Spaces:
Runtime error
Runtime error
File size: 7,782 Bytes
dea85c5 4002809 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 | from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import WebDriverException, TimeoutException
import threading
from PIL import Image
from io import BytesIO
import re
import time
import os
class LLM:
def __init__(self, demo) -> None:
self.demo = demo
self.value = None
self.input_tag = (By.XPATH, "//textarea[@data-testid='textbox']")
def call_function(self):
pass
def get_response_by_label(self):
response_element = WebDriverWait(self.driver, 30).until(
EC.visibility_of_all_elements_located(self.reponse_tag)
)
while True:
current_len = len(response_element[-1].get_attribute("aria-label").replace("bot's message: ", ''))
time.sleep(1)
previous_len = len(response_element[-1].get_attribute("aria-label").replace("bot's message: ", ''))
print(current_len, previous_len)
if current_len == previous_len and current_len > 1:
break
else:
print('Not yet...')
return response_element[-1].get_attribute("aria-label").replace("bot's message: ", '')
def generate(self, text):
self.options = webdriver.ChromeOptions()
self.options.add_argument("--disable-gpu")
self.options.add_argument('--no-sandbox')
self.options.add_argument('--disable-dev-shm-usage')
if not self.demo: self.options.add_argument('--headless')
self.driver = webdriver.Chrome(options=self.options)
try:
self.driver.get(self.url)
input_element = WebDriverWait(self.driver, 60).until(
EC.element_to_be_clickable(self.input_tag)
)
input_element.clear()
input_element.send_keys(text)
self.call_function()
except WebDriverException as e:
if self.demo: print(e)
finally:
print('Driver exited...')
if self.driver:
self.driver.quit()
return self.value
class MultimodalLLM(LLM):
def __init__(self, demo) -> None:
super().__init__(demo)
self.upload_tag = (By.XPATH, "//input[@type='file']")
self.image_tag = (By.XPATH, "//div[contains(@class, 'image-frame')]")
def call_function(self):
pass
def generate(self, image_path, text):
self.options = webdriver.ChromeOptions()
self.options.add_argument("--disable-gpu")
self.options.add_argument('--no-sandbox')
self.options.add_argument('--disable-dev-shm-usage')
if not self.demo: self.options.add_argument('--headless')
self.driver = webdriver.Chrome(options=self.options)
try:
self.driver.get(self.url)
upload_element = WebDriverWait(self.driver, 60).until(
EC.presence_of_element_located(self.upload_tag)
)
print(f"connect to {self.url}")
image_path = os.path.abspath(image_path)
upload_element.send_keys(image_path)
WebDriverWait(self.driver, 10).until(
EC.visibility_of_element_located(self.image_tag)
)
input_element = WebDriverWait(self.driver, 10).until(
EC.element_to_be_clickable(self.input_tag)
)
input_element.clear()
input_element.send_keys(text)
print(f"send question: {text}")
self.call_function()
except WebDriverException as e:
if self.demo: print(e)
finally:
print('Driver exited...')
if self.driver:
self.driver.quit()
return self.value
class GraphAnalyzer(MultimodalLLM):
def __init__(self, demo=True, url="https://mplug-tinychart-3b.hf.space") -> None:
super().__init__(demo)
self.url = url
self.submit_tag = (By.XPATH, "//button[text()='Send']")
self.reponse_tag = (By.XPATH, "//*[@id='chatbot']/div[2]/div[2]/div/div[2]/div/button")
self.alert_tag = (By.XPATH, "/html/body/gradio-app/div/div/div[2]/div/div/div[2]/div[2]")
def call_function(self):
submit_element = self.driver.find_element(*self.submit_tag)
submit_element.click()
try:
alert_element = WebDriverWait(self.driver, 5).until(
EC.visibility_of_all_elements_located(self.alert_tag)
)
alert = alert_element[0].text
print('Alert:', alert)
self.value = {'status': 'alert', 'text': alert}
#retry_time = re.search(r"\d{1,2}:\d{2}:\d{2}", alert)
return
except TimeoutException: pass
response = self.get_response_by_label()
print('Reponse:', response)
self.value = {'status': 'success', 'text': response}
class ImageDescriptor(MultimodalLLM):
def __init__(self, demo=True, url="https://vikhyatk-moondream2.hf.space") -> None:
super().__init__(demo)
self.url = url
self.submit_tag = (By.XPATH, "//button[text()='Submit']")
self.reponse_tag = (By.XPATH, "//*[@id='component-9']/div[2]/div/span/p")
self.alert_tag = (By.XPATH, "/html/body/gradio-app/div/div/div[2]/div/div/div[2]/div[2]")
def call_function(self):
submit_element = self.driver.find_element(*self.submit_tag)
submit_element.click()
"""
try:
alert_element = WebDriverWait(self.driver, 5).until(
EC.visibility_of_all_elements_located(self.alert_tag)
)
alert = alert_element[0].text
print('Alert:', alert)
self.value = {'status': 'alert', 'text': alert}
#retry_time = re.search(r"\d{1,2}:\d{2}:\d{2}", alert)
return
except TimeoutException: pass
"""
response_element = WebDriverWait(self.driver, 30).until(
EC.visibility_of_all_elements_located(self.reponse_tag)
)
while True:
current_len = len(response_element[0].text) - 1
time.sleep(1)
previous_len = len(response_element[0].text) - 1
print(current_len, previous_len)
if current_len == previous_len and current_len > 1:
break
else:
print('Not yet...')
response = response_element[0].text
print('Reponse:', response)
self.value = {'status': 'success', 'text': response}
class DataSummarizer(LLM):
def __init__(self, demo=True, url="https://yousef4-mistral-7b-v0-3-chat.hf.space") -> None:
super().__init__(demo)
self.url = url
self.submit_tag = (By.XPATH, "//button[text()='Submit']")
self.reponse_tag = (By.XPATH, "//*[@data-testid='bot']")
def call_function(self):
submit_element = self.driver.find_element(*self.submit_tag)
submit_element.click()
response = self.get_response_by_label()
print('Reponse:', response)
self.value = {'status': 'success', 'text': response}
class MultiWorkers:
def __init__(self, demo=True) -> None:
self.x = GraphAnalyzer(demo)
self.y = ImageDescriptor(demo)
self.z = DataSummarizer(demo)
if __name__ == '__main__':
x = GraphAnalyzer()
x.generate('./temp/graph_1.png', 'Give me insight about the graph')
#y = ImageDescriptor()
#y.generate("C:/Users/ACER/Downloads/ComfyUI_07194_.png", "Describe the image")
#z = DataSummarizer(demo=True)
#zz = z.generate("John Lennon")
#print('>>', zz)
pass |