dhuynh95

from llama_index.core import Document, VectorStoreIndex
from llama_index.core import Settings
import trafilatura

class PageSummarizer:
    def __init__(self, llm, embed_model):
        self.llm = llm
        self.embed_model = embed_model
        
    def summarize(self, html: str) -> str:

dhuynh95

def compute_box(element):
    location = element.location
    size = element.size

    # Coordinates
    x_coordinate = location['x']
    y_coordinate = location['y']

    # Size
    width = size['width']

dhuynh95

from playwright.async_api import async_playwright
# Example on how to call these async functions using asyncio
import asyncio

async def load():
    # Example where we connect to a local existing Chrome session in debug mode
    playwright = await async_playwright().start()
    browser = await playwright.chromium.connect_over_cdp("http://localhost:9222")
    default_context = browser.contexts[0]

dhuynh95

# Inspired from https://github.com/microsoft/onnxruntime/blob/main/onnxruntime/python/tools/transformers/notebooks/Inference_GPT2_with_OnnxRuntime_on_CPU.ipynb
def get_example_inputs(example, tokenizer):
    
    tokenizer.padding_side = "left"
    tokenizer.pad_token = tokenizer.eos_token
    max_length = 64
    num_attention_heads, hidden_size, num_layer = 12, 768, 12
    
    encodings_dict = tokenizer.batch_encode_plus(example, padding='max_length', max_length=max_length)

dhuynh95

dhuynh95

dhuynh95

@patch_to(CKKSEncoder)
def pi(self, z: np.array) -> np.array:
    """Projects a vector of H into C^{N/2}."""
    
    N = self.M // 4
    return z[:N]

@patch_to(CKKSEncoder)
def pi_inverse(self, z: np.array) -> np.array:
    """Expands a vector of C^{N/2} by expanding it with its

dhuynh95

@patch_to(CKKSEncoder)
def compute_basis_coordinates(self, z):
    """Computes the coordinates of a vector with respect to the orthogonal lattice basis."""
    output = np.array([np.real(np.vdot(z, b) / np.vdot(b,b)) for b in self.sigma_R_basis])
    return output

def round_coordinates(coordinates):
    """Gives the integral rest."""
    coordinates = coordinates - np.floor(coordinates)
    return coordinates

dhuynh95

p1 = encoder.sigma_inverse(m1)
p2 = encoder.sigma_inverse(m2)

dhuynh95

b_reconstructed = encoder.sigma(p)
b_reconstructed