File size: 1,827 Bytes
03d82bf |
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 |
#inget image
import os
import fitz
import chromadb
from chromadb.utils.data_loaders import ImageLoader
from chromadb.utils.embedding_functions import OpenCLIPEmbeddingFunction # type: ignore
path = "mm_vdb2"
client = chromadb.PersistentClient(path=path)
def extract_and_store_images(pdf_path,images_dir=r'extracted_images'):
# Step 1: Extract images from PDF
pdf_document = fitz.open(pdf_path)
os.makedirs(images_dir, exist_ok=True)
for page_num in range(len(pdf_document)):
page = pdf_document.load_page(page_num)
image_list = page.get_images(full=True)
for image_index, img in enumerate(image_list):
xref = img[0]
base_image = pdf_document.extract_image(xref)
image_bytes = base_image["image"]
image_ext = base_image["ext"]
image_filename = f"{images_dir}/page_{page_num+1}_img_{image_index+1}.{image_ext}"
with open(image_filename, "wb") as image_file:
image_file.write(image_bytes)
print(f"Saved: {image_filename}")
print("Image extraction complete.")
# Step 2: Add extracted images to ChromaDB
image_loader = ImageLoader()
CLIP = OpenCLIPEmbeddingFunction()
image_collection = client.get_or_create_collection(name="image", embedding_function=CLIP, data_loader=image_loader)
ids = []
uris = []
for i, filename in enumerate(sorted(os.listdir(images_dir))):
if filename.endswith('.jpeg') or filename.endswith('.png'):
file_path = os.path.join(images_dir, filename)
ids.append(str(i))
uris.append(file_path)
image_collection.add(ids=ids, uris=uris)
print("Images added to the database.")
# return image_vdb
return image_collection
|