About ai-tasks

AI Tasks. A LLM integrated agent orchestration tool for Liferay.

p

Published by

peerkar

Visit View Profile

README.md

View on GitHub

AI Tasks

About

AI Tasks is a tool for Liferay allowing to easily build and manage AI-assisted, agentic workflows without extensive programming knowledge. It leverages large language models (LLMs) and an agent-based approach. It can be used standalone, for example for Liferay chatbots and chat interfaces but also integrated to Liferay workflows and to external orchestrators and vice versa. It lets to visually define LLM driven workflows which are then exposed through a REST endpoint. Liferay integration enables governing access, permissions and auditing with the standard Liferay tools as well as easy integration to existing or new Liferay features, to leverage AI.

AI Tasks backend is built on LangChain4J and supports the Model Context Protocol (MCP) for creating standardized integrations to external and internal services.

AI Tasks admin

Quick Start

See the quick start tutorial here.

Samples

Several sample AI Tasks are provided in the samples folder.

Features

AI integration: Integrate with Anthropic, Vertex AI, OpenAI, Ollama or HuggingFace chat and image LLMs.
MCP support: Integrate the tasks to MCP servers
Workflow orchestration: Design workflows with a visual editor. Export & import as JSON configuration files.
Liferay integration: Manage access, permissions and policies with Liferay. Trigger and consume the tasks through REST API.
Data locality: Local LLMs supported through Ollama.
3rd Party Integration: Integrate to 3rd party workflow automation tools. Let 3rd party tools to integrate to it via REST APIs.
Open Source: Extend and customize the task node types and function callback to your needs

Example Use Cases

Create Liferay chatbots
Create multi-agent tasks operating with internal or external services with the help of MCP
Add AI translation capabilities to Liferay pages, display templates or applications
Add AI summarization capabilities to Liferay pages, display templates or applications
Add image & content generation capabilities to Liferay pages, display templates or applications
Create RAG chatbots grounded to local Liferay semantic search or for example to Google Search
Integrate Liferay OOTB workflows with AI

How To Use It

Create an AI Task, for example a simple LLM chat using the visual designer
From the provided test chatbot, a Liferay display template, client extension, your own frontend or from anywhere, consume the AI Task through its generate REST endpoint:

For example, to send the text Please tell me a joke for an AI Tasks with external reference code sampleJokingChatbotUsingVertexAI, one would send a payload like this:

curl -X 'POST' \
  'http://localhost:8080/o/ai-tasks/v1.0/generate/sampleJokingChatbotUsingVertexAI' \
  -H 'accept: application/json' \
  -H 'Content-Type: application/json' \
  -H 'x-csrf-token: kPNn0CrS' \
  -d '{
  "input": {
"text": "Please tell me a joke"}
}'

If everything was set up correctly, the response, with trace enabled, should look something like this:

{
  "executionTrace": {
    "llmNodeid": {
      "userMessage": "Please tell me a joke",
      "executionTime": "1921ms",
      "systemMessage": "",
      "tokenUsage": {
        "inputTokenCount": 21,
        "totalTokenCount": 72,
        "outputTokenCount": 51
      },
      "finishReason": "STOP",    
      "content": "Why did the golfer wear two pants? Because he's afraid he might get a \"Hole-in-one.\" \n\nThis is a classic punny joke!  Let me know if you'd like to hear another one. 😊"
    }
  }
  "output": {
    "text": "Why did the golfer wear two pants? Because he's afraid he might get a \"Hole-in-one.\" \n\nThis is a classic punny joke!  Let me know if you'd like to hear another one. 😊"
  },
  "took": "1921ms"
}

Installation

Requirements

Liferay DXP 7.4
Java 17
The desired AI services / accounts set up

1. Install the Modules

Clone the repository:
```
[email protected]:peerkar/ai-tasks.git
```
Set up the Liferay bundle. If using the workspace bundle, go to the liferay-workspace folder and run:
```
gw initBundle
```
Start up the DXP and deploy the license
In both the modules and client-extensions directory run:
```
gw deploy
```
Verify from Liferay logs that all the modules were deployed and started succesfully
Access the AI Tasks Admin app in the Applications menu

2. Set up the LLMs

Set up your preferred APIs and services as needed:

Ollama
HuggingFace
OpenAI API
Vertex AI. In local development environment, the gcloud CLI is required.

3. Access the Admin Application

Log in to the portal and go to the Application -> AI Tasks -> AI Tasks Admin

4. Test

Import a sample or create your own task and either test it:

In the AI Task Admin preview
On the local API test page
In the provided test chatbot client extension

Configuration

See the configuration reference.

Extending

Currently there are 3 extension points:

Nodes
Tools
Chat model listeners

See the SPI module.

For extending the tooling, using MCP is recommended.

Good to Remember

Set Up the LLM Quotas

Always use quotas when integrating to external LLM service providers.

Known Issues

Performance

LLM calls can take a long time to execute, meaning blocked threads. This issue will be mitigated with https://github.com/peerkar/ai-tasks/issues/2

Multimodality

AI Tasks is using the LangChain4J AI Services, which don't currently support multimodal input. Please see https://github.com/langchain4j/langchain4j/issues/938

GCloud Client Authentication & Timeouts

Authentication to Vertex AI doesn't work if the gcloud authentication is not done before starting the DXP. To authenticate, enter on the command line:

gcloud auth application-default login
gcloud auth login

If the authorization key is timed out. The portal needs to be shut down before reauthenticating.

ai-tasks