DeepL/deepl-python

Official Python library for the DeepL language translation API.

What it solves

This library provides a straightforward way for Python developers to integrate DeepL's high-quality translation and text-improvement AI directly into their own applications. It handles the complexities of communicating with the DeepL API, including authentication, request formatting, and document processing.

How it works

After installing the library and authenticating with a DeepL API key, you initialize a DeepLClient. This client provides methods to send text or files to DeepL's servers. The library manages the entire lifecycle of these requests, such as handling document uploads, polling for completion status, and downloading the final translated files. It also supports advanced features like custom glossaries, formality adjustments, and rephrasing via the Write API.

Who it’s for

This project is for software developers building applications that require professional-grade language translation, document localization, or AI-powered text refinement.

Highlights

  • Comprehensive API Support: Access to text translation, document translation, and the Write API for rephrasing.
  • Convenience Methods: Simplifies complex workflows like document translation by automatically handling uploading, status polling, and downloading.
  • Customization: Supports glossaries for domain-specific terminology, formality control (formal/informal), and custom instructions to guide translation behavior.
  • Robust Error Handling: Provides specific exceptions for document translation issues and API errors to help with debugging and production stability.

Related

  • Project
    eggplants/deepl-cli

    A Python CLI (and library) that translates text via the DeepL web interface using Playwright, requiring no API key.

  • Project
    lotus-data/lotus

    LOTUS is a Python library for large‑scale, LLM‑driven data processing. It introduces *semantic operators* (LLM‑based map, filter, reduce, join, etc.) and an optimizer that batches and cascades model calls to improve accuracy while lowering API costs. The library supports both pure LLM operators and *agentic* operators that run tool‑using agents (e.g., a sandboxed Python REPL) on each data shard, enabling complex tasks like code‑base analysis, research synthesis, failure‑mode mining, document extraction, LLM‑as‑judge evaluation, and RAG. Install via `pip install lotus-ai`; usage revolves around creating a `Corpus`, specifying a task, and invoking `agent` or semantic operators. Backed by Stanford/UC Berkeley research and documented on ReadTheDocs, with community Discord and example notebooks.

  • Project
    openml/openml-python

    OpenML‑Python is a Python client library for the OpenML platform, enabling easy download/upload of datasets, tasks, and benchmark suites for machine‑learning research.

  • Project
    federicodeponte/opendraft

    OpenDraft is an open‑source Python engine that generates long‑form academic drafts with citations verified against multiple scholarly databases. It uses 19 specialised AI agents, supports 57+ languages, and exports to PDF, Word or LaTeX. Designed for researchers, students and developers, it provides citation‑checking, TL‑DR summaries, audio digests and data‑fetching utilities, but still requires human review before final publication.

  • Project
    OptimalScale/LMFlow

    LMFlow is an extensible Python toolbox for fine‑tuning large language models. It supports full‑parameter training, LoRA, the memory‑efficient LISA algorithm, QLoRA quantization, and a suite of speed‑up tricks (FlashAttention‑2, DeepSpeed, vLLM, SGLang). After training, it provides simple scripts for chat‑style inference and optional Gradio/Flask deployment. The library is designed for Linux/Colab environments and offers optional extras for multimodal models, distributed reward‑model inference, and more.