wehub-resource-sync
fed8b2eed7
Backend release / release (push) Waiting to run
Bandit Security Scan / bandit_scan (push) Waiting to run
Build and push multi-arch DocsGPT Docker image / build (linux/amd64, ubuntu-latest, amd64) (push) Waiting to run
Build and push multi-arch DocsGPT Docker image / build (linux/arm64, ubuntu-24.04-arm, arm64) (push) Waiting to run
Build and push multi-arch DocsGPT Docker image / manifest (push) Blocked by required conditions
Build and push DocsGPT FE Docker image for development / build (linux/amd64, ubuntu-latest, amd64) (push) Waiting to run
Build and push DocsGPT FE Docker image for development / build (linux/arm64, ubuntu-24.04-arm, arm64) (push) Waiting to run
Build and push DocsGPT FE Docker image for development / manifest (push) Blocked by required conditions
Python linting / ruff (push) Waiting to run
Run python tests with pytest / Run tests and count coverage (3.12) (push) Waiting to run
React Widget Build / build (push) Waiting to run
32 lines
929 B
Python
32 lines
929 B
Python
"""Image parser.
|
|
|
|
Contains parser for .png, .jpg, .jpeg files.
|
|
|
|
"""
|
|
from pathlib import Path
|
|
import requests
|
|
from typing import Dict, Union
|
|
|
|
from application.parser.file.base_parser import BaseParser
|
|
from application.core.settings import settings
|
|
|
|
|
|
class ImageParser(BaseParser):
|
|
"""Image parser."""
|
|
|
|
def _init_parser(self) -> Dict:
|
|
"""Init parser."""
|
|
return {}
|
|
|
|
def parse_file(self, file: Path, errors: str = "ignore") -> Union[str, list[str]]:
|
|
if settings.PARSE_IMAGE_REMOTE:
|
|
doc2md_service = "https://llm.arc53.com/doc2md"
|
|
# alternatively you can use local vision capable LLM
|
|
with open(file, "rb") as file_loaded:
|
|
files = {'file': file_loaded}
|
|
response = requests.post(doc2md_service, files=files, timeout=100)
|
|
data = response.json()["markdown"]
|
|
else:
|
|
data = ""
|
|
return data
|