1.9.8 • Published 10 months ago

@aigne/example-chat-bot v1.9.8

Weekly downloads
-
License
MIT
Repository
github
Last release
10 months ago

Chatbot Example

This example demonstrates how to create and run an agent-based chatbot using the AIGNE Framework and AIGNE CLI. The example now supports both one-shot and interactive chat modes, along with customizable model settings and pipeline input/output.

Prerequisites

  • Node.js and npm installed on your machine
  • An OpenAI API key for interacting with OpenAI's services
  • Optional dependencies (if running the example from source code):
    • Pnpm for package management
    • Bun for running unit tests & examples

Quick Start (No Installation Required)

export OPENAI_API_KEY=YOUR_OPENAI_API_KEY # Set your OpenAI API key

# Run in one-shot mode (default)
npx -y @aigne/example-chat-bot

# Run in interactive chat mode
npx -y @aigne/example-chat-bot --chat

# Use pipeline input
echo "Tell me about AIGNE Framework" | npx -y @aigne/example-chat-bot

Installation

Clone the Repository

git clone https://github.com/AIGNE-io/aigne-framework

Install Dependencies

cd aigne-framework/examples/chat-bot

pnpm install

Setup Environment Variables

Setup your OpenAI API key in the .env.local file:

OPENAI_API_KEY="" # Set your OpenAI API key here

Run the Example

pnpm start # Run in one-shot mode (default)

# Run in interactive chat mode
pnpm start -- --chat

# Use pipeline input
echo "Tell me about AIGNE Framework" | pnpm start

Run Options

The example supports the following command-line parameters:

ParameterDescriptionDefault
--chatRun in interactive chat modeDisabled (one-shot mode)
--model <provider[:model]>AI model to use in format 'provider:model' where model is optional. Examples: 'openai' or 'openai:gpt-4o-mini'openai
--temperature <value>Temperature for model generationProvider default
--top-p <value>Top-p sampling valueProvider default
--presence-penalty <value>Presence penalty valueProvider default
--frequency-penalty <value>Frequency penalty valueProvider default
--log-level <level>Set logging level (ERROR, WARN, INFO, DEBUG, TRACE)INFO
--input, -i <input>Specify input directlyNone

Examples

# Run in chat mode (interactive)
pnpm start -- --chat

# Set logging level
pnpm start -- --log-level DEBUG

# Use pipeline input
echo "Tell me about AIGNE Framework" | pnpm start
1.9.8

10 months ago

1.9.7

10 months ago

1.9.6

10 months ago

1.9.5

10 months ago

1.9.4

10 months ago

1.9.3

10 months ago

1.9.2

10 months ago

1.9.1

11 months ago

1.9.0

11 months ago

1.8.1

11 months ago

1.8.0

11 months ago

1.7.0

11 months ago

1.6.0

11 months ago

1.5.0

12 months ago

1.4.2

12 months ago

1.4.1

12 months ago

1.4.1-6

12 months ago

1.4.1-5

12 months ago

1.4.1-4

12 months ago

1.4.1-3

12 months ago

1.4.1-2

12 months ago

1.4.1-1

12 months ago

1.4.1-0

12 months ago

1.3.0

12 months ago

1.2.0

12 months ago

1.1.0

12 months ago