skills.rest
logicalclocks
logicalclocksOFFICIAL
Explore all skills by this author →
Website𝕏@hopsworksGitHub

hops-agent-deployment

Deploy interactive agents as server-only KServe deployments without model attachments.

15|32|Updated Nov 13, 2021
Search Tags:#agent deployment#feature store#LLM workflow#KServe#Hopsworks
One-click install
npx skills add https://github.com/logicalclocks/hopsworks-api --skill hops-agent-deployment
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hops-agent-deployment
Source: https://github.com/logicalclocks/hopsworks-api/tree/main/skills/hops/hops-agent-deployment
Command: npx skills add https://github.com/logicalclocks/hopsworks-api --skill hops-agent-deployment

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of deploying interactive agents, such as LlamaIndex programs, as served Hopsworks deployments, streamlining the process for real-time feature vector serving and ML workflows.

Core Features & Use Cases

  • Interactive Agent Deployment: Deploy server-only KServe deployments with no model attached.
  • Agent Scripting: Utilize entry scripts to handle requests for interactive agents and LLM workflows.
  • Feature Store Integration: Read context from the feature store for RAG (Retrieval-Augmented Generation) capabilities.
  • Git Repository Support: Deploy agents from GitHub, GitLab, or BitBucket repositories.
  • Use Case: Deploy a custom LLM agent for real-time Q&A sessions or chatbots within Hopsworks.

Quick Start

Deploy an agent by providing the entry script and specifying the name and environment.

Frequently Asked Questions about hops-agent-deployment

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy interactive LLM agents as KServe deployments in Hopsworks?▼

Deploy interactive LLM agents as server-only KServe deployments by providing entry scripts and environment configuration, without attaching a model. This streamlines real-time feature vector serving and ML workflows.

Can I deploy an interactive agent from a Git repository?▼

Yes, interactive agents can be deployed from GitHub, GitLab, or BitBucket repositories. You can also deploy them directly from local files by providing the required entry scripts and environment configuration.

Does interactive agent deployment support feature store integration for RAG workflows?▼

Yes, interactive agent deployment supports feature store integration, allowing you to read context from the feature store to enable Retrieval-Augmented Generation capabilities for your LLM workflows.

What is the best way to serve a custom LlamaIndex program for real-time Q&A?▼

The best way to serve a custom LlamaIndex program for real-time Q&A is deploying it as a server-only KServe deployment. You provide entry scripts to handle requests for interactive agents and LLM workflows.

Do I need to attach a model to deploy an interactive agent on KServe?▼

No, interactive agents are deployed as server-only KServe deployments without model attachments. You only need to provide entry scripts and environment configuration to handle requests and LLM workflows.

Related Skills

Explore More Software Engineering Skills→
VeerMuchandiVeerMuchandi
2

Agent Engine Terraform Deployer

Automate ADK agent deployment to Vertex AI Agent Engine with Terraform scripts.

Community
Intermediate
charleshall888charleshall888
1

requirements-gather

Conduct a structured requirements interview and output a Q&A markdown block.

Community
Advanced
abdullahhqaiserabdullahhqaiser

langchain-rag

Build RAG pipelines that load, split, embed, store, and retrieve documents.

Community
Intermediate
ancolemanancoleman
503

model-serving

Deploy LLM and ML models for production inference with vLLM, TensorRT-LLM, Ollama, and BentoML.

Community
Advanced