@ -3,9 +3,15 @@
[](https://github.com/sigoden/aichat/actions/workflows/ci.yaml)
[](https://crates.io/crates/aichat)
Chat with gpt-3.5/chatgpt in terminal.
Using ChatGPT/GPT-3.5/GPT-4 in the terminal.
AIChat in chat mode:
AIChat in command mode:
## Install
@ -21,13 +27,14 @@ Download it from [Github Releases](https://github.com/sigoden/aichat/releases),
## Features
- Support chat and command modes
- Predefine AI [roles ](#roles )
- Use GPT prompt easily
- Powerful [Chat REPL ](#chat-repl )
- Context-ware conversation
- syntax highlighting markdown and other 200 languages.
- syntax highlighting markdown and other 200 languages
- Stream output with hand typing effect
- Multiline input support and emacs-like editing experience
- Support multiple models
- Support proxy
- Support dark/light theme
- Save chat messages
@ -48,12 +55,15 @@ After setting, it will automatically create the configuration file. Of course, y
```yaml
api_key: "< YOUR SECRET API KEY > " # Request via https://platform.openai.com/account/api-keys
organization_id: "org-xxx" # optional, set organization id
model: "gpt-3.5-turbo" # optional, choose a model
temperature: 1.0 # optional, see https://platform.openai.com/docs/api-reference/chat/create#chat/create-temperature
save: true # optional, If set true, aichat will save chat messages to message.md
highlight: true # optional, Set false to turn highlight
proxy: "socks5://127.0.0.1:1080" # optional, set proxy server. e.g. http://127.0.0.1:8080 or socks5://127.0.0.1:1080
conversation_first: false # optional, If set true, start a conversation immediately upon repl
light_theme: false # optional, If set true, use light theme
connect_timeout: 10 # optional, Set a timeout in seconds for connect to gpt.
```
> You can use `.info` to view the current configuration file path and roles file path.
@ -66,7 +76,7 @@ We can let ChatGPT play a certain role through `prompt` to make it better genera
We can predefine a batch of roles in `roles.yaml` .
> We can get the location of `roles.yaml` through the `.info` command.
> We can get the location of `roles.yaml` through the repl's `.info` command or cli's `--info` option .
For example, we define a role
@ -76,7 +86,6 @@ For example, we define a role
I want you to act as a linux shell expert.
I want you to answer only with bash code.
Do not provide explanations.
# temperature: 0.3
```
Let ChatGPT answer questions in the role of a linux shell expert.
@ -84,60 +93,11 @@ Let ChatGPT answer questions in the role of a linux shell expert.
〉.role shell
shell〉 extract encrypted zipfile app.zip to /tmp/app
---
mkdir /tmp/app
unzip -P PASSWORD app.zip -d /tmp/app
---
```
We have provided many [Role Examples ](https://github.com/sigoden/aichat/wiki/Role-Examples ).
## CLI
```
A powerful chatgpt cli.
Usage: aichat [OPTIONS] [TEXT]...
Arguments:
[TEXT]... Input text
Options:
-p, --prompt < PROMPT > Set a GPT prompt
-H, --no-highlight Disable syntax highlightiing
-S, --no-stream No stream output
--list-roles List all roles
-r, --role < ROLE > Select a role
-h, --help Print help
-V, --version Print version
```
### Command mode
```sh
aichat math 3.8x4
```
control highlighting and streaming
```sh
aichat how to post a json in rust # highlight, streaming output
aichat -H -S how to post a json in rust # no highlight, output all at once
```
pipe input/output
```sh
# convert toml to json
cat data.toml | aichat turn toml below to json > data.json
```
### Chat mode
Enter Chat REPL if no text input.
```
$ aichat
Welcome to aichat 0.5.0
Type ".help" for more information.
〉
```
We have provided many awesome [Role Examples ](https://github.com/sigoden/aichat/wiki/Role-Examples ).
## Chat REPL
@ -152,7 +112,7 @@ The Chat REPL supports:
- Undo support
- Clipboard integration
### multi-line editing mode
### multi-line editing
**Type `{` or `(` at the beginning of the line to enter the multi-line editing mode.** In this mode you can type or paste multiple lines of text. Type the corresponding `}` or `)` at the end of the line to exit the mode and submit the content.
@ -174,6 +134,7 @@ The Chat REPL supports:
〉.help
.info Print the information
.set Modify the configuration temporarily
.model Choose a model
.prompt Add a GPT prompt
.role Select a role
.clear role Clear the currently selected role
@ -186,7 +147,6 @@ The Chat REPL supports:
Type `{` to enter the multi-line editing mode, type '}' to exit the mode.
Press Ctrl+C to abort readline, Ctrl+D to exit the REPL
```
### `.info` - view current configuration information.
@ -197,23 +157,35 @@ config_file /home/alice/.config/aichat/config.yaml
roles_file /home/alice/.config/aichat/roles.yaml
messages_file /home/alice/.config/aichat/messages.md
api_key sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
organization_id -
model gpt-3.5-turbo
temperature -
save true
highlight true
proxy -
conversation_first false
light_theme false
connect_timeout 10
dry_run false
```
### `.set` - modify the configuration temporarily
```
〉.set dry_run true
〉.set highlight false
〉.set save false
〉.set temperature 1.2
```
### `.model` - choose a model
```
> .model gpt-4
> .model gpt-4-32k
> .model gpt-3.5-turbo
```
### `.prompt` - use GPT prompt
When you set up a prompt, every message sent later will carry the prompt.
@ -234,7 +206,7 @@ Done
🙈😳
```
`.prompt` actually creates a temporary role called `%TEMP%` internally, so **run `.clear role` to clear the prompt** .
`.prompt` actually creates a temporary role internally, so **run `.clear role` to clear the prompt** .
When you are satisfied with the prompt, add it to `roles.yaml` for later use.
@ -286,14 +258,19 @@ You can run `.conversation` to enter context-aware mode, or set `config.conversa
2
1
＄
〉
```
When enter conversation mode, prompt `〉` will change to `＄ , A number will appear on the right, which means how many tokens left to use.
Once the number becomes zero, you need to start a new conversation.
Exit conversation mode
```
＄
〉
```
## License
Copyright (c) 2023 aichat-developers.
sigoden
1 year ago