skills.rest
Agentient
AgentientOFFICIAL
Explore all skills by this author →
GitHub

rag-patterns

Configure Vertex AI RAG pipelines for grounding agent outputs in private data sources.

2|1|Updated Jan 31, 2026
Search Tags:#rag#agents#retrieval#citations#grounding#corpus#vertex-ai
One-click install
npx skills add https://github.com/Agentient/vibekit --skill rag-patterns-agentient
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-patterns
Source: https://github.com/Agentient/vibekit/tree/main/plugins/adk-tools/skills/rag-patterns
Command: npx skills add https://github.com/Agentient/vibekit --skill rag-patterns-agentient

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ground AI agent outputs in private data sources to reduce hallucinations. This skill provides patterns and practical guidance for implementing a RAG pipeline using Vertex AI, including corpus creation, document ingestion, retrieval tool configuration, and grounding metadata handling.

Core Features & Use Cases

  • RAG Corpus creation and management
  • Document ingestion and chunking for indexing
  • Retrieval tool configuration and grounding metadata parsing
  • Citation extraction and source citation generation

Quick Start

Set up a RAG corpus, upload documents, and instantiate a RAG-enabled agent configured to cite sources.

Frequently Asked Questions about rag-patterns

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

FAQPage Schema
How do I ground AI agent responses with private data to reduce hallucinations?▼

Grounding AI agent responses in private data reduces hallucinations by implementing a RAG pipeline using Vertex AI, including corpus creation, document ingestion, and retrieval tool configuration to provide verifiable context.

What is the best way to set up a RAG corpus for document ingestion and indexing?▼

Setting up a RAG corpus for document ingestion and indexing requires creating a Vertex AI RAG corpus, uploading documents, and configuring chunking parameters to prepare the data for embedding and retrieval operations.

How do I extract citations from a Vertex AI RAG pipeline?▼

Extracting citations from a Vertex AI RAG pipeline involves configuring a retrieval tool and parsing grounding metadata to generate source citations that trace agent outputs back to the original ingested documents.

Does this RAG pattern support end-to-end corpus management and embedding workflows?▼

These RAG patterns satisfy end-to-end requirements for corpus management, document ingestion, retrieval tool creation, embedding, indexing, and citation extraction within Vertex AI agent-enabled workflows.

Why do I need grounding metadata when building RAG-enabled agents?▼

Grounding metadata is needed when building RAG-enabled agents to parse citation extraction data, ensuring that agent responses are traceable to specific source documents within the private corpus.

Can I configure a RAG-enabled agent to cite sources automatically using Vertex AI?▼

You can configure a RAG-enabled agent to cite sources automatically by instantiating the agent with a Vertex AI retrieval tool and applying grounding metadata parsing to extract source citations.

Related Skills

Explore More Software Engineering Skills→
kevinnguyen271090kevinnguyen271090
15

google-adk-python

Build and deploy AI agents with Google ADK Python.

Community
Basic
markus41markus41
18

citations-retrieval

Implement Anthropic's Citations API and RAG patterns for source-grounded responses.

Community
Advanced
Awais68Awais68

context7-integration

Ingest documents into Context7 and search them with role-based filters.

Community
Advanced
masermediagroup-stackmasermediagroup-stack
1

embedding-optimization

Configure embedding models, chunking, and caching for RAG pipelines.

Community
Advanced