-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
9df4104
commit a51dd2d
Showing
1 changed file
with
75 additions
and
70 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,97 +1,102 @@ | ||
| # c - Chatbot CLI | ||
| # c - Interact with Chat AI APIs | ||
|
|
||
| ## Usage | ||
|
|
||
| ``` | ||
| c [COMMAND] | ||
| ``` | ||
| Interact with AI chatbots through the command-line interface (CLI). | ||
|
|
||
| ## Commands | ||
|
|
||
| ### anthropic | ||
| ### `anthropic` | ||
|
|
||
| Anthropic Chat API | ||
| Uses Anthropic's Claude API. | ||
|
|
||
| ``` | ||
| c anthropic [OPTIONS] --anthropic-api-key <ANTHROPIC_API_KEY> [PROMPT] | ||
| c anthropic [OPTIONS] --anthropic-api-key <KEY> [PROMPT] | ||
| ``` | ||
|
|
||
| Interact with Anthropic's Claude chatbot API. Allows specifying model, temperature, max tokens etc. | ||
| #### Arguments | ||
|
|
||
| ### openai | ||
| | Argument | Description | | ||
| |-|-| | ||
| | `PROMPT` | The prompt text to send to Claude. | | ||
|
|
||
| OpenAI Chat API | ||
| #### Options | ||
|
|
||
| ``` | ||
| c openai [OPTIONS] --openai-api-key <OPENAI_API_KEY> [PROMPT] | ||
| ``` | ||
| | Option | Description | | ||
| |-|-| | ||
| | `--session` | Chat session name to store context. | | ||
| | `--model` | Claude model to use (claude-v1, claude2, etc). | | ||
| | `--max-tokens` | Max tokens to generate. | | ||
| | `--temperature` | Randomness of response. | | ||
| | `--top-k` | Only sample from top k tokens. | | ||
| | `--top-p` | Nucleus sampling top-p. | | ||
| | `--stop-sequences` | Strings to stop generation. | | ||
| | `--anthropic-api-key` | Anthropic API key. | | ||
| | `--silent` | Silent mode. | | ||
| | `--stream` | Stream response incrementally. | | ||
| | `--pin` | Pin message to history. | | ||
| | `--format` | Output format (raw, json, yaml). | | ||
| | `-h, --help` | Print help. | | ||
|
|
||
| Interact with OpenAI's chatbot API. Allows specifying model, temperature, max tokens etc. | ||
|
|
||
| ### help | ||
| ### `openai` | ||
|
|
||
| Print help for commands and options | ||
| Uses OpenAI's GPT API. | ||
|
|
||
| ``` | ||
| c help [COMMAND] | ||
| c openai [OPTIONS] --openai-api-key <KEY> [PROMPT] | ||
| ``` | ||
|
|
||
| ## Options | ||
|
|
||
| **-h, --help** | ||
|
|
||
| Print help | ||
|
|
||
| ## Anthropic Options | ||
|
|
||
| **--model** | ||
|
|
||
| Claude model to use (default: claude-v1) | ||
|
|
||
| **--temperature** | ||
|
|
||
| Randomness of response (default: 1) | ||
|
|
||
| **--max-tokens** | ||
|
|
||
| Maximum tokens to generate (default: 1000) | ||
| #### Arguments | ||
|
|
||
| **--stop-sequences** | ||
| | Argument | Description | | ||
| |-|-| | ||
| | `PROMPT` | The prompt text to send GPT. | | ||
|
|
||
| Strings to stop generation | ||
| #### Options | ||
|
|
||
| **--anthropic-api-key** | ||
| | Option | Description | | ||
| |-|-| | ||
| | `--session` | Chat session name to store context. | | ||
| | `--model` | GPT model to use (gpt3, gpt4, etc). | | ||
| | `--max-tokens` | Max tokens to generate. | | ||
| | `--temperature` | Randomness of response. | | ||
| | `--top-p` | Nucleus sampling top-p. | | ||
| | `--stop` | Sequences to stop generation. | | ||
| | `--openai-api-key` | OpenAI API key. | | ||
| | `--silent` | Silent mode. | | ||
| | `--stream` | Stream response incrementally. | | ||
| | `--pin` | Pin message to history. | | ||
| | `--format` | Output format (raw, json, yaml). | | ||
| | `-h, --help` | Print help. | | ||
|
|
||
| Anthropic API key | ||
| ### `vertex` | ||
|
|
||
| ## OpenAI Options | ||
| Uses Google Vertex AI Code API. | ||
|
|
||
| **--model** | ||
|
|
||
| OpenAI model to use | ||
|
|
||
| **--temperature** | ||
|
|
||
| Randomness of response (default: 1) | ||
|
|
||
| **--max-tokens** | ||
|
|
||
| Maximum tokens to generate | ||
|
|
||
| **--openai-api-key** | ||
|
|
||
| OpenAI API key | ||
|
|
||
| ## Output Options | ||
|
|
||
| **-s, --silent** | ||
|
|
||
| Silent mode | ||
|
|
||
| **--stream** | ||
|
|
||
| Stream output | ||
| ``` | ||
| c vertex [OPTIONS] --google-api-key <KEY> [PROMPT] | ||
| ``` | ||
|
|
||
| **-f, --format** | ||
| #### Arguments | ||
|
|
||
| | Argument | Description | | ||
| |-|-| | ||
| | `PROMPT` | The prompt text to send Vertex AI. | | ||
|
|
||
| #### Options | ||
|
|
||
| | Option | Description | | ||
| |-|-| | ||
| | `--session` | Chat session name to store context. | | ||
| | `--model` | Vertex model to use. | | ||
| | `--max-tokens` | Max tokens to generate. | | ||
| | `--temperature` | Randomness of response. | | ||
| | `--top-k` | Only sample from top k tokens. | | ||
| | `--top-p` | Nucleus sampling top-p. | | ||
| | `--stop-sequences` | Strings to stop generation. | | ||
| | `--google-api-key` | Google Vertex API key. | | ||
| | `--silent` | Silent mode. | | ||
| | `--stream` | Stream response incrementally. | | ||
| | `--pin` | Pin message to history. | | ||
| | `--format` | Output format (raw, json, yaml). | | ||
| | `-h, --help` | Print help. | | ||
|
|
||
| Output format (default: raw) |