/google-cloud-solution-hybrid-search-alloydb

name: google-cloud-solution-hybrid-search-alloydb
metadata:
  category: MultiProductSolutions
description: >-
  Discovers requirements and generates architectural, design, and deployment
  guidance for dynamic hybrid search systems by combining semantic search and
  keyword search. Optimized for AlloyDB hybrid search use cases in Google Cloud.
  Use when users need vector search combined with structured SQL
  filtering, faceted attributes, semantic reranking, in-database AI validation,
  or serverless hosting across transactional relational databases, analytical
  data warehouses, or managed database engines. DON'T use this skill for simple
  keyword-only search, or when a standalone non-relational vector database is
  required.

Dynamic Hybrid Search using AlloyDB

This skill provides a workflow to design and implement secure, low-latency, and high-accuracy hybrid search solutions combining structured dataset filtering, vector search indexing, faceted metadata filtering, semantic reranking, recall evaluation, in-database AI validation, database abstraction layers, and serverless application hosting.

Overview of the workflow

The workflow consists of the following phases:

1. **Requirements discovery**. Gather detailed requirements related to the cloud workload or use case that the user needs assistance for. 2. **Solution architecture**. Use the requirements that were gathered in Phase 1 to generate a detailed solution architecture for the cloud workload or use case. 3. **Solution validation**. Create a plan to validate the generated solution, generate validation instructions and scripts, and run the validation. 4. **Solution packaging and presentation**. Consolidate the generated content and present the solution.

**Important notes about the workflow**:

• **Strict phase separation**: During Phase 1 (Requirements discovery), when you

ask the user clarifying questions, DON'T recommend, propose, or outline any architectural designs, cloud services, or component mappings. This prevents premature architecture commitments or hallucinations before the full scope is understood.

• **Halting for approval**: For any step where you are instructed

to "obtain approval before proceeding", you MUST stop executing, present the completed tasks to the user, and wait for their explicit approval. You MUST NOT proceed to execute any subsequent tasks or generate any further guidance in that response.

• **Ground all generated content**: For all tasks across all phases, you MUST

first look in the following resources:

• [Product Mapping](references/product-mapping.md),
• [Design Recommendations](references/design-recommendations.md) for the

required guidance. If the guidance does not provide the required information, you MUST ground the generated content by using the following resources:

• Google Developer Knowledge MCP server:

https://developers.google.com/knowledge/mcp.md.txt

• Server: https://developerknowledge.googleapis.com/mcp
• Tools:
• `developerknowledge:search_documents`
• `developerknowledge:get_documents`
• `developerknowledge:answer_query`
• Relevant skills from https://github.com/google/skills
• Official Google Cloud documentation in

[Related Guidance](references/related-guidance.md)

Product Renaming & Terminology

When generating solution designs, architecture diagrams, and documentation, check the latest Google Cloud documentation for the most up-to-date product names. The table below provides examples of name mappings to be aware of. Note that underlying APIs, Terraform resources, and IAM roles may retain their legacy identifiers.

<table> <thead> <tr> <th>Legacy Name</th> <th>Updated Name</th> <th>Notes</th> </tr> </thead> <tbody> <tr> <td>Vertex AI</td> <td>Gemini Enterprise Agent Platform</td> <td>Gemini Enterprise Agent Platform can be shortened to Agent Platform after first instance</td> </tr> <tr> <td>Vertex AI Embedding</td> <td>Text embedding on Gemini Enterprise Agent Platform</td> <td>This refers to the text embedding models available on Gemini Enterprise Agent Platform</td> </tr> <tr> <td>Vertex AI Matching Engine</td> <td>Vector Search</td> <td></td> </tr> </tbody> </table>

Phase 1: Requirements discovery

In this phase, you must gather detailed requirements related to the hybrid search workload that the user wants to design and deploy in Google Cloud.

**Acknowledge provided requirements**: If the user's prompt already contains some requirements (functional or non-functional, such as catalog size, search modalities, faceted attributes, or latency targets), you MUST explicitly acknowledge and restate all of these requirements in your response. Do NOT ask the user to describe or re-describe any requirements that they have already provided in the prompt.

Complete the following steps strictly in the specified order:

• [ ] **Step 1**: Ask the user to describe the functional requirements of the

workload, including catalog dataset details (e.g., e-commerce apparel, retail products, patent database), search modalities (natural language text, visual search, attribute filters), metadata attributes for faceted filtering (e.g., `category`, `sub_category`, `color`, `gender`, `price`), and quality checks (reranking, LLM validation).

• [ ] **Step 2**: You MUST explicitly ask the user to describe ALL of the

following six categories of non-functional requirements. You need this information because each category represents a critical architectural pillar, and neglecting any of them can result in a solution that is insecure, unreliable, or inefficient (do NOT omit any of them):

• **Security, privacy, and compliance**: E.g., private VPC endpoints, Private

Service Connect, Direct VPC Egress, and access control.

• **Reliability**: E.g., high availability, fai