1.9.8 • Published 6 months ago
@aigne/example-chat-bot v1.9.8
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):
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-botInstallation
Clone the Repository
git clone https://github.com/AIGNE-io/aigne-frameworkInstall Dependencies
cd aigne-framework/examples/chat-bot
pnpm installSetup Environment Variables
Setup your OpenAI API key in the .env.local file:
OPENAI_API_KEY="" # Set your OpenAI API key hereRun 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 startRun Options
The example supports the following command-line parameters:
| Parameter | Description | Default |
|---|---|---|
--chat | Run in interactive chat mode | Disabled (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 generation | Provider default |
--top-p <value> | Top-p sampling value | Provider default |
--presence-penalty <value> | Presence penalty value | Provider default |
--frequency-penalty <value> | Frequency penalty value | Provider default |
--log-level <level> | Set logging level (ERROR, WARN, INFO, DEBUG, TRACE) | INFO |
--input, -i <input> | Specify input directly | None |
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 start1.9.8
6 months ago
1.9.7
6 months ago
1.9.6
6 months ago
1.9.5
6 months ago
1.9.4
6 months ago
1.9.3
6 months ago
1.9.2
6 months ago
1.9.1
6 months ago
1.9.0
6 months ago
1.8.1
6 months ago
1.8.0
7 months ago
1.7.0
7 months ago
1.6.0
7 months ago
1.5.0
7 months ago
1.4.2
7 months ago
1.4.1
7 months ago
1.4.1-6
7 months ago
1.4.1-5
7 months ago
1.4.1-4
7 months ago
1.4.1-3
7 months ago
1.4.1-2
7 months ago
1.4.1-1
7 months ago
1.4.1-0
7 months ago
1.3.0
7 months ago
1.2.0
7 months ago
1.1.0
8 months ago