Leverage Claude 3.5 Sonnet from Anthropic, a cutting-edge LLM model, to
improve translation outcomes. In #2164, the previous use of Qwen2.5 7b a
smaller and less advanced AI model) was an earlier attempt that may have
resulted in suboptimal quality and user experience. While relying solely
on LLMs for translation is generally not ideal, adopting a more advanced
model like Claude 3.5 allows us to address these earlier limitations and
ensures significantly better results, even for a language I do not
understand.
Furthermore, I also use the powerful frontier OpenAI GPT-4o and Google
Gemini-1.5-Pro for proofreading, and thoroughly examined and verified
line breaks to ensure accuracy and facilitate easier contributions and
improvements by others.
Leverage Claude 3.5 Sonnet from Anthropic, a cutting-edge LLM model, to
improve translation outcomes. In #2164, the previous use of Qwen2.5 7b a
smaller and less advanced AI model) was an earlier attempt that may have
resulted in suboptimal quality and user experience. While relying solely
on LLMs for translation is generally not ideal, adopting a more advanced
model like Claude 3.5 allows us to address these earlier limitations and
ensures significantly better results, even for a language I do not
understand.
Furthermore, I also use the powerful frontier OpenAI GPT-4o and Google
Gemini-1.5-Pro for proofreading, and thoroughly examined and verified
line breaks to ensure accuracy and facilitate easier contributions and
improvements by others.
# Description
Leverage Claude 3.5 Sonnet from Anthropic, a cutting-edge LLM model, to
improve translation outcomes. In #2164, the previous use of Qwen2.5 7b
(a smaller and less advanced AI model) was an earlier attempt that may
have resulted in suboptimal quality and user experience. While relying
solely on LLMs for translation is generally not ideal, adopting a more
advanced model like Claude 3.5 allows us to address these earlier
limitations and ensures significantly better results, even for a
language I do not understand.
Furthermore, I also use the powerful frontier OpenAI GPT-4o and Google
Gemini-1.5-Pro for proofreading, and thoroughly examined and verified
line breaks to ensure accuracy and facilitate easier contributions and
improvements by others.
## Checklist
- [x] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ ] I have performed a self-review of my own code
- [ ] I have attached images of the change if it is UI based
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] If my code has heavily changed functionality I have updated
relevant docs on [Stirling-PDFs doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
- [x] My changes generate no new warnings
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)
# Description
Leverage Claude 3.5 Sonnet from Anthropic, a cutting-edge LLM model, to
improve translation outcomes. In #2164, the previous use of Qwen2.5 7b
(a smaller and less advanced AI model) was an earlier attempt that may
have resulted in suboptimal quality and user experience. While relying
solely on LLMs for translation is generally not ideal, adopting a more
advanced model like Claude 3.5 allows us to address these earlier
limitations and ensures significantly better results, even for a
language I do not understand.
Furthermore, I also use the powerful frontier OpenAI GPT-4o and Google
Gemini-1.5-Pro for proofreading, and thoroughly examined and verified
line breaks to ensure accuracy and facilitate easier contributions and
improvements by others.
## Checklist
- [x] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ ] I have performed a self-review of my own code
- [ ] I have attached images of the change if it is UI based
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] If my code has heavily changed functionality I have updated
relevant docs on [Stirling-PDFs doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
- [x] My changes generate no new warnings
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)
# Description
Leverage Claude 3.5 Sonnet from Anthropic, a cutting-edge LLM model, to
improve translation outcomes. In #2164, the previous use of Qwen2.5 7b
(a smaller and less advanced AI model) was an earlier attempt that may
have resulted in suboptimal quality and user experience. While relying
solely on LLMs for translation is generally not ideal, adopting a more
advanced model like Claude 3.5 allows us to address these earlier
limitations and ensures significantly better results, even for a
language I do not understand.
Furthermore, I also use the powerful frontier OpenAI GPT-4o and Google
Gemini-1.5-Pro for proofreading, and thoroughly examined and verified
line breaks to ensure accuracy and facilitate easier contributions and
improvements by others.
## Checklist
- [x] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ ] I have performed a self-review of my own code
- [ ] I have attached images of the change if it is UI based
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] If my code has heavily changed functionality I have updated
relevant docs on [Stirling-PDFs doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
- [x] My changes generate no new warnings
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)
# Description
Leverage Claude 3.5 Sonnet from Anthropic, a cutting-edge LLM model, to
improve translation outcomes. In #2164, the previous use of Qwen2.5 7b
(a smaller and less advanced AI model) was an earlier attempt that may
have resulted in suboptimal quality and user experience. While relying
solely on LLMs for translation is generally not ideal, adopting a more
advanced model like Claude 3.5 allows us to address these earlier
limitations and ensures significantly better results, even for a
language I do not understand.
Furthermore, I also use the powerful frontier OpenAI GPT-4o and Google
Gemini-1.5-Pro for proofreading, and thoroughly examined and verified
line breaks to ensure accuracy and facilitate easier contributions and
improvements by others.
## Checklist
- [x] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ x I have performed a self-review of my own code
- [ ] I have attached images of the change if it is UI based
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] If my code has heavily changed functionality I have updated
relevant docs on [Stirling-PDFs doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
- [x] My changes generate no new warnings
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)
# Description
Leverage Claude 3.5 Sonnet from Anthropic, a frontier LLM model, to
enhance translation quality. The previous use of Qwen2.5 7b, a smaller
and less advanced AI model, may have affected the quality and user
experience(#2164). Typically, relying solely on LLMs for translation
without verification is not preferred. However, given these concerns,
using a frontier LLM model along with references from other language
versions should lead to improved results, even for a language I don't
even understand.
I also use the powerful frontier OpenAI O1 and Google Gemini-1.5-Pro for
proofreading, and manually confirmed line breaks to facilitate easier
contributions and improvements by others.
## Checklist
- [x] I have read the [Contribution
Guidelines](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/CONTRIBUTING.md)
- [ ] I have performed a self-review of my own code
- [ ] I have attached images of the change if it is UI based
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] If my code has heavily changed functionality I have updated
relevant docs on [Stirling-PDFs doc
repo](https://github.com/Stirling-Tools/Stirling-Tools.github.io/blob/main/docs/)
- [ ] My changes generate no new warnings
- [ ] I have read the section [Add New Translation
Tags](https://github.com/Stirling-Tools/Stirling-PDF/blob/main/HowToAddNewLanguage.md#add-new-translation-tags)
(for new translation tags only)
- Update all Dockerfiles to use `alpine:3.21.0` with SHA256 checksum
- Ensure consistent image versioning, enhanced security, and
reproducibility by explicitly specifying the digest.
cc #2436#2516
Changes include:
- Cleaning up the apt cache by adding `rm -rf /var/lib/apt/lists/*`
after each package installation within the same RUN statement.
- Ensuring the Docker image size is minimized by removing unnecessary
files immediately after use.
These adjustments will result in a more space-efficient Docker image.
Adjusted the README to correctly enumerate all 24 languages supported by
the project. This change includes the addition of Hungarian (Magyar) and
Bulgarian (Български) to the list, based on the properties files located
in 'src/main/resources'.
Peter Dave HelloandGitHub
