OCR 없이 PDF 페이지를 찾는 ColPali·ColQwen 가이드

python -m venv .venv
source .venv/bin/activate
python -m pip install -U 'sentence-transformers[image]>=6.0.0' pymupdf pillow

import fitz

doc = fitz.open()
page = doc.new_page(width=595, height=842)
page.insert_text((72, 90), "Product comparison", fontsize=20)
page.insert_text((72, 150), "Model | Warranty", fontsize=13)
page.insert_text((72, 185), "Atlas | 2 years", fontsize=12)
page.insert_text((72, 220), "Nova | 1 year", fontsize=12)
page2 = doc.new_page(width=595, height=842)
page2.insert_text((72, 90), "Support contacts", fontsize=20)
page2.insert_text((72, 150), "Email: help@example.test", fontsize=12)
doc.save("report.pdf")
print("saved report.pdf")

import fitz, json, time
from PIL import Image
from sentence_transformers import MultiVectorEncoder

pdf_path = "report.pdf"
query = "Which page shows the warranty period in the comparison table?"
model = MultiVectorEncoder("vidore/colqwen2.5-v0.2")
page_images = []
start = time.perf_counter()
with fitz.open(pdf_path) as pdf:
    for page_number in range(1, min(len(pdf), 20) + 1):
        page = pdf[page_number - 1]
        pix = page.get_pixmap(matrix=fitz.Matrix(1.5, 1.5), alpha=False)
        image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
        page_images.append((page_number, image))
query_vectors = model.encode_query([query])
page_vectors = model.encode_document([image for _, image in page_images])
scores = model.similarity(query_vectors, page_vectors)[0]
ranked = scores.argsort(descending=True).tolist()[:5]
print(json.dumps({"query": query, "pages_rendered": len(page_images), "elapsed_s": round(time.perf_counter() - start, 3), "top_pages": [{"page": page_images[i][0], "score": float(scores[i])} for i in ranked]}, indent=2))

python make_report.py
python colpali_search.py