mistralai

package
v0.28.0-beta Latest Latest
Warning

This package is not in the latest version of its module.

 Go to latest Published: Sep 24, 2024 License: MIT Imports: 8 Imported by: 0

README 

---
title: "Mistral AI"
lang: "en-US"
draft: false
description: "Learn about how to set up a VDP Mistral AI component https://github.com/instill-ai/instill-core"
---

The Mistral AI component is an AI component that allows users to connect the AI models served on the Mistral AI Platform.
It can carry out the following tasks:
- [Text Generation Chat](#text-generation-chat)
- [Text Embeddings](#text-embeddings)

## Release Stage

`Alpha`

## Configuration

The component definition and tasks are defined in the [definition.json](https://github.com/instill-ai/component/blob/main/ai/mistralai/v0/config/definition.json) and [tasks.json](https://github.com/instill-ai/component/blob/main/ai/mistralai/v0/config/tasks.json) files respectively.

## Setup


In order to communicate with Mistral AI, the following connection details need to be
provided. You may specify them directly in a pipeline recipe as key-value pairs
within the component's `setup` block, or you can create a **Connection** from
the [**Integration Settings**](https://www.instill.tech/docs/vdp/integration)
page and reference the whole `setup` as `setup:
${connection.<my-connection-id>}`.

| Field | Field ID | Type | Note |
| :--- | :--- | :--- | :--- |
| API Key | `api-key` | string | Fill in your Mistral API key. To find your keys, visit the Mistral AI platform page.  |




## Supported Tasks

### Text Generation Chat

Mistral AI's text generation models (often called generative pre-trained transformers or large language models) have been trained to understand natural language, code, and images. The models provide text outputs in response to their inputs. The inputs to these models are also referred to as "prompts". Designing a prompt is essentially how you “program” a large language model model, usually by providing instructions or some examples of how to successfully complete a task

| Input | ID | Type | Description |
| :--- | :--- | :--- | :--- |
| Task ID (required) | `task` | string | `TASK_TEXT_GENERATION_CHAT` |
| Model Name (required) | `model-name` | string | The Mistral model to be used |
| Prompt (required) | `prompt` | string | The prompt text |
| System message | `system-message` | string | The system message helps set the behavior of the assistant. For example, you can modify the personality of the assistant or provide specific instructions about how it should behave throughout the conversation. By default, the model’s behavior is set using a generic message as "You are a helpful assistant." |
| Prompt Images | `prompt-images` | array[string] | The prompt images (Note: The Mistral models are not trained to process images, thus images will be omitted) |
| [Chat history](#text-generation-chat-chat-history) | `chat-history` | array[object] | Incorporate external chat history, specifically previous messages within the conversation. Please note that System Message will be ignored and will not have any effect when this field is populated. Each message should adhere to the format: : \{"role": "The message role, i.e. 'system', 'user' or 'assistant'", "content": "message content"\} |
| Seed | `seed` | integer | The seed |
| Temperature | `temperature` | number | The temperature for sampling |
| Top K | `top-k` | integer | Integer to define the top tokens considered within the sample operation to create new text (Note: The Mistral models does not support top-k sampling) |
| Max new tokens | `max-new-tokens` | integer | The maximum number of tokens for model to generate |
| Top P | `top-p` | number | Float to define the tokens that are within the sample operation of text generation. Add tokens in the sample for more probable to least probable until the sum of the probabilities is greater than top-p (default=0.5) |
| Safe | `safe` | boolean | Safe generation mode |

<details>
<summary> Input Objects in Text Generation Chat</summary>

<h4 id="text-generation-chat-chat-history">Chat History</h4>

Incorporate external chat history, specifically previous messages within the conversation. Please note that System Message will be ignored and will not have any effect when this field is populated. Each message should adhere to the format: : {"role": "The message role, i.e. 'system', 'user' or 'assistant'", "content": "message content"}

| Field | Field ID | Type | Note |
| :--- | :--- | :--- | :--- |
| [Content](#text-generation-chat-content) | `content` | array | The message content  |
| Role | `role` | string | The message role, i.e. 'system', 'user' or 'assistant'  |
<h4 id="text-generation-chat-content">Content</h4>

The message content

| Field | Field ID | Type | Note |
| :--- | :--- | :--- | :--- |
| [Image URL](#text-generation-chat-image-url) | `image-url` | object | The image URL  |
| Text | `text` | string | The text content.  |
| Type | `type` | string | The type of the content part.  <br/><details><summary><strong>Enum values</strong></summary><ul><li>`text`</li><li>`image_url`</li></ul></details>  |
<h4 id="text-generation-chat-image-url">Image Url</h4>

The image URL

| Field | Field ID | Type | Note |
| :--- | :--- | :--- | :--- |
| URL | `url` | string | Either a URL of the image or the base64 encoded image data.  |
</details>



| Output | ID | Type | Description |
| :--- | :--- | :--- | :--- |
| Text | `text` | string | Model Output |
| [Usage](#text-generation-chat-usage) (optional) | `usage` | object | Token usage on the Mistral platform text generation models |

<details>
<summary> Output Objects in Text Generation Chat</summary>

<h4 id="text-generation-chat-usage">Usage</h4>

| Field | Field ID | Type | Note |
| :--- | :--- | :--- | :--- |
| Input Tokens | `input-tokens` | number | The input tokens used by Mistral models |
| Output Tokens | `output-tokens` | number | The output tokens generated by Mistral models |
</details>

### Text Embeddings

An embedding is a list of floating point numbers that captures semantic information about the text that it represents.

| Input | ID | Type | Description |
| :--- | :--- | :--- | :--- |
| Task ID (required) | `task` | string | `TASK_TEXT_EMBEDDINGS` |
| Model Name (required) | `model-name` | string | The Mistral embed model to be used |
| Text (required) | `text` | string | The text |





| Output | ID | Type | Description |
| :--- | :--- | :--- | :--- |
| Embedding | `embedding` | array[number] | Embedding of the input text |
| [Usage](#text-embeddings-usage) (optional) | `usage` | object | Token usage on the Mistral platform embedding models |

<details>
<summary> Output Objects in Text Embeddings</summary>

<h4 id="text-embeddings-usage">Usage</h4>

| Field | Field ID | Type | Note |
| :--- | :--- | :--- | :--- |
| Token Count | `tokens` | number | The token count used by Mistral models |
</details>
## Example Recipes

Recipe for the [Short-film Script Writer](https://instill.tech/instill-ai/pipelines/mistral-demo/playground) pipeline.

```yaml
version: v1beta
component:
  mistral-0:
    type: mistral-ai
    task: TASK_TEXT_GENERATION_CHAT
    input:
      max-new-tokens: 1500
      model-name: codestral-latest
      prompt: |-
        Generate a short-film movie script with the following placeholders:
        [THEME]: ${variable.theme}
        [GENRE]: ${variable.genre}
        [NUM_ACTORS]: ${variable.num_actors}
        [SETTING]: ${variable.setting}
        [TIME_PERIOD]: The era or time frame of the story
        [DURATION]: ${variable.duration}
        [CONFLICT]: ${variable.conflict}

        Please create a script that includes:

        A brief synopsis (2-3 sentences)
        Character descriptions for each main character
        Scene-by-scene breakdown with dialogue and basic action descriptions
        A conclusion that resolves the main conflict

        Ensure the script is coherent, engaging, and fits within the specified parameters. Be creative with the storytelling while maintaining the structure of a proper short film script.
      safe: false
      system-message: You are a helpful assistant.
      temperature: 0.7
      top-k: 10
      top-p: 0.5
    setup:
      api-key: ${secret.INSTILL_SECRET}
variable:
  conflict:
    title: Conflict
    description: The main problem or challenge faced by the characters i.e. existential crisis
    instill-format: string
  duration:
    title: Duration
    description: Approximate length of the film in minutes i.e. 5
    instill-format: string
  genre:
    title: Genre
    description: The type of genre for this film i.e. romance, comedy, horror, action, etc.
    instill-format: string
  num_actors:
    title: Num_actors
    description: The number of actors that will be in this film i.e. 2
    instill-format: string
  setting:
    title: Setting
    description: |
      The primary location where the story takes place i.e. Rome
    instill-format: string
  theme:
    title: Theme
    description: Insert the main theme or central idea of the film i.e. time travelling
    instill-format: string
  time-period:
    title: Time Period
    description: The era or time frame of the story i.e. stone age, 20th century, etc.
    instill-format: string
output:
  result:
    title: Result
    value: ${mistral-0.output.text}
```

Recipe for the [PicassoAI: Cubist Creations at Your Command!](https://instill.tech/instill-ai/pipelines/picasso-ai/playground) pipeline.

```yaml
version: v1beta
component:
  mistral-0:
    type: mistral-ai
    task: TASK_TEXT_GENERATION_CHAT
    input:
      max-new-tokens: 100
      model-name: open-mixtral-8x22b
      prompt: |-
        Generate a Picasso-inspired image based on the following user input:

        ${variable.prompt}

        Using the specified Picasso period: ${variable.period}


        Transform this input into a detailed text-to-image prompt by:

        1. Identifying the key elements or subjects in the user's description

        2. Adding artistic elements and techniques specific to the ${variable.period} period of Picasso's work

        3. Including cubist or abstract features characteristic of the ${variable.period}

        4. Suggesting a composition or scene layout typical of Picasso's work from this era

        Enhance the prompt with vivid, descriptive language and specific Picasso-style elements from the ${variable.period}. The final prompt should begin with "Create an image in the style of Picasso's ${variable.period} period:" followed by the enhanced description.
      safe: false
      system-message: You are a helpful assistant.
      temperature: 0.7
      top-k: 10
      top-p: 0.5
    setup:
      api-key: ${secret.INSTILL_SECRET}
  openai-0:
    type: openai
    task: TASK_TEXT_TO_IMAGE
    input:
      model: dall-e-3
      n: 1
      prompt: |-
        Using this primary color palette: ${variable.colour}

        ${mistral-0.output.text}
      quality: standard
      size: 1024x1024
      style: vivid
    setup:
      api-key: ${secret.INSTILL_SECRET}
variable:
  colour:
    title: Colour
    description: Describe the main colour to use i.e. blue, random
    instill-format: string
    instill-ui-order: 1
  period:
    title: Period
    description: |
      Input different Picasso periods i.e. Blue, Rose, African, Synthetic Cubism, etc.
    instill-format: string
  prompt:
    title: Prompt
    description: Input prompt here i.e. "A cute baby wombat"
    instill-format: string
output:
  image:
    title: Image
    value: ${openai-0.output.results}
```

Documentation

Index

Constants

View Source 
const (
	TextGenerationTask = "TASK_TEXT_GENERATION_CHAT"
	TextEmbeddingTask  = "TASK_TEXT_EMBEDDINGS"
)

Variables

This section is empty.

Functions

func Init 

func Init(bc base.Component) *component

Types

type ChatMessage 

type ChatMessage struct {
	Role    string              `json:"role"`
	Content []MultiModalContent `json:"content"`
}

type MistralClient 

type MistralClient struct {
	// contains filtered or unexported fields
}

type MultiModalContent 

type MultiModalContent struct {
	ImageURL URL    `json:"image-url"`
	Text     string `json:"text"`
	Type     string `json:"type"`
}

type TextEmbeddingInput 

type TextEmbeddingInput struct {
	Text      string `json:"text"`
	ModelName string `json:"model-name"`
}

type TextEmbeddingOutput 

type TextEmbeddingOutput struct {
	Embedding []float64          `json:"embedding"`
	Usage     textEmbeddingUsage `json:"usage"`
}

type TextGenerationInput 

type TextGenerationInput struct {
	ChatHistory  []ChatMessage `json:"chat-history"`
	MaxNewTokens int           `json:"max-new-tokens"`
	ModelName    string        `json:"model-name"`
	Prompt       string        `json:"prompt"`
	PromptImages []string      `json:"prompt-images"`
	Seed         int           `json:"seed"`
	SystemMsg    string        `json:"system-message"`
	Temperature  float64       `json:"temperature"`
	TopK         int           `json:"top-k"`
	TopP         float64       `json:"top-p"`
	Safe         bool          `json:"safe"`
}

type TextGenerationOutput 

type TextGenerationOutput struct {
	Text  string    `json:"text"`
	Usage chatUsage `json:"usage"`
}

type URL 

type URL struct {
	URL string `json:"url"`
}

Source Files

View all Source files

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL
go.dev uses cookies from Google to deliver and enhance the quality of its services and to analyze traffic. Learn more.