Source: debgpt
Section: python
Homepage: https://salsa.debian.org/deeplearning-team/debgpt
Priority: optional
Standards-Version: 4.6.2
Vcs-Git: https://salsa.debian.org/deeplearning-team/debgpt.git
Vcs-Browser: https://salsa.debian.org/deeplearning-team/debgpt
Maintainer: Debian Deep Learning Team <debian-ai@lists.debian.org>
Uploaders: Mo Zhou <lumin@debian.org>
Build-Depends: debhelper-compat (= 13),
 dh-python,
 pybuild-plugin-pyproject,
 python3-all,
 python3-openai,
 python3-rich,
 python3-prompt-toolkit,
 python3-requests,
 python3-bs4,
 pandoc,

Package: debgpt
Architecture: all
Depends: ${misc:Depends}, ${python3:Depends},
Recommends: python3-zmq, git, tldr, man-db,
Suggests: python3-torch | python3-torch-cuda | python3-torch-rocm,
          python3-transformers,
Description: Chatting LLM with Debian-Specific Knowledge
 Large language models (LLMs) are newly emerged tools, which are capable of
 handling tasks that traditional software could never achieve, such as writing
 code based on the specification provided by the user. In this tool, we
 attempt to experiment and explore the possibility of leveraging LLMs to aid
 Debian development, in any extent.
 .
 Essentially, the idea of this tool is to gather some pieces of
 Debian-specific knowledge, combine them together in a prompt, and then send
 them all to the LLM. This tool provides convenient functionality for
 automatically retrieving information from BTS, buildd, Debian Policy, system
 manual pages, tldr manuals, Debian Developer References, etc. It also provides
 convenient wrappers for external tools such as git, where debgpt can
 automatically generate the git commit message and commit the changes for you.
 .
 This tool supports multiple frontends, including OpenAI and ZMQ.
 The ZMQ frontend/backend are provided in this tool to make it self-contained.
