Knowledge Catalog (formerly Dataplex)
Always-on context and governance for your agents
Knowledge Catalog is a dynamic, always-on, universal context engine for agents. It unifies structured, unstructured, and SaaS data into a governed, agent-ready truth.
Features
Automated governance across your entire data ecosystem
Deliver scalable, automated governance by transforming raw metadata into a trusted foundation for AI. Enforce policy-based quality checks and anomaly detection across distributed data sources and multimodal data. By combining auto-captured lineage with automated metadata generation, Knowledge Catalog uses Gemini to translate all of these signals into clear business context. This unified control plane standardizes definitions and ensures every data asset is governed, traceable, and ready for agentic workflows.
Multimodal metadata extraction and context curation
Always on cataloging and metadata harvesting is automatic across Google's Data Cloud, including technical metadata and other information like relationships and profiling. It supports 3P databases and partners like Atlan, Collibra, Datahub, Ab Initio and Anomalo. Knowledge Catalog doesn't just list files; it actively reads unstructured data on Google Cloud Storage and can connect unstructured data to structured data to provide unified context across all of your multimodal data.
Defined business semantics
Sync business logic into a single, governed layer. Knowledge Catalog automatically synthesizes context from schemas, query logs, and Looker models to define the relationships and measures AI agents need to reason effectively. Whether you are vibe coding semantic models or extracting logic from a sheet, everything flows into a unified glossary. This ensures consistent, policy-based governance across your entire enterprise.
Context retrieval for your agents
Enable your agents to retrieve holistic context from your enterprise data. Through semantic search, Context APIs, and MCP tools, agents can instantly discover data assets, extract pre-generated enriched metadata. By utilizing these pre-vetted "golden queries" and semantic insights, agents can execute complex tasks, retrieve accurate information, and navigate your data ecosystem with unprecedented precision and scale.
How It Works
Data to AI governance
Build your data to AI governance foundation
Build your data to AI governance foundation
In a single search experience, you can discover data and AI assets org-wide and instantly discover AI models, datasets, and related data artifacts, spanning projects and regions while adhering to IAM permissions. You can also augment assets with business context and enrich AI artifacts with business metadata for informed decision-making, such as ownership, key attributes, and relevant context.
Tutorials, quickstarts, & labs
Build your data to AI governance foundation
Build your data to AI governance foundation
In a single search experience, you can discover data and AI assets org-wide and instantly discover AI models, datasets, and related data artifacts, spanning projects and regions while adhering to IAM permissions. You can also augment assets with business context and enrich AI artifacts with business metadata for informed decision-making, such as ownership, key attributes, and relevant context.
Multimodal data discovery
Make multimodal data insights easily discoverable by agents
Make multimodal data insights easily discoverable by agents
Critical business knowledge often remains locked in unstructured sources like design docs, wikis, PDFs and images. You can instantly turn thousands of PDF contracts, design docs, and wikis into a structured knowledge graph. AI agents can then query this to answer complex questions—like "What are the common liability clauses in our 2025 vendor agreements?"—with grounded, traceable facts.
Tutorials, quickstarts, & labs
Make multimodal data insights easily discoverable by agents
Make multimodal data insights easily discoverable by agents
Critical business knowledge often remains locked in unstructured sources like design docs, wikis, PDFs and images. You can instantly turn thousands of PDF contracts, design docs, and wikis into a structured knowledge graph. AI agents can then query this to answer complex questions—like "What are the common liability clauses in our 2025 vendor agreements?"—with grounded, traceable facts.
Automated data product creation
Automatically create governed data products for agents
Automatically create governed data products for agents
Move beyond simple tables to create data products: self-contained units of intelligence that include built-in intent, SLAs, and governance constraints. By automatically inferring relationships across the data estate, Knowledge Catalog packages these assets into data products so they can be easily distributed and scaled across cross-functional AI teams and agents.
Tutorials, quickstarts, & labs
Automatically create governed data products for agents
Automatically create governed data products for agents
Move beyond simple tables to create data products: self-contained units of intelligence that include built-in intent, SLAs, and governance constraints. By automatically inferring relationships across the data estate, Knowledge Catalog packages these assets into data products so they can be easily distributed and scaled across cross-functional AI teams and agents.
Shared semantics for humans and agents
Define business semantics across your organization
Define business semantics across your organization
Data engineers define structure in technical schemas while analysts define meaning in BI tools, creating a gap for AI agents that can lead to untrusted results. Knowledge Catalog helps you build a shared semantic layer with strict enterprise governance. Whether a human asks a question or an agent performs a task via API, the answer is always based on the same trusted enterprise truth.
Tutorials, quickstarts, & labs
Define business semantics across your organization
Define business semantics across your organization
Data engineers define structure in technical schemas while analysts define meaning in BI tools, creating a gap for AI agents that can lead to untrusted results. Knowledge Catalog helps you build a shared semantic layer with strict enterprise governance. Whether a human asks a question or an agent performs a task via API, the answer is always based on the same trusted enterprise truth.
Govern your open lakehouse
Unified governance for your open lakehouse
Unified governance for your open lakehouse
Knowledge Catalog is deeply integrated with Google Cloud's Lakehouse and integrates its catalog to support governance policies that are centrally defined and enforced across multiple engines like BigQuery and Google Cloud Managed Service for Apache Spark. Knowledge Catalog also enriches governance across Lakehouse by supporting semantic search, data lineage, profiling, and quality checks, providing a managed foundation for your open data lakehouse.
Tutorials, quickstarts, & labs
Unified governance for your open lakehouse
Unified governance for your open lakehouse
Knowledge Catalog is deeply integrated with Google Cloud's Lakehouse and integrates its catalog to support governance policies that are centrally defined and enforced across multiple engines like BigQuery and Google Cloud Managed Service for Apache Spark. Knowledge Catalog also enriches governance across Lakehouse by supporting semantic search, data lineage, profiling, and quality checks, providing a managed foundation for your open data lakehouse.
Pricing
| Knowledge Catalog pricing | Knowledge Catalog pricing is based on pay-as-you-go usage. | |
|---|---|---|
| Service and usage | Description | Price (USD) |
Knowledge Catalog processing | Knowledge Catalog standard and premium processing are metered by the Data Compute Unit (DCU). DCU-hour is an abstract billing unit and the actual metering depends on the individual features you use. | |
Free tier Knowledge Catalog processing First 100 DCU-hour per month for Knowledge Catalog standard processing. | No charge | |
Standard Knowledge Catalog processing Knowledge Catalog standard tier covers the data discovery functionality that automatically discovers table and fileset metadata from Cloud Storage. | Starting at $0.060 per DCU-hour | |
Premium Knowledge Catalog processing The Knowledge Catalog premium processing tier covers the data exploration workbench, data lineage, data quality, and data profiling capabilities of Knowledge Catalog. | Starting at $0.089 per DCU-hour | |
Knowledge Catalog metadata and API pricing | Metadata storage pricing Knowledge Catalog measures the average amount of the stored metadata during a short time interval. For billing, these measurements are combined into a one-month average, which is multiplied by the monthly rate. | |
Knowledge Catalog free tier First 1 MiB monthly average storage. | No charge | |
Metadata storage Over 1 MiB monthly average storage. | Starting at $2 per GiB per month | |
API charges Knowledge Catalog charges for API calls made to the Data Catalog API and Data Lineage API. | ||
API calls First 1 million in a month. | No charge | |
API calls Over 1 million in a month. | Starting at $10 per 100,000 API calls | |
Knowledge Catalog shuffle storage pricing | Shuffle storage pricing covers any disk storage specified in the environments configured for the data exploration workbench. | Starting at $0.040 per GB-month |
Other usage | Data organization features in Knowledge Catalog (lake, zone, or asset setup) and security policy application and propagation, are provided free of charge. | |
Some Knowledge Catalog functionalities trigger job execution using Google Cloud Managed Service for Apache Spark, BigQuery, and Dataflow. Usages for those services are charged according to their respective pricing models, and charges will show up under those services as such. | ||
Knowledge Catalog pricing
Knowledge Catalog pricing is based on pay-as-you-go usage.
Knowledge Catalog processing
Knowledge Catalog standard and premium processing are metered by the Data Compute Unit (DCU). DCU-hour is an abstract billing unit and the actual metering depends on the individual features you use.
Free tier Knowledge Catalog processing
First 100 DCU-hour per month for Knowledge Catalog standard processing.
No charge
Standard Knowledge Catalog processing
Knowledge Catalog standard tier covers the data discovery functionality that automatically discovers table and fileset metadata from Cloud Storage.
Starting at
$0.060
per DCU-hour
Premium Knowledge Catalog processing
The Knowledge Catalog premium processing tier covers the data exploration workbench, data lineage, data quality, and data profiling capabilities of Knowledge Catalog.
Starting at
$0.089
per DCU-hour
Knowledge Catalog metadata and API pricing
Metadata storage pricing
Knowledge Catalog measures the average amount of the stored metadata during a short time interval. For billing, these measurements are combined into a one-month average, which is multiplied by the monthly rate.
Knowledge Catalog free tier
First 1 MiB monthly average storage.
No charge
Metadata storage
Over 1 MiB monthly average storage.
Starting at
$2
per GiB per month
API charges
Knowledge Catalog charges for API calls made to the Data Catalog API and Data Lineage API.
API calls
First 1 million in a month.
No charge
API calls
Over 1 million in a month.
Starting at
$10
per 100,000 API calls
Knowledge Catalog shuffle storage pricing
Shuffle storage pricing covers any disk storage specified in the environments configured for the data exploration workbench.
Starting at
$0.040
per GB-month
Other usage
Data organization features in Knowledge Catalog (lake, zone, or asset setup) and security policy application and propagation, are provided free of charge.
Some Knowledge Catalog functionalities trigger job execution using Google Cloud Managed Service for Apache Spark, BigQuery, and Dataflow. Usages for those services are charged according to their respective pricing models, and charges will show up under those services as such.
Partners & Integration
Partnering with industry leaders
Partners
Explore all partners in Google Cloud Partner Center.
