Fireworks AI | Documentation

The Fireworks AI component is an AI component that allows users to connect the AI models served on the Fireworks AI Platform. It can carry out the following tasks:

Text Generation Chat
Text Embeddings

#Release Stage

Alpha

#Configuration

The component configuration is defined and maintained here.

#Setup

Field	Field ID	Type	Note
API Key	`api-key`	string	Fill in your Fireworks AI API key. To find your keys, visit the Fireworks AI API Keys page.

#Supported Tasks

#Text Generation Chat

Provide text outputs in response to text inputs.

Input	ID	Type	Description
Task ID (required)	`task`	string	`TASK_TEXT_GENERATION_CHAT`
Model Name (required)	`model`	string	The OSS 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: According to Fireworks AI documentation on 2024-07-24, the total number of images included in a single API request should not exceed 30, and all the images should be smaller than 5MB in size)
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
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)

Output	ID	Type	Description
Text	`text`	string	Model Output
Usage (optional)	`usage`	object	Token usage on the Fireworks AI platform text generation models

#Text Embeddings

Turn text into a vector of numbers that capture its meaning, unlocking use cases like semantic search.

Input	ID	Type	Description
Task ID (required)	`task`	string	`TASK_TEXT_EMBEDDINGS`
Model Name (required)	`model`	string	The OSS embedding model to be used
Text (required)	`text`	string	The text

Output	ID	Type	Description
Embedding	`embedding`	array[number]	Embedding of the input text
Usage (optional)	`usage`	object	Token usage on the Fireworks AI platform embedding models

#Example Recipes

Recipe for the Fireworks Chinese Content Writer pipeline.

version: v1beta
component:
    fireworks-0:
        type: fireworks-ai
        task: TASK_TEXT_GENERATION_CHAT
        input:
            max-new-tokens: 200
            model: qwen2-72b-instruct
            prompt: ${variable.prompt}
            system-message: You are a expert social media content writing assistant. Output the result in chinese for 小紅書.
            temperature: 0.05
            top-k: 10
            top-p: 0.5
        setup:
            api-key: ${secret.INSTILL_SECRET}
variable:
    prompt:
        title: prompt
        description: input prompt i.e. "寫一份生椰拿鐵文案", "write about horses"
        instill-format: string
output:
    output:
        title: output
        value: ${fireworks-0.output.text}