OperateGPT: Revolutionize Your Operations with One-Line Requests

简体中文 |Documents|

• Using large language models and multi-agent technology, a single request can automatically generate marketing copy, images, and videos, and with one click, can be sent to multiple platforms, achieving a rapid transformation in marketing operations.

Supported Platforms

Operate Platform	Supported	API	Notes
YouTube	Coming soon	Coming soon
Twitter	Coming soon	Coming soon
CSDN	Coming soon	Coming soon
Bilibili	Coming soon	Coming soon
Zhihu	Coming soon	Coming soon
Wechat	Coming soon	Coming soon
Douban	Coming soon	Coming soon
TikTok	Coming soon	Coming soon

Supported LLMs

LLM	Supported	Model Type	Notes
ChatGPT	Yes	Proxy
Bard	Yes	Proxy
Claude	Coming soon	Proxy
Vicuna-13b-v1.5	Coming soon	Local Model
ChatGLM2-6B	Coming soon	Local Model
Qwen-7b-Chat	Coming soon	Local Model

Supported Embedding Models

LLM	Supported	Notes
all-MiniLM-L6-v2	Yes
text2vec-large-chinese	Coming soon

Installation

Firstly, download and install the relevant LLMs.

mkdir models & cd models

# Size: 522 MB
git lfs install 
git clone https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2

# [Options]
# Size: 94 GB, supported run in cpu model(RAM>14 GB). stablediffusion-proxy service is recommended, https://github.com/xuyuan23/stablediffusion-proxy
git lfs install 
git clone https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0

# [Options]
# Size: 16 GB, supported run in cpu model(RAM>16 GB). Text2Video service is recommended. https://github.com/xuyuan23/Text2Video
git lfs install
git clone https://huggingface.co/cerspense/zeroscope_v2_576w

Then, download dependencies and launch your project.

pip install -r requirements.txt

# copy file `.env.template` to new file `.env`, and modify the params in `.env`.
cp .env.template .env 

[Options]
# deploy stablediffusion service, if StableDiffusion proxy is used, no need to execute it!
python operategpt/providers/stablediffusion.py

[Options]
# deploy Text2Video service, if Text2Video proxy server is used, no need to execute it!
python operategpt/providers/text2video.py

python main.py "what is MetaGPT?"

Configuration

• By default, ChatGPT is used as the LLM, and you need to configure the OPEN_AI_KEY in .env

OPEN_AI_KEY=sk-xxx

# If you don't deploy stable diffusion service, no image will be generated.
SD_PROXY_URL=127.0.0.1:7860

# If you don't deploy Text2Video service, no videos will be generated.
T2V_PROXY_URL=127.0.0.1:7861

• More Details see file .env.template

Display

• The content is fully generated by OperateGPT: http://operategpt.cn/web/#/602177878/0

• Video DEMO

operateGPT_demo_low.mp4