ChatFireworks

​

Node Details

• Name: ChatFireworks
• Type: ChatFireworks
• Version: 1.0
• Category: Chat Models

​

Base Classes

• ChatFireworks
• [Other base classes from ChatFireworks]

​

Parameters

​

Credential (Required)

​

Parameters

​

Credential (Required)

• Type: credential
• Name: fireworksApi
• Description: API key for authenticating with Fireworks AI services

​

Inputs

​

Inputs

1. Cache

   • Type: BaseCache
   • Optional: Yes
   • Description: Caching mechanism for storing and retrieving chat responses

2. Model

   • Type: string
   • Default: “accounts/fireworks/models/llama-v2-13b-chat”
   • Description: The specific Fireworks AI model to use for chat

3. Temperature

   • Type: number
   • Default: 0.9
   • Step: 0.1
   • Optional: Yes
   • Description: Controls the randomness of the model’s output. Higher values make the output more random, while lower values make it more deterministic

​

Initialization

The node initializes a ChatFireworks instance with the following configurations:

• Fireworks API Key (from credentials)
• Model name
• Temperature
• Streaming option (default: true)
• Cache (if provided)

​

Usage

This node is used to integrate Fireworks AI’s chat capabilities into a workflow. It allows users to interact with various Fireworks chat models, with options to adjust the model’s behavior through temperature settings and caching mechanisms.

​

Input/Output

• Input: The node expects input in the form of chat messages or prompts (handled externally)
• Output: Generates chat responses using the specified Fireworks AI model

​

Notes

• The node supports streaming responses by default
• Temperature can be adjusted to control the creativity/randomness of the model’s outputs
• Caching can be implemented to improve response times for repeated queries
• The default model is set to “llama-v2-13b-chat”, but this can be changed as needed