### Install Python Dependencies (Bash)

Source: https://github.com/fasuizu-br/dify-brainiall-plugin/blob/main/GUIDE.md

This command installs all Python dependencies listed in the `requirements.txt` file. Ensure you have Python 3.11+ installed.

```bash
pip install -r requirements.txt
```

--------------------------------

### Initialize and Run Dify Plugin

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

This Python script demonstrates the entry point for the Dify Brainiall plugin. It initializes the Plugin class with custom request timeout settings and then runs the plugin. This is essential for starting the plugin's operations within the Dify environment.

```python
# Plugin entry point (main.py)
from dify_plugin import Plugin, DifyPluginEnv

plugin = Plugin(DifyPluginEnv(MAX_REQUEST_TIMEOUT=120))

if __name__ == "__main__":
    plugin.run()
```

--------------------------------

### Credential Validation and Usage Example for Brainiall

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

This Python code snippet shows how to validate credentials for a specific model using the Brainiall provider. It includes a usage example demonstrating the expected structure for the credentials dictionary, which requires a 'brainiall_api_key' and 'mode'.

```python
# Validate credentials for a specific model
def validate_credentials(self, model: str, credentials: dict) -> None:
    self._add_custom_parameters(credentials)
    super().validate_credentials(model, credentials)

# Usage example - credentials structure
credentials = {
    "brainiall_api_key": "your-api-key-here",
    "mode": "chat",
}
```

--------------------------------

### Interact with Brainiall API using cURL

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

This example shows how to make a direct API call to the Brainiall service using cURL. It demonstrates sending a chat completion request with specific model parameters, messages, and authentication details. The `stream: true` option indicates that the response should be streamed.

```bash
# Direct API call using curl
curl -X POST "https://apim-ai-apis.azure-api.net/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_BRAINIALL_API_KEY" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello, how are you?"}
    ],
    "temperature": 0.7,
    "max_tokens": 4096,
    "stream": true
  }'
```

--------------------------------

### Dify Plugin Manifest Structure (YAML)

Source: https://github.com/fasuizu-br/dify-brainiall-plugin/blob/main/GUIDE.md

The `manifest.yaml` file describes a Dify plugin's metadata, type, author, resources, and extensions. It's crucial for defining the plugin's capabilities and how it integrates with Dify.

```yaml
version: "1.0.0"
type: "plugin"
author: "Your Organization"
label:
  en: "My Awesome Plugin"
  zh: "我的超棒插件"
created_at: "2023-10-27T10:00:00Z"
icon: "icon.png"
resource:
  memory: 512
  permission:
    tool:
      enabled: true
    model:
      enabled: true
      llm: true
      text_embedding: true
      rerank: true
      tts: true
      speech2text: true
      moderation: true
    node:
      enabled: true
    endpoint:
      enabled: true
    app:
      enabled: true
    storage:
      enabled: true
      size: 1073741824
plugins:
  tools: []
  models: []
  endpoints: []
meta:
  version: "0.0.1"
  arch: ["amd64", "arm64"]
  runner:
    language: "python"
    version: "3.12"
    entrypoint: "main"
```

--------------------------------

### Configure DeepSeek R1 Model (YAML)

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

Specifies the configuration for the DeepSeek R1 model, detailing its identifier, display label, model type, supported features, operational mode, context size, parameter rules, and pricing details. This setup is for reasoning and general tasks.

```yaml
# DeepSeek R1 configuration (models/llm/deepseek-r1.yaml)
model: deepseek-r1
label:
  en_US: DeepSeek R1
model_type: llm
features:
  - agent-thought
model_properties:
  mode: chat
  context_size: 128000
parameter_rules:
  - name: temperature
    use_template: temperature
  - name: top_p
    use_template: top_p
  - name: max_tokens
    use_template: max_tokens
    default: 4096
    min: 1
    max: 64000
pricing:
  input: "1.35"
  output: "5.40"
  unit: "0.000001"
  currency: USD

```

--------------------------------

### Plugin Entry Point

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

Initialize and run the Dify plugin with custom timeout settings.

```APIDOC
## Plugin Entry Point

### Description
Initialize and run the Dify plugin with custom timeout settings.

### Method
N/A (Script Execution)

### Endpoint
N/A (Script Execution)

### Code Example
```python
# Plugin entry point (main.py)
from dify_plugin import Plugin, DifyPluginEnv

plugin = Plugin(DifyPluginEnv(MAX_REQUEST_TIMEOUT=120))

if __name__ == "__main__":
    plugin.run()
```
```

--------------------------------

### Available Models Reference

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

Reference table for available models, including their context size and pricing information.

```APIDOC
## Available Models Reference

### Description
Reference table for available models, including their context size and pricing information.

### Models
| Model | Context Size | Input/Output Pricing ($/MTok) |
|-------|-------------|-------------------------------|
| claude-opus-4-6 | 200K | $5 / $25 |
| claude-sonnet-4-6 | 200K | $3 / $15 |
| claude-haiku-4-5 | 200K | $1 / $5 |
| claude-opus-4-5 | 200K | $15 / $75 |
| deepseek-r1 | 128K | $1.35 / $5.40 |
| deepseek-v3 | 128K | $0.27 / $1.10 |
| llama-3.3-70b | 128K | $0.72 / $0.72 |
| llama-4-scout-17b | 512K | $0.17 / $0.17 |
| qwen-3-235b | 128K | $0.80 / $2.40 |
| mistral-large-3 | 128K | $2 / $6 |
| nova-pro | 300K | $0.80 / $3.20 |
| nova-micro | 128K | $0.035 / $0.14 |
```

--------------------------------

### Define Provider Schema (YAML)

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

This YAML configuration outlines the structure for defining a provider within the system. It includes specifications for credential forms and references to the models that the provider supports, enabling the system to manage and utilize various AI services.

```yaml
# Provider YAML Configuration
# Define the provider schema with credential forms and model references.

```

--------------------------------

### Generate Customizable LLM Model Schema (Python)

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

Defines a Python function to dynamically create an AIModelEntity for customizable LLM models. It configures features like tool calling based on credentials and sets parameters such as context size, mode, temperature, max tokens, and top_p. This function is essential for integrating flexible LLM models into the system.

```python
from dify_plugin.entities.model import (
    AIModelEntity, FetchFrom, I18nObject, ModelFeature,
    ModelPropertyKey, ModelType, ParameterRule, ParameterType,
)
from dify_plugin.entities.model.llm import LLMMode

def get_customizable_model_schema(
    self, model: str, credentials: dict
) -> Optional[AIModelEntity]:
    return AIModelEntity(
        model=model,
        label=I18nObject(en_US=model, zh_Hans=model),
        model_type=ModelType.LLM,
        features=(
            [
                ModelFeature.TOOL_CALL,
                ModelFeature.MULTI_TOOL_CALL,
                ModelFeature.STREAM_TOOL_CALL,
            ]
            if credentials.get("function_calling_type") == "tool_call"
            else []
        ),
        fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
        model_properties={
            ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size", 8000)),
            ModelPropertyKey.MODE: LLMMode.CHAT.value,
        },
        parameter_rules=[
            ParameterRule(
                name="temperature",
                use_template="temperature",
                label=I18nObject(en_US="Temperature", zh_Hans="温度"),
                type=ParameterType.FLOAT,
            ),
            ParameterRule(
                name="max_tokens",
                use_template="max_tokens",
                default=4096,
                min=1,
                max=int(credentials.get("max_tokens", 16384)),
                label=I18nObject(en_US="Max Tokens", zh_Hans="最大标记"),
                type=ParameterType.INT,
            ),
            ParameterRule(
                name="top_p",
                use_template="top_p",
                label=I18nObject(en_US="Top P", zh_Hans="Top P"),
                type=ParameterType.FLOAT,
            ),
        ],
    )

```

--------------------------------

### Provider Configuration

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

Configuration details for the Brainiall provider, including supported model types, configuration methods, and schema for model and provider credentials.

```APIDOC
## Provider Configuration (provider/brainiall.yaml)

### Provider Details
- **Provider**: `brainiall`
- **Label**: `Brainiall` (en_US)
- **Supported Model Types**: `llm`
- **Configuration Methods**: `predefined-model`, `customizable-model`

### Model Credential Schema
- **Model Name**:
  - Label: `Model Name` (en_US)
  - Placeholder: `Enter your model name` (en_US)
- **Credential Form Schemas**:
  - **`brainiall_api_key`**:
    - Label: `API Key` (en_US)
    - Type: `secret-input`
    - Required: `true`
  - **`context_size`**:
    - Label: `Model context size` (en_US)
    - Default: `4096`
    - Required: `true`
    - Type: `text-input`
  - **`max_tokens`**:
    - Label: `Upper bound for max tokens` (en_US)
    - Default: `4096`
    - Type: `text-input`
  - **`function_calling_type`**:
    - Label: `Function calling` (en_US)
    - Default: `no_call`
    - Type: `select`
    - Options:
      - Label: `Not Support` (en_US), Value: `no_call`
      - Label: `Support` (en_US), Value: `tool_call`

### Provider Credential Schema
- **Credential Form Schemas**:
  - **`brainiall_api_key`**:
    - Label: `API Key` (en_US)
    - Type: `secret-input`
    - Required: `true`
```

--------------------------------

### OpenAI-Compatible API Usage

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

Access models through the standard OpenAI API format using cURL for direct API calls.

```APIDOC
## OpenAI-Compatible API Usage

### Description
Access models through the standard OpenAI API format.

### Method
`POST`

### Endpoint
`https://apim-ai-apis.azure-api.net/v1/chat/completions`

### Parameters
#### Headers
- **Content-Type** (`string`): `application/json`
- **Authorization** (`string`): `Bearer YOUR_BRAINIALL_API_KEY`

#### Request Body
- **model** (`string`): The name of the model to use (e.g., `claude-sonnet-4-6`).
- **messages** (`array`): An array of message objects representing the conversation history.
  - **role** (`string`): The role of the message sender (`system`, `user`, `assistant`).
  - **content** (`string`): The content of the message.
- **temperature** (`number`, optional): Controls randomness. Lower values make output more focused and deterministic.
- **max_tokens** (`integer`, optional): The maximum number of tokens to generate in the completion.
- **stream** (`boolean`, optional): Whether to stream back partial message deltas as they are generated.

### Request Example
```bash
curl -X POST "https://apim-ai-apis.azure-api.net/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_BRAINIALL_API_KEY" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello, how are you?"}
    ],
    "temperature": 0.7,
    "max_tokens": 4096,
    "stream": true
  }'
```

### Response
#### Success Response (200)
- **id** (`string`): Unique identifier for the completion.
- **object** (`string`): Type of object returned (e.g., `chat.completion`).
- **created** (`integer`): Unix timestamp of creation.
- **model** (`string`): The model used for the completion.
- **choices** (`array`): A list of completion choices.
  - **index** (`integer`): Index of the choice.
  - **message** (`object`):
    - **role** (`string`): Role of the message sender.
    - **content** (`string`): The content of the message.
  - **finish_reason** (`string`): The reason the model stopped generating tokens.
- **usage** (`object`):
  - **prompt_tokens** (`integer`): Number of tokens in the prompt.
  - **completion_tokens** (`integer`): Number of tokens in the completion.
  - **total_tokens** (`integer`): Total tokens used.

#### Response Example
```json
{
  "id": "chatcmpl-12345",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "claude-sonnet-4-6",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "I am doing well, thank you! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}
```
```

--------------------------------

### Configure Llama 4 Scout 17B Model with Vision (YAML)

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

This YAML configuration defines the Llama 4 Scout 17B model, highlighting its multimodal vision capabilities. It includes settings for its label, type, features, context size, parameter rules for temperature and max tokens, and associated pricing information.

```yaml
# Llama 4 Scout with vision (models/llm/llama-4-scout-17b.yaml)
model: llama-4-scout-17b
label:
  en_US: Llama 4 Scout 17B
model_type: llm
features:
  - agent-thought
  - vision
model_properties:
  mode: chat
  context_size: 512000
parameter_rules:
  - name: temperature
    use_template: temperature
  - name: max_tokens
    default: 4096
    min: 1
    max: 8192
pricing:
  input: "0.17"
  output: "0.17"
  unit: "0.000001"
  currency: USD

```

--------------------------------

### Configure Brainiall Provider

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

This YAML configuration defines the Brainiall provider for Dify, specifying supported model types, configuration methods, and schemas for both model and provider credentials. It includes fields for API keys, context size, max tokens, and function calling support.

```yaml
provider: brainiall
label:
  en_US: Brainiall
supported_model_types:
  - llm
configurate_methods:
  - predefined-model
  - customizable-model
model_credential_schema:
  model:
    label:
      en_US: Model Name
    placeholder:
      en_US: Enter your model name
  credential_form_schemas:
    - variable: brainiall_api_key
      label:
        en_US: API Key
      type: secret-input
      required: true
    - variable: context_size
      default: "4096"
      label:
        en_US: Model context size
      required: true
      type: text-input
    - variable: max_tokens
      default: "4096"
      label:
        en_US: Upper bound for max tokens
      type: text-input
    - variable: function_calling_type
      default: no_call
      label:
        en_US: Function calling
      options:
        - label:
            en_US: Not Support
          value: no_call
        - label:
            en_US: Support
          value: tool_call
      type: select
provider_credential_schema:
  credential_form_schemas:
    - variable: brainiall_api_key
      label:
        en_US: API Key
      type: secret-input
      required: true
```

--------------------------------

### Validate Brainiall Provider Credentials in Python

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

This Python code snippet demonstrates how to validate Brainiall provider credentials within a Dify plugin. It uses the ModelProvider class and raises a CredentialsValidateFailedError if the API key or other required parameters are missing or invalid.

```python
from dify_plugin import ModelProvider
from dify_plugin.errors.model import CredentialsValidateFailedError
from typing import Mapping

class BrainiallModelProvider(ModelProvider):
    def validate_provider_credentials(self, credentials: Mapping) -> None:
        """
        Validate provider credentials.
        If validation fails, raise CredentialsValidateFailedError.
        """
        try:
            model_instance = self.get_model_instance("llm")
            model_instance.validate_credentials(
                model="deepseek-v3",
                credentials={
                    "brainiall_api_key": credentials["brainiall_api_key"],
                    "mode": "chat",
                },
            )
        except CredentialsValidateFailedError as ex:
            raise ex
```

--------------------------------

### Configure Claude Sonnet 4.6 Model (YAML)

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

Defines the configuration for the Claude Sonnet 4.6 model, including its label, type, features (vision support), model properties (context size, mode), parameter rules, and pricing. This YAML file enables the integration and specific usage of this model.

```yaml
# Example: Claude Sonnet 4.6 with vision support (models/llm/claude-sonnet-4-6.yaml)
model: claude-sonnet-4-6
label:
  en_US: Claude Sonnet 4.6
model_type: llm
features:
  - agent-thought
  - vision
model_properties:
  mode: chat
  context_size: 200000
parameter_rules:
  - name: temperature
    use_template: temperature
  - name: top_p
    use_template: top_p
  - name: max_tokens
    use_template: max_tokens
    default: 4096
    min: 1
    max: 64000
  - name: response_format
    use_template: response_format
pricing:
  input: "3.0"
  output: "15.0"
  unit: "0.000001"
  currency: USD

```

--------------------------------

### Invoke LLM Models with Brainiall Gateway in Python

Source: https://context7.com/fasuizu-br/dify-brainiall-plugin/llms.txt

This Python code defines a BrainiallLargeLanguageModel class that inherits from OAICompatLargeLanguageModel. It customizes the invocation process by adding specific Brainiall parameters like API key, mode, and endpoint URL before calling the parent class's _invoke method, enabling streaming and function calling support.

```python
from dify_plugin import OAICompatLargeLanguageModel
from dify_plugin.entities.model.llm import LLMResult
from dify_plugin.entities.model.message import PromptMessage, PromptMessageTool
from typing import Union, Generator, Optional

BRAINIALL_ENDPOINT_URL = "https://apim-ai-apis.azure-api.net/v1"

class BrainiallLargeLanguageModel(OAICompatLargeLanguageModel):
    def _invoke(
        self,
        model: str,
        credentials: dict,
        prompt_messages: list[PromptMessage],
        model_parameters: dict,
        tools: Optional[list[PromptMessageTool]] = None,
        stop: Optional[list[str]] = None,
        stream: bool = True,
        user: Optional[str] = None,
    ) -> Union[LLMResult, Generator]:
        self._add_custom_parameters(credentials)
        return super()._invoke(
            model, credentials, prompt_messages, model_parameters, tools, stop, stream
        )

    @classmethod
    def _add_custom_parameters(cls, credentials: dict) -> None:
        credentials["api_key"] = credentials.get(
            "brainiall_api_key", credentials.get("api_key", "")
        )
        credentials["mode"] = "chat"
        credentials["endpoint_url"] = BRAINIALL_ENDPOINT_URL
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.