關於Discourse AI

Support

AI 生成的摘要

關於Discourse AI Discussion Summary

The discussion revolves around self-hosting and using Discourse AI with Docker. Chan_Patrick initially shared their struggle in setting up Discourse AI, despite reading the English documentation. They asked if they needed to use Docker to set up AI for features like toxicity.

Lhc_fl confirmed that all Processor: Discourse functions require Docker setup. JammyDodger suggested following the necessary steps in the Discourse AI self-hosted guide.

Chan_Patrick later shared a Docker command they tried to run, but encountered an error. qianping_chen empathized with their struggle, finding it difficult to understand. sam asked Chan_Patrick to explain what they tried and what they aim to achieve, requesting a response in English.

1

大家好，本人安裝了Discourse AI插件但未能設定和使用！本人閱讀了好幾次英文版Discourse AI 說明書但也未能掌握其設定。
因本人是self-hosting ，哪我是不是需要自行用docker 架設AI ! 例如：toxicity

謝謝

2

您是否也按照 Discourse AI - Self-Hosted Guide 中的必要步骤进行了操作？

3

正是如此，Module Providers里提到的所有Processor为Discourse的功能都需要自己用docker架设AI

That’s right. All the functions of Processor: Discourse mentioned in Module Providers require you to use docker to set up AI.

4 
docker run -d --rm --gpus all --shm-size 1g   -p 8080:80   -v /mnt:/data   -e GPTQ_BITS=4   -e GPTQ_GROUPSIZE=32   -e REVISION=gptq-4bit-32g-actorder_True   ghcr.io/huggingface/text-generation-inference:latest   --model-id TheBloke/Upstage-Llama-2-70B-instruct-v2-GPTQ   --max-batch-prefill-tokens=12000   --max-total-tokens=12000   --max-input-length=10000   --quantize=gptq   --sharded=true   --num-shard=$(lspci | grep NVIDIA | wc -l | tr -d '\\n')   --rope-factor=2

Error response from daemon: could not select device driver “” with capabilities: [[gpu]].

5

和你一样痛苦, 实在太难了, 完全搞不懂

6

您能解释一下您尝试了什么以及您想实现什么吗？（请用英语回复 - 即使您使用谷歌翻译）