Welcome
UnO Agentic AI Builder
Credential Library
HuggingFace Credentials
Use HuggingFace Credentials to establish a secure and authenticated connection between HCL UnO Agentic AI Builder solutions and the Hugging Face API. This credential is required for accessing models or services that require authentication on the Hugging Face platform, often for downloading gated models or interacting with paid/rate-limited endpoints.

What's new
HCL Universal Orchestrator is constantly evolving to offer you the most comprehensive orchestration capabilities. For known limitations, workarounds, and contact information of HCL Customer Support, see Release notes.
Getting started with HCL Universal Orchestrator
HCL Universal Orchestrator is a cloud-native workload orchestration and scheduling platform built on Kubernetes. Its microservices-based architecture enables the centralized orchestration of multi-cloud and hybrid environments from a single point of control.
Deploying and Administrating
All the information you need to deploy and administrate HCL Universal Orchestrator.
Using the UI
The UI is the HCL Universal Orchestrator interface, from which you can design your scheduling environment and monitor every process.
Orchestrating
Orchestrate anything with HCL Universal Orchestrator.
Orchestrating from Mobile
You can use your mobile devices to manage quickly and easily your whole HCL Universal Orchestrator environment.
Monitoring
Take your environment under control.
Using REST API
Use REST APIs to easily integrate workload scheduling capabilities with external products and solutions.
Administering multitenancy for service providers
Configure and administer a HCL Universal Orchestrator multitenant environment.
Uno AI Pilot
Welcome to the HCL Universal Orchestrator AI Pilot documentation. This resource is designed to guide you through everything you need to know about using UnO AI Pilot effectively. You will find detailed instructions, feature overviews, and helpful tips to ensure you get the best experience with UnO AI Pilot.
UnO Agentic AI Builder
- Overview of UnO Agentic AI Builder
- Welcome to UnO Agentic AI Builder
- Managing the Folder Workspace
- Templates Catalog
- Deployment Overview
- Access Control Overview
- User Guide
- Installation and Configuration
  This section guides you through installing the UnO Agentic AI Builder.
- Credential Library
  - Amazon Bedrock Credentials
    Use AWS Bedrock Credentials to establish a secure and authenticated connection between HCL UnO Agentic AI Builder solutions and Amazon Bedrock. This essential connection allows your AI agents to seamlessly interact with Amazon's portfolio of high-performance foundation models (FMs) for all generative AI tasks.
  - Anthropic Credentials
    Use Anthropic Credentials to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to your Anthropic instance.
  - API Key Credentials
    Use API Key Credential to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to web services or APIs that rely solely on an API key for authentication. This allows your agents to make authenticated requests to external systems using a simple and widely supported authentication method.
  - Azure Blob Credentials
    Use Azure Blob Credential to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to Microsoft Azure Blob Storage. This allows your agents to store, retrieve, and manage unstructured data (such as text or binary data) in highly scalable object storage.
  - Astra DB Credentials
    Use Astra DB Credentials to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to a DataStax Astra DB database. This allows your agents to perform scalable and serverless data operations powered by Apache Cassandra, without managing infrastructure.
  - Azure Credentials
    Use Azure Credentials to establish a secure and authenticated connection between HCL UnO Agentic AI Builder solutions and Azure OpenAI Service. These credentials enable AI agents to utilize Azure-hosted LLMs, which are typically tied to specific deployments, allowing for enterprise-grade security and control.
  - AWS S3 Account Credentials
    Use AWS S3 Account Credentials to establish a secure and authenticated connection from HCLUnO Agentic AI Builder solutions to Amazon Simple Storage Service (S3). This allows your agents to upload, download, or manage files in your S3 buckets.
  - Basic Authentication Credentials
    Use Basic Authentication Credential to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to web services or APIs that utilize HTTP Basic Authentication or an FTP server. This allows your agents to perform operations with systems that accept a username and password for authentication.
  - Bearer Token Credentials
    Use Bearer Token Credential to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to APIs or services that utilize OAuth 2.0 Bearer Tokens for authentication. This allows your agents to securely access protected resources by presenting a valid access token.
  - Cassandra DB Credentials
    Use Cassandra DB Credentials to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to an Apache Cassandra database. This allows your agents to interact with distributed NoSQL clusters for high-volume, high-availability data storage and retrieval.
  - Exa Search Account Credentials
    Use Exa Search Account Credential to establish a secure and authenticated connection between HCL UnO Agentic AI Builderand the Exa neural search service. This credential enables agents to perform real-time, AI-optimized internet searches by securely managing the Exa API key. Once configured, agents can retrieve high-quality web results, summaries, and source URLs to fulfill complex queries within their workflows.
  - HuggingFace Credentials
    Use HuggingFace Credentials to establish a secure and authenticated connection between HCL UnO Agentic AI Builder solutions and the Hugging Face API. This credential is required for accessing models or services that require authentication on the Hugging Face platform, often for downloading gated models or interacting with paid/rate-limited endpoints.
  - OpenAI Account Credentials
    Use OpenAI Account Credentials to establish a secure and authenticated connection between HCL UnO Agentic AI Builder and the OpenAI API. These credentials are essential for enabling AI agents to interact with OpenAI models for natural language processing and generation tasks.
  - Google Search API Credentials
    Use Google Search API Account Credentials to establish a secure and authenticated connection from HCL UnO Agentic AI Buildersolutions to the Google Custom Search JSON API. This allows your agents to perform programmatic searches using Google's powerful search capabilities, either across the entire web or within specific websites you define.
  - GitHub API Credentials
    Use GitHub API Credentials to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to the GitHub API. These credentials are essential when configuring tools or integrations within your agents and workflows that need access to GitHub repositories, issues, or other resources.
  - Google OAuth Credentials
    Use Google OAuth Credentials to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to Google APIs on behalf of an end-user.
  - Google Service Account Credentials
    Use Google Service Account Credentials to establish a secure and programmatic connection from HCL UnO Agentic AI Builder solutions to Google Cloud Platform (GCP) services. Unlike user accounts, service accounts represent non-human users and are ideal for server-to-server interactions, allowing your agents to access Google APIs without requiring direct end-user authentication.
  - Jira API Credentials
    Use Jira API Credentials to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to your Jira instance. This integration enables your agents to interact programmatically with Jira projects, issues, workflows, and user data.
  - Nvidia Credentials
    Use Nvidia Credentials to establish a secure and authenticated connection between HCL UnO Agentic AI Builder and the Nvidia AI Foundations API (Nvidia NIMs/Inference Microservices). These credentials allow agents to securely access and utilize models hosted by Nvidia for high-performance generative tasks.
  - Ollama Credentials
    Use Ollama Credentials to establish a secure connection between HCL UnO Agentic AI Builder solutions and a locally or remotely hosted Ollama server. This allows your AI agents to interact with community-driven LLMs or Small Language Models (SLMs) managed by the Ollama framework, offering flexibility for specialized or resource-constrained deployments.
  - Postgres Database Credentials
    Use PostgreSQL Database Credentials to establish a secure and authenticated connection between HCL UnO Agentic AI Builder and a PostgreSQL database.
  - Search API Account Credentials
    Use Search API Account Credentials to establish a secure and authenticated connection from your HCL UnO Agentic AI Builder solutions to a generic Search API service. This credential type enables integration with third-party search providers that support API key-based authentication, allowing agents to perform external information retrieval from web indexes or structured data sources.
  - Slack Credentials
    The Slack Credential allows HCL UnO Agentic AI Builder to securely store and manage the authentication required to interact with your Slack workspace. By configuring this credential, you authorize your agents to execute actions - such as sending messages or alerts - using a dedicated Slack Bot identity.
  - Tavily Account Credentials
    Use Tavily Account Credentials to establish a secure and authenticated connection from HCLUnO Agentic AI Builder solutions to the Tavily API. Tavily is a search API purpose-built for AI agents, delivering fast, relevant, and summarized search results from the web. Integrating Tavily enables agents to perform real-time information retrieval and contextual understanding from external sources.
  - Watsonx Credentials
    Use Watsonx Credentials to establish a secure and authenticated connection from HCL UnO Agentic AI Builder solutions to your Watsonx instance.
- LLM/SLM Profile Library
- Tools Library
- Templates Library
- Key Terminology
- Best practices to Create Agents
- Troubleshooting UnO Agentic AI Builder
- Known Limitations
  This section outlines known limitations and constraints of the current release, helping users understand the boundaries of supported functionality and avoid unintended usage scenarios.
Troubleshooting
Recover your environment if any issue occurs.
Notices

HuggingFace Credentials

Use HuggingFace Credentials to establish a secure and authenticated connection between HCL UnO Agentic AI Builder solutions and the Hugging Face API. This credential is required for accessing models or services that require authentication on the Hugging Face platform, often for downloading gated models or interacting with paid/rate-limited endpoints.

Before you begin

Ensure the following prerequisites are met:

You must have an active Hugging Face account.
You must have generated a valid Hugging Face Access Token from your account settings.
Ensure you have access rights to any gated models or specific inference endpoints you intend to use.

Table 1. Mandatory fields
Option	Description
Credential Name	A unique, user-defined name for this HuggingFace credential. This name will be used to identify the credential within the HCL UnO Agentic AI Builder.
API Token	Your secret token for accessing HuggingFace.

Table 2. Optional fields
Options	Description
Endpoint URL	The custom inference endpoint URL if you are using a dedicated Hugging Face Inference Endpoint.
Discover Models	When selected, the system automatically retrieves and displays the latest available LLM models from Hugging Face account in the LLM Name dropdown. When not selected, the system uses the predefined, static list of models bundled with the product, and newly released Hugging Face account models will not appear in the dropdown.