Linux command
chatgpt-cli 命令
文本
复制后可按需替换文件名、目录或参数。
常用示例
Start interactive chat
chatgpt
Send a single prompt
chatgpt "[Your question here]"
Chat with specific model
chatgpt -m [gpt-4] "[prompt]"
Set system prompt
chatgpt -s "[You are a helpful assistant]" "[prompt]"
Pipe input to ChatGPT
cat [file.txt] | chatgpt "[Summarize this]"
Use with specific temperature
chatgpt -t [0.7] "[prompt]"
Stream response
chatgpt --stream "[prompt]"
说明
chatgpt-cli provides command-line access to OpenAI's ChatGPT models. It enables conversational AI interactions from the terminal, supporting both interactive sessions and single-query scripting. The tool handles conversation context, allowing multi-turn dialogues in interactive mode. Input can come from arguments, stdin (pipes), or interactive prompts. Responses are rendered with markdown formatting by default for better readability. Integration with shell pipelines enables powerful workflows: analyzing files, transforming text, generating code, and automating content creation. The streaming option shows responses as they're generated.
参数
- -m, --model _name_
- Model to use (gpt-4, gpt-3.5-turbo, etc.).
- -s, --system _prompt_
- System prompt to set context.
- -t, --temperature _value_
- Sampling temperature (0-2, default 1).
- --max-tokens _n_
- Maximum tokens in response.
- --stream
- Stream response tokens as generated.
- -c, --continue
- Continue previous conversation.
- --api-key _key_
- OpenAI API key (or set OPENAI_API_KEY).
- --no-markdown
- Disable markdown rendering.
- -o, --output _file_
- Write response to file.
- -i, --interactive
- Start interactive mode.
FAQ
What is the chatgpt-cli command used for?
chatgpt-cli provides command-line access to OpenAI's ChatGPT models. It enables conversational AI interactions from the terminal, supporting both interactive sessions and single-query scripting. The tool handles conversation context, allowing multi-turn dialogues in interactive mode. Input can come from arguments, stdin (pipes), or interactive prompts. Responses are rendered with markdown formatting by default for better readability. Integration with shell pipelines enables powerful workflows: analyzing files, transforming text, generating code, and automating content creation. The streaming option shows responses as they're generated.
How do I run a basic chatgpt-cli example?
Run `chatgpt` in a terminal, then adjust file names, paths, flags, or remote targets for your system.
What does -m, --model _name_ do in chatgpt-cli?
Model to use (gpt-4, gpt-3.5-turbo, etc.).