max_new_tokens=max_new_tokens,
        )
    s = generation_output.sequences[0]
    output = tokenizer.decode(s)
    return output.split("### Response:")[1].strip()




model_deplot = Pix2StructForConditionalGeneration.from_pretrained("google/deplot")
processor_deplot = Pix2StructProcessor.from_pretrained("google/deplot")

def process_document(image, question):
    # image = Image.open(image)
    inputs = processor_deplot(images=image, text="Generate the underlying data table for the figure below:", return_tensors="pt")
    predictions = model_deplot.generate(**inputs)
    table = processor_deplot.decode(predictions[0], skip_special_tokens=True)

    # send prompt+table to LLM
    res = evaluate(table, question)
    print (res)
 
description = "Demo for deplot+llm for QA or summarisation. To use it, simply upload your image and type a question and click 'submit', or click one of the examples to load them. Read more at the links below."
article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2212.10505' target='_blank'>DePlot: One-shot visual language reasoning by plot-to-table translation</a></p>"

demo = gr.Interface(
    fn=process_document,
    inputs=["image", "text"],
    outputs="text",
    title="Demo: deplot+llm test",
    description=description,
    article=article,
    enable_queue=True,
    examples=[["example_1.png", "When is the coffee break?"], ["example_2.jpeg", "What's the population of Stoddard?"]],
    cache_examples=False)

demo.launch()