JoshuaPurtell

from pydantic import BaseModel
from typing import List
import anthropic
import instructor
import asyncio

# Patching the Anthropics client with the instructor for enhanced capabilities
anthropic_client = instructor.patch(
    create=anthropic.AsyncAnthropic().messages.create,
    mode=instructor.Mode.ANTHROPIC_TOOLS

JoshuaPurtell

import asyncio
import copy
import hashlib
import json
import os
import random
from dataclasses import dataclass
from typing import Any, Dict, List, Optional

import numpy as np

JoshuaPurtell

from pdf2image import convert_from_bytes
from transformers import NougatImageProcessor, NougatTokenizerFast
from transformers.models.vision_encoder_decoder import VisionEncoderDecoderModel
MODEL_ID = "facebook/nougat-small"
def first_page_to_title_and_authors(file):
    tokenizer = NougatTokenizerFast.from_pretrained(MODEL_ID)
    processor = NougatImageProcessor.from_pretrained(MODEL_ID)
    model = VisionEncoderDecoderModel.from_pretrained(MODEL_ID)
    file_bytes = file.read()
    first_page = convert_from_bytes(file_bytes)[0]