adk-rag-agent
Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed responses. Covers VertexAiRagRetrieval tool, corpus setup, and citation formatting.
Best use case
adk-rag-agent is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed responses. Covers VertexAiRagRetrieval tool, corpus setup, and citation formatting.
Teams using adk-rag-agent should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/adk-rag-agent/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How adk-rag-agent Compares
| Feature / Agent | adk-rag-agent | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Build RAG (Retrieval-Augmented Generation) agents with Google ADK and Vertex AI RAG Engine. Use when implementing document Q&A, knowledge base search, or citation-backed responses. Covers VertexAiRagRetrieval tool, corpus setup, and citation formatting.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# Google ADK RAG Agent
Build agents that answer questions from document corpora using Vertex AI RAG Engine.
## Requirements
- Vertex AI backend (not Gemini API)
- Google Cloud project with Vertex AI enabled
- RAG corpus created in Vertex AI
## Environment Variables
```bash
GOOGLE_GENAI_USE_VERTEXAI=1
GOOGLE_CLOUD_PROJECT=your-project-id
GOOGLE_CLOUD_LOCATION=us-central1
RAG_CORPUS=projects/{PROJECT_ID}/locations/{LOCATION}/ragCorpora/{CORPUS_ID}
```
## Core Implementation
```python
from google.adk import Agent
from google.adk.tools import VertexAiRagRetrieval
# Configure RAG retrieval tool
rag_tool = VertexAiRagRetrieval(
name="retrieve_docs",
description="Retrieve relevant documentation for the question",
rag_corpus=os.environ["RAG_CORPUS"],
similarity_top_k=10,
vector_distance_threshold=0.6,
)
# Create agent with RAG tool
agent = Agent(
name="rag_agent",
model="gemini-2.0-flash-001",
instruction=INSTRUCTION_PROMPT,
tools=[rag_tool],
)
```
## Instruction Prompt Pattern
```python
INSTRUCTION_PROMPT = """
You are an AI assistant with access to a specialized document corpus.
RETRIEVAL:
- Use retrieve_docs for specific knowledge questions
- Skip retrieval for casual conversation
- Ask clarifying questions when intent is unclear
SCOPE:
- Only answer questions related to the corpus
- Say "I don't have information about that" for out-of-scope queries
CITATIONS:
- Always cite sources at the end of responses
- Format: [Title](url) or [Document Section](url)
- Consolidate multiple citations from the same source
"""
```
## Corpus Setup
Create corpus via Vertex AI Console or SDK:
```python
from vertexai.preview import rag
# Create corpus
corpus = rag.create_corpus(display_name="my-corpus")
# Import documents (PDF, TXT, HTML)
rag.import_files(
corpus_name=corpus.name,
paths=["gs://bucket/doc.pdf"], # or local files
chunk_size=512,
chunk_overlap=100,
)
```
## Key Parameters
| Parameter | Description | Default |
|-----------|-------------|---------|
| `similarity_top_k` | Max chunks to retrieve | 10 |
| `vector_distance_threshold` | Min similarity (0-1, lower=stricter) | 0.6 |
| `chunk_size` | Tokens per chunk at import | 512 |
| `chunk_overlap` | Overlap between chunks | 100 |
## Citation Best Practices
1. Single source → single citation at end
2. Multiple sources → list all citations
3. Same document, multiple chunks → consolidate into one citation
4. Never expose internal chunk IDs to users
## References
- [Corpus setup details](references/corpus-setup.md)
- [Sample repo](https://github.com/google/adk-samples/tree/main/python/agents/RAG)Related Skills
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.
ontopo
An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
vly-money
Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.
astro
This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.
grail-miner
This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.
lets-go-rss
A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.
ux
This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.
chrome-debug
This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.
advanced-skill-creator
Meta-skill that generates domain-specific skills using advanced reasoning techniques. PROACTIVELY activate for: (1) Create/build/make skills, (2) Generate expert panels for any domain, (3) Design evaluation frameworks, (4) Create research workflows, (5) Structure complex multi-step processes, (6) Instantiate templates with parameters. Triggers: "create a skill for", "build evaluation for", "design workflow for", "generate expert panel for", "how should I approach [complex task]", "create skill", "new skill for", "skill template", "generate skill"