类似通义灵码的扩展,里面的自动补全功能是怎么实现的 #340
Labels
No Label
bug
duplicate
enhancement
help wanted
invalid
question
wontfix
No Milestone
No project
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: HswOAuth/llm_course#340
Loading…
Reference in New Issue
Block a user
No description provided.
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
就是如图所示,在ide创建一个文件 里面随便输入一个string 通义灵码就会进行自动补全。现在想做个类似通义灵码的扩展,在做自动补全这个功能有些困惑。我用那种提示词的方法,就是根据上述代码生成代码(不含中文)调用大模型,结果发现了大模型返回的效果并不理想,远远达不到通义灵码的效果。
我上网查阅了一些资料 ,说是把那些代码转换为ast,ast能更加直观的反应代码的结构,把这个提示词给大模型,并且大模型要进行微调,专门用于代码补全。
请问大佬是这样做的吗,如果不是应该怎么做,自动补全才能达到比较好的效果
不是特别清楚通义灵码的实现,找到一个开源项目可以参考看看,
https://beginor.github.io/2024/07/12/ai-code-assistant-with-local-llm.html
https://github.com/continuedev/continue