aicommit2 2.2.0 → 2.2.2

package/README.md

@@ -25,16 +25,14 @@ _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 and more.
-- **Local Model Support**: Use local AI models via Ollama.
+- **Multi-AI Support**: Integrates with OpenAI, Anthropic Claude, Google Gemini, Mistral AI, Cohere, Groq, Ollama and more.
+- **OpenAI API Compatibility**: Support for any service that implements the OpenAI API specification.
 - **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 Prompt**: Supports user-defined system prompt templates.
 
 ## Supported Providers
 
-### Remote
-
 - [OpenAI](https://openai.com/)
 - [Anthropic Claude](https://console.anthropic.com/)
 - [Gemini](https://gemini.google.com/)
@@ -44,10 +42,8 @@ _aicommit2_ is a reactive CLI tool that automatically generates Git commit messa
 - [Perplexity](https://docs.perplexity.ai/)
 - [DeepSeek](https://www.deepseek.com/)
 - [Huggingface **(Unofficial)**](https://huggingface.co/chat/)
-
-### Local
-
 - [Ollama](https://ollama.com/)
+- [OpenAI API Compatibility](#openai-api-compatible-services)
 
 ## Setup
 
@@ -86,7 +82,7 @@ You can also use your model for free with [Ollama](https://ollama.com/) and it i
 ollama run llama3.2 # model you want use. ex) codellama, deepseek-coder
 ```
 
-3. Set the host, model and numCtx. (The default numCtx value in Ollama is 2048. It is recommended to set it to 4096 or higher.)
+3. Set the host, model and numCtx. (The default numCtx value in Ollama is 2048. It is recommended to set it to `4096` or higher.)
 ```sh
 aicommit2 config set OLLAMA.host=<your host>
 aicommit2 config set OLLAMA.model=<your model>
@@ -435,19 +431,20 @@ aicommit2 config set codeReviewPromptPath="/path/to/user/prompt.txt"
 ```
 
 ## Available General Settings by Model
-|                      | timeout | temperature | maxTokens |  topP  |
-|:--------------------:|:-------:|:-----------:|:---------:|:------:|
-|      **OpenAI**      |    ✓    |      ✓      |     ✓     |   ✓    |
-| **Anthropic Claude** |         |      ✓      |     ✓     |   ✓    |
-|      **Gemini**      |         |      ✓      |     ✓     |   ✓    |
-|    **Mistral AI**    |    ✓    |      ✓      |     ✓     |   ✓    |
-|    **Codestral**     |    ✓    |      ✓      |     ✓     |   ✓    |
-|      **Cohere**      |         |      ✓      |     ✓     |   ✓    |
-|       **Groq**       |    ✓    |      ✓      |     ✓     |   ✓    |
-|    **Perplexity**    |    ✓    |      ✓      |     ✓     |   ✓    |
-|     **DeepSeek**     |    ✓    |      ✓      |     ✓     |   ✓    |
-|   **Huggingface**    |         |             |           |        |
-|      **Ollama**      |    ✓    |      ✓      |           |   ✓    |
+|                             | timeout | temperature | maxTokens |  topP  |
+|:---------------------------:|:-------:|:-----------:|:---------:|:------:|
+|         **OpenAI**          |    ✓    |      ✓      |     ✓     |   ✓    |
+|    **Anthropic Claude**     |         |      ✓      |     ✓     |   ✓    |
+|         **Gemini**          |         |      ✓      |     ✓     |   ✓    |
+|       **Mistral AI**        |    ✓    |      ✓      |     ✓     |   ✓    |
+|        **Codestral**        |    ✓    |      ✓      |     ✓     |   ✓    |
+|         **Cohere**          |         |      ✓      |     ✓     |   ✓    |
+|          **Groq**           |    ✓    |      ✓      |     ✓     |   ✓    |
+|       **Perplexity**        |    ✓    |      ✓      |     ✓     |   ✓    |
+|        **DeepSeek**         |    ✓    |      ✓      |     ✓     |   ✓    |
+|       **Huggingface**       |         |             |           |        |
+|         **Ollama**          |    ✓    |      ✓      |           |   ✓    |
+| **OpenAI API-Compatible**   |    ✓    |      ✓      |     ✓     |   ✓    |
 
 > All AI support the following options in General Settings.
 > - systemPrompt, systemPromptPath, codeReview, codeReviewPromptPath, exclude, type, locale, generate, logging, includeBody, maxLength
@@ -514,10 +511,10 @@ aicommit2 config set OPENAI.topP=0.2
 
 ### Anthropic
 
-| Setting     | Description    | Default                   |
-|-------------|----------------|---------------------------|
-| `key`       | API key        | -                         |
-| `model`     | Model to use   | `claude-3-haiku-20240307` |
+| Setting     | Description    | Default                     |
+|-------------|----------------|-----------------------------|
+| `key`       | API key        | -                           | 
+| `model`     | Model to use   | `claude-3-5-haiku-20241022` |
 
 ##### ANTHROPIC.key
 
@@ -525,14 +522,14 @@ The Anthropic API key. To get started with Anthropic Claude, request access to t
 
 ##### ANTHROPIC.model
 
-Default: `claude-3-haiku-20240307`
+Default: `claude-3-5-haiku-20241022`
 
 Supported:
-- `claude-3-haiku-20240307`
-- `claude-3-sonnet-20240229`
-- `claude-3-opus-20240229`
-- `claude-3-5-sonnet-20240620`
 - `claude-3-5-sonnet-20241022`
+- `claude-3-5-haiku-20241022`
+- `claude-3-opus-20240229`
+- `claude-3-sonnet-20240229`
+- `claude-3-haiku-20240307`
 
 ```sh
 aicommit2 config set ANTHROPIC.model="claude-3-5-sonnet-20240620"
@@ -546,10 +543,10 @@ Anthropic does not support the following options in General Settings.
 
 ### Gemini
 
-| Setting            | Description            | Default           |
-|--------------------|------------------------|-------------------|
-| `key`              | API key                | -                 |
-| `model`            | Model to use           | `gemini-1.5-pro`  |
+| Setting            | Description            | Default                |
+|--------------------|------------------------|------------------------|
+| `key`              | API key                | -                      |
+| `model`            | Model to use           | `gemini-2.0-flash-exp` |
 
 ##### GEMINI.key
 
@@ -561,15 +558,16 @@ aicommit2 config set GEMINI.key="your api key"
 
 ##### GEMINI.model
 
-Default: `gemini-1.5-pro`
+Default: `gemini-2.0-flash-exp`
 
 Supported:
-- `gemini-1.5-pro`
+- `gemini-2.0-flash-exp`
 - `gemini-1.5-flash`
-- `gemini-1.5-pro-exp-0801`
+- `gemini-1.5-flash-8b`
+- `gemini-1.5-pro`
 
 ```sh
-aicommit2 config set GEMINI.model="gemini-1.5-pro-exp-0801"
+aicommit2 config set GEMINI.model="gemini-1.5-flash"
 ```
 
 ##### Unsupported Options
@@ -580,10 +578,10 @@ Gemini does not support the following options in General Settings.
 
 ### Mistral
 
-| Setting  | Description      | Default        |
-|----------|------------------|----------------|
-| `key`    | API key          | -              |
-| `model`  | Model to use     | `mistral-tiny` |
+| Setting  | Description      | Default            |
+|----------|------------------|--------------------|
+| `key`    | API key          | -                  |
+| `model`  | Model to use     | `pixtral-12b-2409` |
 
 ##### MISTRAL.key
 
@@ -591,23 +589,16 @@ The Mistral API key. If you don't have one, please sign up and subscribe in [Mis
 
 ##### MISTRAL.model
 
-Default: `mistral-tiny`
+Default: `pixtral-12b-2409`
 
 Supported:
-- `open-mistral-7b`
-- `mistral-tiny-2312`
-- `mistral-tiny`
-- `open-mixtral-8x7b`
-- `mistral-small-2312`
-- `mistral-small`
-- `mistral-small-2402`
-- `mistral-small-latest`
-- `mistral-medium-latest`
-- `mistral-medium-2312`
-- `mistral-medium`
+- `codestral-latest`
 - `mistral-large-latest`
-- `mistral-large-2402`
+- `pixtral-large-latest`
+- `ministral-8b-latest`
+- `mistral-small-latest`
 - `mistral-embed`
+- `mistral-moderation-latest`
 
 ### Codestral
 
@@ -626,10 +617,10 @@ Default: `codestral-latest`
 
 Supported:
 - `codestral-latest`
-- `codestral-2405`
+- `codestral-2501`
 
 ```sh
-aicommit2 config set CODESTRAL.model="codestral-2405"
+aicommit2 config set CODESTRAL.model="codestral-2501"
 ```
 
 ### Cohere
@@ -648,10 +639,19 @@ The Cohere API key. If you don't have one, please sign up and get the API key in
 Default: `command`
 
 Supported models:
+- `command-r7b-12-2024`
+- `command-r-plus-08-2024`
+- `command-r-plus-04-2024`
+- `command-r-plus`
+- `command-r-08-2024`
+- `command-r-03-2024`
+- `command-r`
 - `command`
 - `command-nightly`
 - `command-light`
 - `command-light-nightly`
+- `c4ai-aya-expanse-8b`
+- `c4ai-aya-expanse-32b`
 
 ```sh
 aicommit2 config set COHERE.model="command-nightly"
@@ -706,10 +706,10 @@ aicommit2 config set GROQ.model="llama3-8b-8192"
 
 ### Perplexity
 
-| Setting  | Description      | Default                           |
-|----------|------------------|-----------------------------------|
-| `key`    | API key          | -                                 |
-| `model`  | Model to use     | `llama-3.1-sonar-small-128k-chat` |
+| Setting  | Description      | Default  |
+|----------|------------------|----------|
+| `key`    | API key          | -        |
+| `model`  | Model to use     | `sonar`  |
 
 ##### PERPLEXITY.key
 
@@ -717,22 +717,19 @@ The Perplexity API key. If you don't have one, please sign up and get the API ke
 
 ##### PERPLEXITY.model
 
-Default: `llama-3.1-sonar-small-128k-chat`
+Default: `sonar`
 
 Supported:
-- `llama-3.1-sonar-small-128k-chat`
-- `llama-3.1-sonar-large-128k-chat`
-- `llama-3.1-sonar-large-128k-online`
+- `sonar-pro`
+- `sonar`
 - `llama-3.1-sonar-small-128k-online`
-- `llama-3.1-8b-instruct`
-- `llama-3.1-70b-instruct`
-- `llama-3.1-8b`
-- `llama-3.1-70b`
+- `llama-3.1-sonar-large-128k-online`
+- `llama-3.1-sonar-huge-128k-online`
 
 > The models mentioned above are subject to change.
 
 ```sh
-aicommit2 config set PERPLEXITY.model="llama-3.1-70b"
+aicommit2 config set PERPLEXITY.model="sonar-pro"
 ```
 
 ### DeepSeek
@@ -740,7 +737,7 @@ aicommit2 config set PERPLEXITY.model="llama-3.1-70b"
 | Setting | Description      | Default            |
 |---------|------------------|--------------------|
 | `key`   | API key          | -                  |
-| `model` | Model to use     | `deepseek-coder`   |
+| `model` | Model to use     | `deepseek-chat`    |
 
 ##### DEEPSEEK.key
 
@@ -748,14 +745,14 @@ The DeepSeek API key. If you don't have one, please sign up and subscribe in [De
 
 ##### DEEPSEEK.model
 
-Default: `deepseek-coder`
+Default: `deepseek-chat`
 
 Supported:
-- `deepseek-coder`
 - `deepseek-chat`
+- `deepseek-reasoner`
 
 ```sh
-aicommit2 config set DEEPSEEK.model="deepseek-chat"
+aicommit2 config set DEEPSEEK.model="deepseek-reasoner"
 ```
 
 ### HuggingFace
@@ -803,13 +800,14 @@ Huggingface does not support the following options in General Settings.
 
 ### Ollama
 
-| Setting   | Description                            | Default                |
-|-----------|----------------------------------------|------------------------|
-| `model`   | Model(s) to use (comma-separated list) | -                      |
-| `host`    | Ollama host URL                        | http://localhost:11434 |
-| `auth`    | Authentication type                    | Bearer                 |
-| `key`     | Authentication key                     | -                      |
-| `timeout` | Request timeout (milliseconds)         | 100_000 (100sec)       |
+| Setting    | Description                                                 | Default                |
+|------------|-------------------------------------------------------------|------------------------|
+| `model`    | Model(s) to use (comma-separated list)                      | -                      |
+| `host`     | Ollama host URL                                             | http://localhost:11434 |
+| `auth`     | Authentication type                                         | Bearer                 |
+| `key`      | Authentication key                                          | -                      |
+| `timeout`  | Request timeout (milliseconds)                              | 100_000 (100sec)       |
+| `numCtx`   | The maximum number of tokens the model can process at once  | 2048                   |
 
 ##### OLLAMA.model
 
@@ -851,6 +849,7 @@ aicommit2 config set OLLAMA.key=<key>
 ```
 
 Few examples of authentication methods:
+
 | **Authentication Method** | **OLLAMA.auth**              | **OLLAMA.key**                        |
 |---------------------------|------------------------------|---------------------------------------|
 | Bearer                    | `Bearer`                     | `<API key>`                           |
@@ -869,12 +868,64 @@ Request timeout for the Ollama.
 aicommit2 config set OLLAMA.timeout=<timeout>
 ```
 
+##### OLLAMA.numCtx
+
+The maximum number of tokens the model can process at once, determining its context length and memory usage.
+It is recommended to set it to 4096 or higher.
+
+```sh
+aicommit2 config set OLLAMA.numCtx=4096
+```
+
 ##### Unsupported Options
 
 Ollama does not support the following options in General Settings.
 
 - maxTokens
 
+### OpenAI API-Compatible Services
+
+You can configure any OpenAI API-compatible service by adding a configuration section with the `compatible=true` option. This allows you to use services that implement the OpenAI API specification.
+
+```sh
+# together
+aicommit2 config set TOGETHER.compatible=true
+aicommit2 config set TOGETHER.url=https://api.together.xyz
+aicommit2 config set TOGETHER.path=/v1
+aicommit2 config set TOGETHER.model=meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
+aicommit2 config set TOGETHER.key="your-api-key"
+```
+
+| Setting      | Description                            | Required             | Default |
+|--------------|----------------------------------------|----------------------|---------|
+| `compatible` | Enable OpenAI API compatibility mode   | ✓ (**must be true**) | false   |
+| `url`        | Base URL of the API endpoint           | ✓                    | -       |
+| `path`       | API path for chat completions          |                      | -       |
+| `key`        | API key for authentication             | ✓                    | -       |
+| `model`      | Model identifier to use                | ✓                    | -       |
+
+Example configuration:
+```ini
+[TOGETHER]
+compatible=true
+key=<your-api-key>
+url=https://api.together.xyz/v1
+model=meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
+
+[GEMINI_COMPATIBILITY]
+compatible=true
+key=<your-api-key>
+url=https://generativelanguage.googleapis.com
+path=/v1beta/openai/
+model=gemini-1.5-flash
+
+[OLLAMA_COMPATIBILITY]
+compatible=true
+key=ollama
+url=http://localhost:11434/v1
+model=llama3.2
+```
+
 ## Watch Commit Mode
 
 ![watch-commit-gif](https://github.com/tak-bro/aicommit2/blob/main/img/watch-commit-min.gif?raw=true)