This video shows step by step demo with code as how to analyze comics in any language and talk to them using LlamaIndex and ChatGPT.
Code Used:
%pip install llama_index ftfy regex tqdm
%pip install git+https://github.com/openai/CLIP.git
%pip install torch torchvision
%pip install matplotlib scikit-image
%pip install -U qdrant_client
import os
openai_api_key = os.environ['OPENAI_API_KEY']
from PIL import Image
import matplotlib.pyplot as plt
import os
image_paths = []
for img_path in os.listdir("./urdu"):
image_paths.append(str(os.path.join("./urdu", img_path)))
def plot_images(image_paths):
images_shown = 0
plt.figure(figsize=(25, 12))
for img_path in image_paths:
if os.path.isfile(img_path):
image = Image.open(img_path)
plt.subplot(2, 2, images_shown + 1)
plt.imshow(image)
plt.xticks([])
plt.yticks([])
images_shown += 1
if images_shown >= 9:
break
plot_images(image_paths)
from llama_index.multi_modal_llms.openai import OpenAIMultiModal
from llama_index import SimpleDirectoryReader
image_documents = SimpleDirectoryReader("./urdu").load_data()
openai_mm_llm = OpenAIMultiModal(
model="gpt-4-vision-preview", api_key=openai_api_key, max_new_tokens=1500
)
response_eng = openai_mm_llm.complete(
prompt="Describe the comic strip panels as an alternative text",
image_documents=image_documents,
)
print(response_eng)