chatgpt 命令

常用示例

说明

chatgpt is a command-line interface for interacting with OpenAI's ChatGPT models. It provides terminal-based access to the GPT language models for text generation, coding assistance, analysis, and general conversation. The tool supports both interactive mode for back-and-forth conversation and single-prompt mode for quick queries. Input can be piped from other commands or files, making it useful in shell pipelines for text processing tasks. Configuration can be set via command-line flags, environment variables, or a config file. The OPENAI_API_KEY environment variable is the standard way to provide credentials. Different models offer varying capabilities, speed, and pricing. System prompts allow customizing the assistant's behavior and expertise area. Temperature controls response creativity — lower values produce more focused responses while higher values increase variety. The streaming option displays responses token-by-token as they're generated.

参数

--model, -m _model_

Specify the model to use (gpt-4, gpt-3.5-turbo, etc.).

--system, -s _prompt_

Set a system prompt to define assistant behavior.

--continue, -c

Continue the previous conversation.

--temperature, -t _value_

Control randomness (0.0-2.0, default: 1.0).

--max-tokens _n_

Maximum tokens in the response.

--top-p _value_

Nucleus sampling parameter.

--stream

Stream the response as it's generated.

--no-stream

Wait for complete response before displaying.

--api-key _key_

OpenAI API key (or set OPENAI_API_KEY environment variable).

--config _file_

Path to configuration file.

--list-models

List available models.

--help

Display help information.

--version

Display version information.