docling-project/docling

implement retry strategy for remote calls

Open

#2465 opened on Oct 15, 2025

View on GitHub
 (2 comments) (0 reactions) (1 assignee)Python (59,751 stars) (4,140 forks)batch import
enhancementgood first issue

Description

Hi, when for example sending images for description to remote API, it would be beneficial to add a retry strategy in the underlying requests calls, i.e.:

import requests

from requests.adapters import HTTPAdapter, Retry

s = requests.Session()

retries = Retry(total=5,
                backoff_factor=0.1,
                status_forcelist=[ 500, 502, 503, 504 ])

s.mount('http://', HTTPAdapter(max_retries=retries))

s.get('http://httpstat.us/500')

This way we could solve various errors that might happen during these calls, such as:

"Requests to the ChatCompletions_Create Operation under Azure OpenAI API have exceeded token rate limit of your current AIServices S0 pricing tier. Please retry after 11 seconds.

Contributor guide

Tech stack
python
Domain
backend
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
blocked
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Pythonrequests library
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60
Research direction
The issue requests adding a retry strategy to remote HTTP calls in docling/utils/api image request.py. The current code uses `requests`; a session with retry adapter should be implemented as shown in the issue description. The retry should handle 500 level errors and rate limits. No linked PRs or maintainer comments are present, so the implementation can follow the provided snippet.