sunxichen

Wrong segment number when using api to add batch segments.

1

### Self Checks - [X] This is only for bug report, if you would like to ask a quesion, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [X] I have searched for existing...

How to use the python binding?

9

I successfully installed it from source, but I don't know how to use the `chat` and `stream_chat ` interfaces, or how to load the model, etc. Are there any documents...

### Self Checks - [X] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [X] I confirm that I am using English to submit this...

Extend Tool/Plugin Support to Include Chatbots, Agents, and Workflows

4

### Self Checks - [X] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [X] I confirm that I am using English to submit this...

[BUG] Issues ablout openai /v1/chat/completions interface in streaming mode

2

**Issue description:** 感觉目前的实现跟openai标准的输出的不太一样： 1. finish_reason全都是null，即使生成到最后一个字符了也是null，正常应该是"stop"或"length"吧 2. index全是0 3. stop参数目前不支持："The stop parameter is not currently supported" 4. 在启动服务时，已经设置--eos_id 151645的情况下，生成的内容虽然在之后终止了，但还是会返回，正常情况下这个字符不应该返回的吧 **Steps to reproduce:** 请求示例： { "model": "Qwen", "messages": [ { "role": "user",...

Integration of Guided Generation Features from vllm into XInference

8

### Is your feature request related to a problem? Please describe Currently, when utilizing Xinference with vllm as the backend, users are unable to leverage vllm's advanced guided generation capabilities,...