FastGPT icon indicating copy to clipboard operation
FastGPT copied to clipboard

Use the HTTP module to submit information after content extraction. How can you trigger only one HTTP request?

Open jinghai opened this issue 2 years ago • 2 comments

例行检查

  • [ ] 我已确认目前没有类似 features
  • [ ] 我已确认我已升级到最新版本
  • [ ] 我已完整查看过项目 README,已确定现有版本无法满足需求
  • [ ] 我理解并愿意跟进此 features,协助测试和提供反馈
  • [x] 我理解并认可上述内容,并理解项目维护者精力有限,不遵循规则的 features 可能会被无视或直接关闭

我的场景是聊天过程中抽取用户信息,比如姓名和联系方式,抽取到以后使用HTTP提交到后台,我期望的是提交成功以后就不再次抽取和提交了,不知道是否能够做到。

目前的现象是抽取成功了,但每次聊天都会触发抽取成功,然后又提交一次HTTP。

功能描述

应用场景

相关示例

jinghai avatar Jan 24 '24 06:01 jinghai

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿


Routine inspection

  • [ ] I have confirmed that there are currently no similar features
  • [ ] I have confirmed that I have upgraded to the latest version
  • [ ] I have fully reviewed the project README and determined that the existing version cannot meet the needs.
  • [ ] I understand and am willing to follow up on this feature, assist with testing and provide feedback
  • [x] I understand and agree with the above content, and understand that project maintainers have limited energy. Features that do not follow the rules may be ignored or closed directly

My scenario is to extract user information during the chat, such as name and contact information, and then submit it to the backend using HTTP. What I hope is that after the submission is successful, it will not be extracted and submitted again. I don’t know if it can be done.

The current phenomenon is that the extraction is successful, but each chat triggers a successful extraction and then submits HTTP again.

Function description

Application Scenario

Related Examples

c121914yu avatar Jan 24 '24 06:01 c121914yu

目前不太行,每个流程都是独立的,除了对话记录,没有历史状态。

c121914yu avatar Feb 27 '24 13:02 c121914yu