LLM based APIs
Project description
Void Terminal (虚空终端)
The CLI & python API for the well-known project gpt_academic
.
Installation
- Pip installation.
pip install void-terminal
- source installation.
bash init.bash
Usage (Commandline)
- Chat
vt -a "你好,世界树!"
- Ask about how to do a linux command
vt -c "请列举当前系统运行的所有docker容器"
- Config (For all possible configurations, read
config.py
in the mother project.)
# Warning! This will write configuration into .bashrc and change your ENV variables !! Use with caution !!
# 警告,该命令会修改你的.bashrc文件,持久修改你的环境变量
vt --set_conf API_KEY "sk-123456789123456789123456789"
vt --set_conf LLM_MODEL "gpt-3.5-turbo"
vt --set_conf DEFAULT_WORKER_NUM "20"
Usage (Python API)
- Chat without interaction
import void_terminal as vt
# For more available configurations (including network proxy, api, using chatglm etc.),
# see config.py of in the mother project:
# https://github.com/binary-husky/gpt_academic.git
vt.set_conf(key="API_KEY", value="sk-xxxxxxxxxxxxxx")
vt.set_conf(key="LLM_MODEL", value="gpt-3.5-turbo")
chat_kwargs = vt.get_chat_default_kwargs()
chat_kwargs['inputs'] = '你好, 世界树。'
result = vt.get_chat_handle()(**chat_kwargs)
print('\n*************\n' + result + '\n*************\n' )
- Using mother project's plugin (Example: translate THIS readme file to Chinese)
import void_terminal as vt
from rich.live import Live
from rich.markdown import Markdown
vt.set_conf(key="API_KEY", value="sk-xxxxxxxxxxxxxx")
vt.set_conf(key="LLM_MODEL", value="gpt-3.5-turbo")
plugin = vt.get_plugin_handle('void_terminal.crazy_functions.批量Markdown翻译->Markdown翻译指定语言')
plugin_kwargs = vt.get_plugin_default_kwargs()
plugin_kwargs['main_input'] = './README.md'
my_working_plugin = plugin(**plugin_kwargs)
with Live(Markdown(""), auto_refresh=False) as live:
for cookies, chat, hist, msg in my_working_plugin:
md_str = vt.chat_to_markdown_str(chat)
md = Markdown(md_str)
live.update(md, refresh=True)
- Using mother project's plugin (Example: chat with multiple LLM models)
import void_terminal as vt
from rich.live import Live
from rich.markdown import Markdown
llm_model = "gpt-3.5-turbo&gpt-4"
vt.set_conf(key="API_KEY", value="sk-xxxxxxxxxxxxxx")
vt.set_conf(key="LLM_MODEL", value=llm_model)
plugin = vt.get_plugin_handle('void_terminal.crazy_functions.询问多个大语言模型->同时问询_指定模型')
plugin_kwargs = vt.get_plugin_default_kwargs()
plugin_kwargs['main_input'] = '你好, 世界树。'
plugin_kwargs['plugin_kwargs'] = {"advanced_arg": llm_model}
my_working_plugin = plugin(**plugin_kwargs)
with Live(Markdown(""), auto_refresh=False) as live:
for cookies, chat, hist, msg in my_working_plugin:
md_str = vt.chat_to_markdown_str(chat)
md = Markdown(md_str)
live.update(md, refresh=True)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
void-terminal-0.0.6.tar.gz
(10.0 MB
view hashes)
Built Distribution
Close
Hashes for void_terminal-0.0.6-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d182e11c2591954b7744e68b3adcbde8737ab5dfef873aa9799ca52539240893 |
|
MD5 | b7ea8517eea44a23322f1729e67014d4 |
|
BLAKE2b-256 | e0c41d6f76f8b30e0e4448c0c6b3afceb4a8ced58aa58c588d1bfeebb6027dc8 |