Skip to content

fix HunyuanOCR crash in vLLM #39

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
souvikchand wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix HunyuanOCR crash in vLLM #39

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions Hunyuan-OCR-master/Hunyuan-OCR-vllm/run_hy_ocr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
from openai import OpenAI
from tqdm import tqdm
from typing import Dict, List
import mimetypes

def encode_image(image_path: str) -> str:
"""
Expand All @@ -28,16 +29,19 @@ def create_chat_messages(image_path: str, prompt: str) -> List[Dict]:
Returns:
List of message dictionaries
"""
# Detect MIME type (jpg/png/webp/etc)
mime, _ = mimetypes.guess_type(image_path)
if mime is None:
mime = "image/jpeg" # fallback

return [
{"role": "system", "content": ""},
{
"role": "user",
"content": [
{
"type": "image_url",
"image_url": {
"url": f"data:image/jpeg;base64,{encode_image(image_path)}"
}
"image_url": f"data:{mime};base64,{encode_image(image_path)}"
},
{"type": "text", "text": prompt}
]
Expand Down