aicommit2 1.12.6 → 2.0.0

package/README.md

@@ -1,6 +1,6 @@
 <div align="center">
   <div>
-    <img src="https://github.com/tak-bro/aicommit2/blob/main/img/demo_body_min.gif?raw=true" alt="AICommit2"/>
+    <img src="https://github.com/tak-bro/aicommit2/blob/main/img/demo-min.gif?raw=true" alt="AICommit2"/>
     <h1 align="center">AICommit2</h1>
   </div>
   <p>
@@ -25,11 +25,11 @@ _aicommit2_ is a reactive CLI tool that automatically generates Git commit messa
 
 ## Key Features
 
-- **Multi-AI Support**: Integrates with OpenAI, Anthropic Claude, Google Gemini, Mistral AI, Cohere, Groq, Huggingface.
+- **Multi-AI Support**: Integrates with OpenAI, Anthropic Claude, Google Gemini, Mistral AI, Cohere, Groq and more.
 - **Local Model Support**: Use local AI models via Ollama.
 - **Reactive CLI**: Enables simultaneous requests to multiple AIs and selection of the best commit message.
 - **Git Hook Integration**: Can be used as a prepare-commit-msg hook.
-- **Custom Prompts**: Supports user-defined prompt templates.
+- **Custom Prompt**: Supports user-defined system prompt templates.
 
 ## Supported Providers
 
@@ -38,12 +38,11 @@ _aicommit2_ is a reactive CLI tool that automatically generates Git commit messa
 - [OpenAI](https://openai.com/)
 - [Anthropic Claude](https://console.anthropic.com/)
 - [Gemini](https://gemini.google.com/)
-- [Mistral AI](https://mistral.ai/)
-    - [Codestral **(Free till August 1, 2024)**](https://mistral.ai/news/codestral/)
+- [Mistral AI](https://mistral.ai/) (including [Codestral](https://mistral.ai/news/codestral/))
 - [Cohere](https://cohere.com/)
 - [Groq](https://groq.com/)
-- [Huggingface **(Unofficial)**](https://huggingface.co/chat/)
 - [Perplexity](https://docs.perplexity.ai/)
+- [Huggingface **(Unofficial)**](https://huggingface.co/chat/)
 
 ### Local
 
@@ -59,66 +58,22 @@ _aicommit2_ is a reactive CLI tool that automatically generates Git commit messa
 npm install -g aicommit2
 ```
 
-2. Retrieve and set API keys or Cookie you intend to use:
-
-It is not necessary to set all keys. **But at least one key must be set up.**
-
-- [OpenAI](https://platform.openai.com/account/api-keys)
-```sh
-aicommit2 config set OPENAI_KEY=<your key>
-```
-
-- [Anthropic Claude](https://console.anthropic.com/)
-```sh
-aicommit2 config set ANTHROPIC_KEY=<your key>
-```
-
-- [Gemini](https://aistudio.google.com/app/apikey)
-```sh
-aicommit2 config set GEMINI_KEY=<your key>
-```
-
-- [Mistral AI](https://console.mistral.ai/)
-```sh
-aicommit2 config set MISTRAL_KEY=<your key>
-```
-
-- [Codestral](https://console.mistral.ai/)
-```sh
-aicommit2 config set CODESTRAL_KEY=<your key>
-```
-
-- [Cohere](https://dashboard.cohere.com/)
-```sh
-aicommit2 config set COHERE_KEY=<your key>
-```
-
-- [Groq](https://console.groq.com)
-```sh
-aicommit2 config set GROQ_KEY=<your key>
-```
-
-- [Huggingface **(Unofficial)**](https://github.com/tak-bro/aicommit2?tab=readme-ov-file#how-to-get-cookieunofficial-api)
-```shell
-# Please be cautious of Escape characters(\", \') in browser cookie string 
-aicommit2 config set HUGGINGFACE_COOKIE="<your browser cookie>"
-```
+2. Set up API keys (**at least ONE key must be set**):
 
-- [Perplexity](https://docs.perplexity.ai/)
 ```sh
-aicommit2 config set PERPLEXITY_KEY=<your key>
+aicommit2 config set OPENAI.key=<your key>
+aicommit2 config set OLLAMA.model=<your local model>
+# ... (similar commands for other providers)
 ```
 
-This will create a `.aicommit2` file in your home directory.
-
-> You may need to create an account and set up billing.
-
-3. Run aicommit2 with your staged files in git repository:
+3. Run _aicommit2_ with your staged files in git repository:
 ```shell
 git add <files...>
 aicommit2
 ```
 
+> 👉 **Tip:** Use the `aic2` alias if `aicommit2` is too long for you.
+
 ## Using Locally
 
 You can also use your model for free with [Ollama](https://ollama.com/) and it is available to use both Ollama and remote providers **simultaneously**.
@@ -126,18 +81,16 @@ You can also use your model for free with [Ollama](https://ollama.com/) and it i
 1. Install Ollama from [https://ollama.com](https://ollama.com/)
 
 2. Start it with your model
-
 ```shell
-ollama run llama3 # model you want use. ex) codellama, deepseek-coder
+ollama run llama3.1 # model you want use. ex) codellama, deepseek-coder
 ```
 
 3. Set the model and host
-
 ```sh
-aicommit2 config set OLLAMA_MODEL=<your model>
+aicommit2 config set OLLAMA.model=<your model>
 ```
 
-> If you want to use ollama, you must set **OLLAMA_MODEL**.
+> If you want to use Ollama, you must set **OLLAMA.model**.
 
 4. Run _aicommit2_ with your staged in git repository
 ```shell
@@ -172,202 +125,165 @@ For example, you can stage all changes in tracked files with as you commit:
 aicommit2 --all # or -a
 ```
 
-> 👉 **Tip:** Use the `aic2` alias if `aicommit2` is too long for you.
-
 #### CLI Options
 
-##### `--locale` or `-l`
-- Locale to use for the generated commit messages (default: **en**)
+- `--locale` or `-l`: Locale to use for the generated commit messages (default: **en**)
+- `--all` or `-a`: Automatically stage changes in tracked files for the commit (default: **false**)
+- `--type` or `-t`: Git commit message format (default: **conventional**). It supports [`conventional`](https://conventionalcommits.org/) and [`gitmoji`](https://gitmoji.dev/)
+- `--confirm` or `-y`: Skip confirmation when committing after message generation (default: **false**)
+- `--clipboard` or `-c`: Copy the selected message to the clipboard (default: **false**).
+  - If you give this option, **_aicommit2_ will not commit**.
+- `--generate` or `-g`: Number of messages to generate (default: **1**)
+  - **Warning**: This uses more tokens, meaning it costs more.
+- `--prompt` or `-p`: System prompt for fine-tuning
+  - **Warning**: This option is **not recommended**. Please use `systemPrompt` or `systemPromptPath` for each model.
 
+Example:
 ```sh
-aicommit2 --locale <s> # or -l <s>
+aicommit2 --locale "jp" --all --type "conventional" --generate 3 --clipboard
 ```
 
-##### `--generate` or `-g`
-- Number of messages to generate (Warning: generating multiple costs more) (default: **1**)
-- Sometimes the recommended commit message isn't the best so you want it to generate a few to pick from. You can generate multiple commit messages at once by passing in the `--generate <i>` flag, where 'i' is the number of generated messages:
+### Git hook
 
-```sh
-aicommit2 --generate <i> # or -g <i>
-```
+You can also integrate _aicommit2_ with Git via the [`prepare-commit-msg`](https://git-scm.com/docs/githooks#_prepare_commit_msg) hook. This lets you use Git like you normally would, and edit the commit message before committing.
 
-> Warning: this uses more tokens, meaning it costs more.
+#### Install
 
-##### `--all` or `-a`
-- Automatically stage changes in tracked files for the commit (default: **false**)
+In the Git repository you want to install the hook in:
 
 ```sh
-aicommit2 --all # or -a
+aicommit2 hook install
 ```
 
-##### `--type` or `-t`
-- Automatically stage changes in tracked files for the commit (default: **conventional**)
-- it supports [`conventional`](https://conventionalcommits.org/) and [`gitmoji`](https://gitmoji.dev/)
-
-```sh
-aicommit2 --type conventional # or -t conventional
-aicommit2 --type gitmoji # or -t gitmoji
-```
+#### Uninstall
 
-##### `--confirm` or `-y`
-- Skip confirmation when committing after message generation (default: **false**)
+In the Git repository you want to uninstall the hook from:
 
 ```sh
-aicommit2 --confirm # or -y
+aicommit2 hook uninstall
 ```
 
-##### `--clipboard` or `-c`
-- Copy the selected message to the clipboard (default: **false**)
-- This is a useful option when you don't want to commit through _aicommit2_.
-- If you give this option, _aicommit2_ will not commit.
+### Configuration
 
-```sh
-aicommit2 --clipboard # or -c
-```
+#### Reading and Setting Configuration
 
-##### `--promptPath` or `-p`
-- Allow users to specify a custom file path for their own prompt template
-- Enable users to define and use their own prompts instead of relying solely on the default prompt
-- Please see [Custom Prompt Template](#custom-prompt-template)
+- READ: `aicommit2 config get <key>`
+- SET: `aicommit2 config set <key>=<value>`
 
+Example:
 ```sh
-aicommit2 --promptPath <s> # or -p <s>
+aicommit2 config get OPENAI
+aicommit2 config get GEMINI.key
+aicommit2 config set OPENAI.generate=3 GEMINI.temperature=0.5
 ```
 
-### Git hook
-
-You can also integrate _aicommit2_ with Git via the [`prepare-commit-msg`](https://git-scm.com/docs/githooks#_prepare_commit_msg) hook. This lets you use Git like you normally would, and edit the commit message before committing.
-
-#### Install
-
-In the Git repository you want to install the hook in:
+#### How to Configure in detail
 
+1. Command-line arguments: **use the format** `--[ModelName].[SettingKey]=value`
 ```sh
-aicommit2 hook install
+aicommit2 --OPENAI.locale="jp" --GEMINI.temperatue="0.5"
 ```
 
-#### Uninstall
-
-In the Git repository you want to uninstall the hook from:
-
-```sh
-aicommit2 hook uninstall
-```
+2. Configuration file: **use INI format in the `~/.aicommit2` file or use `set` command**.
+   Example `~/.aicommit2`:
+```ini
+# General Settings
+logging=true
+generate=2
+temperature=1.0
 
-#### Usage
+# Model-Specific Settings
+[OPENAI]
+key="<your-api-key>"
+temperature=0.8
+generate=1
+systemPromptPath="<your-prompt-path>"
 
-1. Stage your files and commit:
+[GEMINI]
+key="<your-api-key>"
+generate=5
+ignoreBody=false
 
-```sh
-git add <files...>
-git commit # Only generates a message when it's not passed in
+[OLLAMA]
+temperature=0.7
+model[]=llama3.1
+model[]=codestral
 ```
 
-> If you ever want to write your own message instead of generating one, you can simply pass one in: `git commit -m "My message"`
+> The priority of settings is: **Command-line Arguments > Model-Specific Settings > General Settings > Default Values**.
 
-2. _aicommit2_ will generate the commit message for you and pass it back to Git. Git will open it with the [configured editor](https://docs.github.com/en/get-started/getting-started-with-git/associating-text-editors-with-git) for you to review/edit it.
+## General Settings
 
-3. Save and close the editor to commit!
+The following settings can be applied to most models, but support may vary.
+Please check the documentation for each specific model to confirm which settings are supported.
 
-## Configuration
+| Setting            | Description                                                          | Default      |
+|--------------------|----------------------------------------------------------------------|--------------|
+| `systemPrompt`     | System Prompt text                                                   | -            |
+| `systemPromptPath` | Path to system prompt file                                           | -            |
+| `timeout`          | Request timeout (milliseconds)                                       | 10000        |
+| `temperature`      | Model's creativity (0.0 - 2.0)                                       | 0.7          |
+| `maxTokens`        | Maximum number of tokens to generate                                 | 1024         |
+| `locale`           | Locale for the generated commit messages                             | en           |
+| `generate`         | Number of commit messages to generate                                | 1            |
+| `type`             | Type of commit message to generate                                   | conventional |
+| `maxLength`        | Maximum character length of the Subject of generated commit message  | 50           |
+| `logging`          | Enable logging                                                       | true         |
+| `ignoreBody`       | Whether the commit message includes body                             | true         |
 
-### Reading a configuration value
+> 👉 **Tip:** To set the General Settings for each model, use the following command.
+> ```shell
+> aicommit2 config set OPENAI.locale="jp"
+> aicommit2 config set CODESTRAL.type="gitmoji"
+> aicommit2 config set GEMINI.ignoreBody=false
+> ```
 
-To retrieve a configuration option, use the command:
+##### systemPrompt
+- Allow users to specify a custom system prompt
 
 ```sh
-aicommit2 config get <key>
+aicommit2 config set systemPrompt="Generate git commit message."
 ```
 
-For example, to retrieve the API key, you can use:
+> `systemPrompt` takes precedence over `systemPromptPath` and does not apply at the same time.
 
-```sh
-aicommit2 config get OPENAI_KEY
-```
-
-You can also retrieve multiple configuration options at once by separating them with spaces:
+##### systemPromptPath
+- Allow users to specify a custom file path for their own system prompt template
+- Please see [Custom Prompt Template](#custom-prompt-template)
 
 ```sh
-aicommit2 config get OPENAI_KEY OPENAI_MODEL GEMINI_KEY 
+aicommit2 config set systemPromptPath="/path/to/user/prompt.txt"
 ```
 
-### Setting a configuration value
+##### timeout
+
+The timeout for network requests in milliseconds.
 
-To set a configuration option, use the command:
+Default: `10_000` (10 seconds)
 
 ```sh
-aicommit2 config set <key>=<value>
+aicommit2 config set timeout=20000 # 20s
 ```
 
-For example, to set the API key, you can use:
+##### temperature
 
-```sh
-aicommit2 config set OPENAI_KEY=<your-api-key>
-```
+The temperature (0.0-2.0) is used to control the randomness of the output
 
-You can also set multiple configuration options at once by separating them with spaces, like
+Default: `0.7`
 
 ```sh
-aicommit2 config set OPENAI_KEY=<your-api-key> generate=3 locale=en
+aicommit2 config set temperature=0.3
 ```
 
-## Options
-
-| Option               | Default                                | Description                                                                                                                        |
-|----------------------|----------------------------------------|------------------------------------------------------------------------------------------------------------------------------------|
-| `OPENAI_KEY`         | N/A                                    | The OpenAI API key                                                                                                                 |
-| `OPENAI_MODEL`       | `gpt-3.5-turbo`                        | The OpenAI Model to use                                                                                                            |
-| `OPENAI_URL`         | `https://api.openai.com`               | The OpenAI URL                                                                                                                     |
-| `OPENAI_PATH`        | `/v1/chat/completions`                 | The OpenAI request pathname                                                                                                        |
-| `ANTHROPIC_KEY`      | N/A                                    | The Anthropic API key                                                                                                              |
-| `ANTHROPIC_MODEL`    | `claude-3-haiku-20240307`              | The Anthropic Model to use                                                                                                         |
-| `GEMINI_KEY`         | N/A                                    | The Gemini API key                                                                                                                 |
-| `GEMINI_MODEL`       | `gemini-1.5-pro-latest`                | The Gemini Model                                                                                                                   |
-| `MISTRAL_KEY`        | N/A                                    | The Mistral API key                                                                                                                |
-| `MISTRAL_MODEL`      | `mistral-tiny`                         | The Mistral Model to use                                                                                                           |
-| `CODESTRAL_KEY`      | N/A                                    | The Codestral API key                                                                                                              |  
-| `CODESTRAL_MODEL`    | `codestral-latest`                     | The Codestral Model to use                                                                                                         |
-| `COHERE_KEY`         | N/A                                    | The Cohere API Key                                                                                                                 |
-| `COHERE_MODEL`       | `command`                              | The identifier of the Cohere model                                                                                                 |
-| `GROQ_KEY`           | N/A                                    | The Groq API Key                                                                                                                   |
-| `GROQ_MODEL`         | `gemma-7b-it`                          | The Groq model name to use                                                                                                         |
-| `HUGGINGFACE_COOKIE` | N/A                                    | The HuggingFace Cookie string                                                                                                      |
-| `HUGGINGFACE_MODEL`  | `mistralai/Mixtral-8x7B-Instruct-v0.1` | The HuggingFace Model to use                                                                                                       |
-| `PERPLEXITY_KEY`     | N/A                                    | The Perplexity API key                                                                                                             |
-| `PERPLEXITY_MODEL`   | `llama-3.1-sonar-small-128k-chat`      | The Perplexity Model to use                                                                                                        |
-| `OLLAMA_MODEL`       | N/A                                    | The Ollama Model. It should be downloaded your local                                                                               |
-| `OLLAMA_HOST`        | `http://localhost:11434`               | The Ollama Host                                                                                                                    |
-| `OLLAMA_TIMEOUT`     | `100_000` ms                           | Request timeout for the Ollama                                                                                                     |
-| `locale`             | `en`                                   | Locale for the generated commit messages                                                                                           |
-| `generate`           | `1`                                    | Number of commit messages to generate                                                                                              |
-| `type`               | `conventional`                         | Type of commit message to generate                                                                                                 |
-| `proxy`              | N/A                                    | Set a HTTP/HTTPS proxy to use for requests(only **OpenAI**)                                                                        |
-| `timeout`            | `10_000` ms                            | Network request timeout                                                                                                            |
-| `max-length`         | `50`                                   | Maximum character length of the generated commit message(Subject)                                                                  |
-| `max-tokens`         | `1024`                                 | The maximum number of tokens that the AI models can generate (for **Open AI, Anthropic, Gemini, Mistral, Codestral**)              |
-| `temperature`        | `0.7`                                  | The temperature (0.0-2.0) is used to control the randomness of the output (for **Open AI, Anthropic, Gemini, Mistral, Codestral**) |
-| `promptPath`         | N/A                                    | Allow users to specify a custom file path for their own prompt template                                                            |
-| `logging`            | `false`                                | Whether to log AI responses for debugging (true or false)                                                                          |
-| `ignoreBody`         | `true`                                 | Whether the commit message includes body (true or false)                                                                           |
-
-> **Currently, options are set universally. However, there are plans to develop the ability to set individual options in the future.**
+##### maxTokens
 
-### Available Options by Model
-|                      | locale | generate | type  | proxy |        timeout         | max-length  | max-tokens | temperature | prompt |
-|:--------------------:|:------:|:--------:|:-----:|:-----:|:----------------------:|:-----------:|:----------:|:-----------:|:------:|
-|      **OpenAI**      |   ✓    |    ✓     |   ✓   |   ✓   |           ✓            |      ✓      |     ✓      |      ✓      |   ✓    |
-| **Anthropic Claude** |   ✓    |    ✓     |   ✓   |       |                        |      ✓      |     ✓      |      ✓      |   ✓    |
-|      **Gemini**      |   ✓    |    ✓     |   ✓   |       |                        |      ✓      |     ✓      |      ✓      |   ✓    |
-|    **Mistral AI**    |   ✓    |    ✓     |   ✓   |       |           ✓            |      ✓      |     ✓      |      ✓      |   ✓    |
-|    **Codestral**     |   ✓    |    ✓     |   ✓   |       |           ✓            |      ✓      |     ✓      |      ✓      |   ✓    |
-|      **Cohere**      |   ✓    |    ✓     |   ✓   |       |                        |      ✓      |     ✓      |      ✓      |   ✓    |
-|       **Groq**       |   ✓    |    ✓     |   ✓   |       |           ✓            |      ✓      |            |             |   ✓    |
-|   **Huggingface**    |   ✓    |    ✓     |   ✓   |       |                        |      ✓      |            |             |   ✓    |
-|    **Perplexity**    |   ✓    |    ✓     |   ✓   |       |           ✓            |      ✓      |     ✓      |      ✓      |   ✓    |
-|      **Ollama**      |   ✓    |    ✓     |   ✓   |       | ⚠<br/>(OLLAMA_TIMEOUT) |      ✓      |            |      ✓      |   ✓    |
+The maximum number of tokens that the AI models can generate.
 
+Default: `1024`
 
-### Common Options
+```sh
+aicommit2 config set maxTokens=3000
+```
 
 ##### locale
 
@@ -375,6 +291,10 @@ Default: `en`
 
 The locale to use for the generated commit messages. Consult the list of codes in: https://wikipedia.org/wiki/List_of_ISO_639_language_codes.
 
+```sh
+aicommit2 config set locale="jp"
+```
+
 ##### generate
 
 Default: `1`
@@ -383,189 +303,251 @@ The number of commit messages to generate to pick from.
 
 Note, this will use more tokens as it generates more results.
 
-##### proxy
-
-Set a HTTP/HTTPS proxy to use for requests.
-
-To clear the proxy option, you can use the command (note the empty value after the equals sign):
-
-> **Only supported within the OpenAI**
-
 ```sh
-aicommit2 config set proxy=
+aicommit2 config set generate=2
 ```
 
-##### timeout
+##### type
 
-The timeout for network requests to AI in milliseconds.
+Default: `conventional`
 
-Default: `10_000` (10 seconds)
+Supported: `conventional`, `gitmoji`
+
+The type of commit message to generate. Set this to "conventional" to generate commit messages that follow the Conventional Commits specification:
 
 ```sh
-aicommit2 config set timeout=20000 # 20s
+aicommit2 config set type="conventional"
 ```
 
-##### max-length
+##### maxLength
 
-The maximum character length of the generated commit message.
+The maximum character length of the Subject of generated commit message
 
 Default: `50`
 
 ```sh
-aicommit2 config set max-length=100
+aicommit2 config set maxLength=100
 ```
 
-##### type
-
-Default: `conventional`
+##### logging
 
-Supported: `conventional`, `gitmoji`
+Default: `true`
 
-The type of commit message to generate. Set this to "conventional" to generate commit messages that follow the Conventional Commits specification:
+Option that allows users to decide whether to generate a log file capturing the responses.
+The log files will be stored in the `~/.aicommit2_log` directory(user's home).
 
-```sh
-aicommit2 config set type=conventional
-```
+![log-path](https://github.com/tak-bro/aicommit2/blob/main/img/log_path.png?raw=true)
 
-You can clear this option by setting it to an empty string:
+- You can remove all logs below comamnd.
 
 ```sh
-aicommit2 config set type=
+aicommit2 log removeAll 
 ```
 
-##### max-tokens
-The maximum number of tokens that the AI models can generate.
+##### ignoreBody
 
-Default: `1024`
+Default: `true`
+
+This option determines whether the commit message includes body. If you want to include body in message, you can set it to `false`.
 
 ```sh
-aicommit2 config set max-tokens=3000
+aicommit2 config set ignoreBody="false"
 ```
 
-##### temperature
-The temperature (0.0-2.0) is used to control the randomness of the output
+![ignore_body_false](https://github.com/tak-bro/aicommit2/blob/main/img/demo_body_min.gif?raw=true)
 
-Default: `0.7`
 
 ```sh
-aicommit2 config set temperature=0
+aicommit2 config set ignoreBody="true"
 ```
 
-##### promptPath
-- Allow users to specify a custom file path for their own prompt template
-- Enable users to define and use their own prompts instead of relying solely on the default prompt
-- Please see [Custom Prompt Template](#custom-prompt-template)
+![ignore_body_true](https://github.com/tak-bro/aicommit2/blob/main/img/ignore_body_true.png?raw=true)
 
-```sh
-aicommit2 config set promptPath="/path/to/user/prompt.txt"
-```
+## Model-Specific Settings
 
-##### logging
+> Some models mentioned below are subject to change.
 
-Default: `false`
+### OpenAI
 
-Option that allows users to decide whether to generate a log file capturing the responses.
-The log files will be stored in the `~/.aicommit2_log` directory(user's home).
+| Setting            | Description                                                         | Default                |
+|--------------------|---------------------------------------------------------------------|------------------------|
+| `key`              | API key                                                             | -                      |
+| `model`            | Model to use                                                        | `gpt-3.5-turbo`        |
+| `url`              | API endpoint URL                                                    | https://api.openai.com |
+| `path`             | API path                                                            | /v1/chat/completions   |
+| `proxy`            | Proxy settings                                                      | -                      |
 
-![log-path](https://github.com/tak-bro/aicommit2/blob/main/img/log_path.png?raw=true)
+##### OPENAI.key
 
-```sh
-aicommit2 config set logging="true"
-```
+The OpenAI API key. You can retrieve it from [OpenAI API Keys page](https://platform.openai.com/account/api-keys).
 
-- You can remove all logs below comamnd.
- 
 ```sh
-aicommit2 log removeAll 
+aicommit2 config set OPENAI.key="your api key"
 ```
 
-##### ignoreBody
+##### OPENAI.model
 
-Default: `true`
+Default: `gpt-3.5-turbo`
 
-This option determines whether the commit message includes body. If you want to include body in message, you can set it to `false`.
+The Chat Completions (`/v1/chat/completions`) model to use. Consult the list of models available in the [OpenAI Documentation](https://platform.openai.com/docs/models/model-endpoint-compatibility).
+
+> Tip: If you have access, try upgrading to [`gpt-4`](https://platform.openai.com/docs/models/gpt-4) for next-level code analysis. It can handle double the input size, but comes at a higher cost. Check out OpenAI's website to learn more.
 
 ```sh
-aicommit2 config set ignoreBody="false"
+aicommit2 config set OPENAI.model=gpt-4
 ```
 
-![ignore_body_false](https://github.com/tak-bro/aicommit2/blob/main/img/ignore_body_false.png?raw=true)
+##### OPENAI.url
 
+Default: `https://api.openai.com`
+
+The OpenAI URL. Both https and http protocols supported. It allows to run local OpenAI-compatible server.
 
 ```sh
-aicommit2 config set ignoreBody="true"
+aicommit2 config set OPENAI.url="<your-host>"
 ```
 
-![ignore_body_true](https://github.com/tak-bro/aicommit2/blob/main/img/ignore_body_true.png?raw=true)
+##### OPENAI.path
+
+Default: `/v1/chat/completions`
+
+The OpenAI Path.
 
 ### Ollama
 
-##### OLLAMA_MODEL
+| Setting            | Description                                                                                                      | Default                |
+|--------------------|------------------------------------------------------------------------------------------------------------------|------------------------|
+| `model`            | Model(s) to use (comma-separated list)                                                                           | -                      |
+| `host`             | Ollama host URL                                                                                                  | http://localhost:11434 |
+| `timeout`          | Request timeout (milliseconds)                                                                                   | 100_000 (100sec)       |
+
+##### OLLAMA.model
 
 The Ollama Model. Please see [a list of models available](https://ollama.com/library)
 
 ```sh
-aicommit2 config set OLLAMA_MODEL="llama3"
-aicommit2 config set OLLAMA_MODEL="llama3,codellama" # for multiple models
+aicommit2 config set OLLAMA.model="llama3.1"
+aicommit2 config set OLLAMA.model="llama3,codellama" # for multiple models
+
+aicommit2 config add OLLAMA.model="gemma2" # Only Ollama.model can be added.
 ```
 
-##### OLLAMA_HOST
+> OLLAMA.model is only **string array** type to support multiple Ollama. Please see [this section](#loading-multiple-ollama-models).
+
+##### OLLAMA.host
 
 Default: `http://localhost:11434`
 
 The Ollama host
 
 ```sh
-aicommit2 config set OLLAMA_HOST=<host>
+aicommit2 config set OLLAMA.host=<host>
 ```
 
-##### OLLAMA_TIMEOUT
+##### OLLAMA.timeout
 
 Default: `100_000` (100 seconds)
 
-Request timeout for the Ollama. Default OLLAMA_TIMEOUT is **100 seconds** because it can take a long time to run locally.
+Request timeout for the Ollama.
 
 ```sh
-aicommit2 config set OLLAMA_TIMEOUT=<timeout>
+aicommit2 config set OLLAMA.timeout=<timeout>
 ```
 
-### OPEN AI
+##### Unsupported Options
 
-##### OPENAI_KEY
+Ollama does not support the following options in General Settings.
+ 
+- maxTokens
 
-The OpenAI API key. You can retrieve it from [OpenAI API Keys page](https://platform.openai.com/account/api-keys).
+### HuggingFace
 
-##### OPENAI_MODEL
+| Setting            | Description                                                                                                      | Default                                |
+|--------------------|------------------------------------------------------------------------------------------------------------------|----------------------------------------|
+| `cookie`           | Authentication cookie                                                                                            | -                                      |
+| `model`            | Model to use                                                                                                     | `CohereForAI/c4ai-command-r-plus`      |
 
-Default: `gpt-3.5-turbo`
+##### HUGGINGFACE.cookie
 
-The Chat Completions (`/v1/chat/completions`) model to use. Consult the list of models available in the [OpenAI Documentation](https://platform.openai.com/docs/models/model-endpoint-compatibility).
+The [Huggingface Chat](https://huggingface.co/chat/) Cookie. Please check [how to get cookie](https://github.com/tak-bro/aicommit2?tab=readme-ov-file#how-to-get-cookieunofficial-api)
 
-> Tip: If you have access, try upgrading to [`gpt-4`](https://platform.openai.com/docs/models/gpt-4) for next-level code analysis. It can handle double the input size, but comes at a higher cost. Check out OpenAI's website to learn more.
+```sh
+# Please be cautious of Escape characters(\", \') in browser cookie string
+aicommit2 config set HUGGINGFACE.cookie="your-cooke"
+```
+
+##### HUGGINGFACE.model
+
+Default: `CohereForAI/c4ai-command-r-plus`
+
+Supported:
+- `CohereForAI/c4ai-command-r-plus`
+- `meta-llama/Meta-Llama-3-70B-Instruct`
+- `HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1`
+- `mistralai/Mixtral-8x7B-Instruct-v0.1`
+- `NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO`
+- `01-ai/Yi-1.5-34B-Chat`
+- `mistralai/Mistral-7B-Instruct-v0.2`
+- `microsoft/Phi-3-mini-4k-instruct`
 
 ```sh
-aicommit2 config set OPENAI_MODEL=gpt-4
+aicommit2 config set HUGGINGFACE.model="mistralai/Mistral-7B-Instruct-v0.2"
 ```
 
-##### OPENAI_URL
+##### Unsupported Options
 
-Default: `https://api.openai.com`
+Huggingface does not support the following options in General Settings.
 
-The OpenAI URL. Both https and http protocols supported. It allows to run local OpenAI-compatible server.
+- maxTokens
+- timeout
+- temperature
 
-##### OPENAI_PATH
+### Gemini
 
-Default: `/v1/chat/completions`
+| Setting            | Description                                                                                                      | Default           |
+|--------------------|------------------------------------------------------------------------------------------------------------------|-------------------|
+| `key`              | API key                                                                                                          | -                 |
+| `model`            | Model to use                                                                                                     | `gemini-1.5-pro`  |
 
-The OpenAI Path.
+##### GEMINI.key
 
-### Anthropic Claude
+The Gemini API key. If you don't have one, create a key in [Google AI Studio](https://aistudio.google.com/app/apikey).
+
+```sh
+aicommit2 config set GEMINI.key="your api key"
+```
 
-##### ANTHROPIC_KEY
+##### GEMINI.model
+
+Default: `gemini-1.5-pro`
+
+Supported:
+- `gemini-1.5-pro`
+- `gemini-1.5-flash`
+- `gemini-1.5-pro-exp-0801`
+
+```sh
+aicommit2 config set GEMINI.model="gemini-1.5-pro-exp-0801"
+```
+
+##### Unsupported Options
+
+Gemini does not support the following options in General Settings.
+
+- timeout
+
+### Anthropic
+
+| Setting     | Description    | Default                   |
+|-------------|----------------|---------------------------|
+| `key`       | API key        | -                         |
+| `model`     | Model to use   | `claude-3-haiku-20240307` |
+
+##### ANTHROPIC.key
 
 The Anthropic API key. To get started with Anthropic Claude, request access to their API at [anthropic.com/earlyaccess](https://www.anthropic.com/earlyaccess).
 
-##### ANTHROPIC_MODEL
+##### ANTHROPIC.model
 
 Default: `claude-3-haiku-20240307`
 
@@ -573,37 +555,30 @@ Supported:
 - `claude-3-haiku-20240307`
 - `claude-3-sonnet-20240229`
 - `claude-3-opus-20240229`
-- `claude-2.1`
-- `claude-2.0`
-- `claude-instant-1.2`
+- `claude-3-5-sonnet-20240620`
 
 ```sh
-aicommit2 config set ANTHROPIC_MODEL=claude-instant-1.2
+aicommit2 config set ANTHROPIC.model="claude-3-5-sonnet-20240620"
 ```
 
-### GEMINI
-
-##### GEMINI_KEY
+##### Unsupported Options
 
-The Gemini API key. If you don't have one, create a key in [Google AI Studio](https://aistudio.google.com/app/apikey).
-
-##### GEMINI_MODEL
+Anthropic does not support the following options in General Settings.
 
-Default: `gemini-1.5-pro-latest`
-
-Supported:
-- `gemini-1.5-pro-latest`
-- `gemini-1.5-flash-latest`
+- timeout
 
-> The models mentioned above are subject to change.
+### Mistral
 
-### MISTRAL
+| Setting            | Description                                                                                                      | Default        |
+|--------------------|------------------------------------------------------------------------------------------------------------------|----------------|
+| `key`              | API key                                                                                                          | -              |
+| `model`            | Model to use                                                                                                     | `mistral-tiny` |
 
-##### MISTRAL_KEY
+##### MISTRAL.key
 
 The Mistral API key. If you don't have one, please sign up and subscribe in [Mistral Console](https://console.mistral.ai/).
 
-##### MISTRAL_MODEL
+##### MISTRAL.model
 
 Default: `mistral-tiny`
 
@@ -623,15 +598,18 @@ Supported:
 - `mistral-large-2402`
 - `mistral-embed`
 
-> The models mentioned above are subject to change.
+### Codestral
 
-### CODESTRAL
+| Setting            | Description                                                                                                      | Default            |
+|--------------------|------------------------------------------------------------------------------------------------------------------|--------------------|
+| `key`              | API key                                                                                                          | -                  |
+| `model`            | Model to use                                                                                                     | `codestral-latest` |
 
-##### CODESTRAL_KEY
+##### CODESTRAL.key
 
 The Codestral API key. If you don't have one, please sign up and subscribe in [Mistral Console](https://console.mistral.ai/codestral).
 
-##### CODESTRAL_MODEL
+##### CODESTRAL.model
 
 Default: `codestral-latest`
 
@@ -639,67 +617,82 @@ Supported:
 - `codestral-latest`
 - `codestral-2405`
 
-> The models mentioned above are subject to change.
+```sh
+aicommit2 config set CODESTRAL.model="codestral-2405"
+```
 
-### Cohere
+#### Cohere
 
-##### COHERE_KEY
+| Setting            | Description                                                                                                      | Default     |
+|--------------------|------------------------------------------------------------------------------------------------------------------|-------------|
+| `key`              | API key                                                                                                          | -           |
+| `model`            | Model to use                                                                                                     | `command`   |
+
+##### COHERE.key
 
 The Cohere API key. If you don't have one, please sign up and get the API key in [Cohere Dashboard](https://dashboard.cohere.com/).
 
-##### COHERE_MODEL
+##### COHERE.model
 
 Default: `command`
 
-Supported:
+Supported models:
 - `command`
 - `command-nightly`
 - `command-light`
 - `command-light-nightly`
 
-> The models mentioned above are subject to change.
+```sh
+aicommit2 config set COHERE.model="command-nightly"
+```
+
+##### Unsupported Options
+
+Cohere does not support the following options in General Settings.
+
+- timeout
 
 ### Groq
 
-##### GROQ_KEY
+| Setting            | Description            | Default        |
+|--------------------|------------------------|----------------|
+| `key`              | API key                | -              |
+| `model`            | Model to use           | `gemma2-9b-it` |
+
+##### GROQ.key
 
 The Groq API key. If you don't have one, please sign up and get the API key in [Groq Console](https://console.groq.com).
 
-##### GROQ_MODEL
+##### GROQ.model
 
-Default: `gemma-7b-it`
+Default: `gemma2-9b-it`
 
 Supported:
-- `llama3-8b-8192`
-- `llama3-70b-8192`
-- `mixtral-8x7b-32768`
+- `gemma2-9b-it`
 - `gemma-7b-it`
+- `llama-3.1-70b-versatile`
+- `llama-3.1-8b-instant`
+- `llama3-70b-8192`
+- `llama3-8b-8192`
+- `llama3-groq-70b-8192-tool-use-preview`
+- `llama3-groq-8b-8192-tool-use-preview`
 
-> The models mentioned above are subject to change.
-
-### HuggingFace Chat
-
-##### HUGGINGFACE_COOKIE
-
-The [Huggingface Chat](https://huggingface.co/chat/) Cookie. Please check [how to get cookie](https://github.com/tak-bro/aicommit2?tab=readme-ov-file#how-to-get-cookieunofficial-api)
+```sh
+aicommit2 config set GROQ.model="llama3-8b-8192"
+```
 
-##### HUGGINGFACE_MODEL
+### Perplexity
 
-Default: `CohereForAI/c4ai-command-r-plus`
+| Setting            | Description      | Default                           |
+|--------------------|------------------|-----------------------------------|
+| `key`              | API key          | -                                 |
+| `model`            | Model to use     | `llama-3.1-sonar-small-128k-chat` |
 
-Supported:
-- `CohereForAI/c4ai-command-r-plus`
-- `meta-llama/Meta-Llama-3-70B-Instruct`
-- `HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1`
-- `mistralai/Mixtral-8x7B-Instruct-v0.1`
-- `NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO`
-- `01-ai/Yi-1.5-34B-Chat`
-- `mistralai/Mistral-7B-Instruct-v0.2`
-- `microsoft/Phi-3-mini-4k-instruct`
+##### PERPLEXITY.key
 
-> The models mentioned above are subject to change.
+The Perplexity API key. If you don't have one, please sign up and get the API key in [Perplexity](https://docs.perplexity.ai/)
 
-##### PERPLEXITY_MODEL
+##### PERPLEXITY.model
 
 Default: `llama-3.1-sonar-small-128k-chat`
 
@@ -715,6 +708,25 @@ Supported:
 
 > The models mentioned above are subject to change.
 
+```sh
+aicommit2 config set PERPLEXITY.model="llama-3.1-70b"
+```
+
+#### Usage
+
+1. Stage your files and commit:
+
+```sh
+git add <files...>
+git commit # Only generates a message when it's not passed in
+```
+
+> If you ever want to write your own message instead of generating one, you can simply pass one in: `git commit -m "My message"`
+
+2. _aicommit2_ will generate the commit message for you and pass it back to Git. Git will open it with the [configured editor](https://docs.github.com/en/get-started/getting-started-with-git/associating-text-editors-with-git) for you to review/edit it.
+
+3. Save and close the editor to commit!
+
 ## Upgrading
 
 Check the installed version with:
@@ -731,23 +743,29 @@ npm update -g aicommit2
 
 ## Custom Prompt Template
 
-_aicommit2_ supports custom prompt templates through the `promptPath` option. This feature allows you to define your own prompt structure, giving you more control over the commit message generation process.
+_aicommit2_ supports custom prompt templates through the `systemPromptPath` option. This feature allows you to define your own prompt structure, giving you more control over the commit message generation process.
 
-### Using the promptPath Option
+### Using the systemPromptPath Option
 To use a custom prompt template, specify the path to your template file when running the tool:
+
 ```
-aicommit2 config set promptPath="/path/to/user/prompt.txt"
+aicommit2 config set systemPromptPath="/path/to/user/prompt.txt"
+aicommit2 config set OPENAI.systemPromptPath="/path/to/another-prompt.txt"
 ```
 
+For the above command, OpenAI uses the prompt in the `another-prompt.txt` file, and the rest of the model uses `prompt.txt`.
+
+> **NOTE**: For the `systemPromptPath` option, set the **template path**, not the template content
+
 ### Template Format
 
 Your custom template can include placeholders for various commit options.
 Use curly braces `{}` to denote these placeholders for options. The following placeholders are supported:
 
-- [{locale}](#locale): The language for the commit message (string)
-- [{maxLength}](#max-length): The maximum length for the commit message (number)
-- [{type}](#type): The type of the commit (conventional or gitmoji)
-- [{generate}](#generate): The number of commit messages to generate (number)
+- [{locale}](#locale): The language for the commit message (**string**)
+- [{maxLength}](#max-length): The maximum length for the commit message (**number**)
+- [{type}](#type): The type of the commit message (**conventional** or **gitmoji**)
+- [{generate}](#generate): The number of commit messages to generate (**number**)
 
 ### Example Template
 
@@ -764,35 +782,31 @@ Remember to follow these guidelines:
 3. Explain the 'why' behind the change
 ```
 
-#### Appended Text
+### **Appended Text**
 
-Please note that the following text will always be appended to the end of your custom prompt:
+Please note that the following text will **always** be appended to the end of your custom prompt:
 
 ```
-Provide your response as a JSON array where each element is an object with "subject", "body", and "footer" keys.
-The "subject" should include the type, optional scope, and description . If there's no body or footer, use an empty string for those fields.
-Example response format:
+Provide your response as a JSON array containing exactly 1 object, each with the following keys:
+- "subject": The main commit message using the conventional style. It should be a concise summary of the changes.
+- "body": An optional detailed explanation of the changes. If not needed, use an empty string.
+- "footer": An optional footer for metadata like BREAKING CHANGES. If not needed, use an empty string.
+The array must always contain 1 element, no more and no less.
+Example response format: 
 [
   {
-    "subject": "string",
-    "body": "string",
-    "footer": "string"
-  },
-  ...
+    "subject": "fix: fix bug in user authentication process",
+    "body": "- Update login function to handle edge cases\n- Add additional error logging for debugging",
+    "footer": ""
+  }
 ]
+Ensure you generate exactly 1 commit message, even if it requires creating slightly varied versions for similar changes.
+The response should be valid JSON that can be parsed without errors.
 ```
 
 This ensures that the output is consistently formatted as a JSON array, regardless of the custom template used.
 
-### Notes
-
-If the specified file cannot be read or parsed, _aicommit2_ will fall back to using the default prompt generation logic.
-Ensure your template includes all necessary instructions for generating appropriate commit messages.
-You can still use all other command-line options in conjunction with `promptPath`.
-
-By using custom templates, you can tailor the commit message generation to your team's specific needs or coding standards.
-
-> NOTE: For the `promptPath` option, set the **template path**, not the template content
+> NOTE: The template may vary depending on the generate and commit message type.
 
 ## Loading Multiple Ollama Models
 
@@ -817,10 +831,10 @@ OLLAMA_MAX_LOADED_MODELS=3 ollama serve
 
 ##### 2. Configuring _aicommit2_
 
-Next, set up _aicommit2_ to specify multiple models. You can assign a list of models, separated by **commas(`,`)**, to the OLLAMA_MODEL environment variable. Here's how you do it:
+Next, set up _aicommit2_ to specify multiple models. You can assign a list of models, separated by **commas(`,`)**, to the OLLAMA.model environment variable. Here's how you do it:
 
 ```shell
-aicommit2 config set OLLAMA_MODEL="mistral,dolphin-llama3"
+aicommit2 config set OLLAMA.model="mistral,dolphin-llama3"
 ```
 
 With this command, _aicommit2_ is instructed to utilize both the "mistral" and "dolphin-llama3" models when making requests to the Ollama server.
@@ -833,7 +847,6 @@ aicommit2
 
 > Note that this feature is available starting from Ollama version [**0.1.33**](https://github.com/ollama/ollama/releases/tag/v0.1.33) and _aicommit2_ version [**1.9.5**](https://www.npmjs.com/package/aicommit2/v/1.9.5).
 
-
 ## How to get Cookie(**Unofficial API**)
 
 * Login to the site you want
@@ -847,26 +860,13 @@ aicommit2
 
 ![how-to-get-cookie](https://github.com/tak-bro/aicommit2/assets/7614353/66f2994d-23d9-4c88-a113-f2d3dc5c0669)
 
-## Disclaimer
-
-This project utilizes certain functionalities or data from external APIs, but it is important to note that it is not officially affiliated with or endorsed by the providers of those APIs. The use of external APIs is at the sole discretion and risk of the user.
-
-## Risk Acknowledgment
+## Disclaimer and Risks
 
-Users are responsible for understanding and abiding by the terms of use, rate limits, and policies set forth by the respective API providers. The project maintainers cannot be held responsible for any misuse, downtime, or issues arising from the use of the external APIs.
-
-It is recommended that users thoroughly review the API documentation and adhere to best practices to ensure a positive and compliant experience.
-
-## Please Star ⭐️
-If this project has been helpful to you, I would greatly appreciate it if you could click the Star⭐️ button on this repository!
-
-## Maintainers
-
-- [@tak-bro](https://env-tak.github.io/)
+This project uses functionalities from external APIs but is not officially affiliated with or endorsed by their providers. Users are responsible for complying with API terms, rate limits, and policies.
 
 ## Contributing
 
-If you want to help fix a bug or implement a feature in [Issues](https://github.com/tak-bro/aicommit2/issues), checkout the [Contribution Guide](CONTRIBUTING.md) to learn how to setup and test the project.
+For bug fixes or feature implementations, please check the [Contribution Guide](CONTRIBUTING.md).
 
 ## Contributors ✨
 
@@ -880,8 +880,15 @@ Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/d
     <td align="center"><a href="https://github.com/eltociear"><img src="https://avatars.githubusercontent.com/eltociear" width="100px;" alt=""/><br /><sub><b>@eltociear</b></sub></a><br /><a href="https://github.com/tak-bro/aicommit2/commits?author=eltociear" title="Documentation">📖</a></td>
     <td align="center"><a href="https://github.com/ubranch"><img src="https://avatars.githubusercontent.com/ubranch" width="100px;" alt=""/><br /><sub><b>@ubranch</b></sub></a><br /><a href="https://github.com/tak-bro/aicommit2/commits?author=ubranch" title="Code">💻</a></td>
     <td align="center"><a href="https://github.com/bhodrolok"><img src="https://avatars.githubusercontent.com/bhodrolok" width="100px;" alt=""/><br /><sub><b>@bhodrolok</b></sub></a><br /><a href="https://github.com/tak-bro/aicommit2/commits?author=bhodrolok" title="Code">💻</a></td>
+    <td align="center"><a href="https://github.com/ryicoh"><img src="https://avatars.githubusercontent.com/ryicoh" width="100px;" alt=""/><br /><sub><b>@ryicoh</b></sub></a><br /><a href="https://github.com/tak-bro/aicommit2/commits?author=ryicoh" title="Code">💻</a></td>
   </tr>
 </table>
 <!-- markdownlint-restore -->
 <!-- prettier-ignore-end -->
 <!-- ALL-CONTRIBUTORS-LIST:END -->
+
+---
+
+If this project has been helpful, please consider giving it a Star ⭐️!
+
+Maintainer: [@tak-bro](https://env-tak.github.io/)