a replication of one chunk translation workflow using Agently development framework

[Maplemx]

INSTRUCTION

This dir translation_agent_Agently is a replication of one chunk translation workflow using Agently development framework with some extra features:

• You can switch models easily by changing the settings in ./app.py to test the workflow
• Clearly expression of workflow using Agently Workflow in ./workflow.py
• You can edit prompt yaml files in ./prompt_yamls to optimize prompt instructions without coding, these prompt yaml files will be loaded into model request when the workflow start
• Add a command line user input interface (enter 3 times to ensure programe know source text input is over)

HOW TO RUN

git clone [email protected]:Maplemx/translation-agent.git
cd translation-agent/src/translation-agent-Agently
pip install -r requirements.txt
python app.py

[j-dominguez9]

Hi @Maplemx , thank you for suggesting this new application. We are currently working on integrating a gradio app that has a similar functionality. I invite you please to checkout PR #30 and provide feedback if there is something missing from that application. Thanks!

[Maplemx]

Hi @Maplemx , thank you for suggesting this new application. We are currently working on integrating a gradio app that has a similar functionality. I invite you please to checkout PR #30 and provide feedback if there is something missing from that application. Thanks!嗨，感谢您推荐这个新应用程序。我们目前正在努力集成具有类似功能的 gradio 应用程序。我邀请您查看 PR #30 并在该应用程序中缺少某些内容时提供反馈。谢谢！

Hi @j-dominguez9 , thank you for inviting me to checkout PR #30 and that's a great work. In fact Agently is a development framework more like LangChain than Gradio or Streamlit. I think this PR can provide two extra features for the applicaiton:

1. Extend more model support for those models did not adjust OpenAI request format like Ernie, MiniMax
2. Separate those key prompts from workflow codes into YAML files to enable users to customize their translation workflow actions