Skip to content
J·BJon BishopFractional growth marketer

Data platforms · llms.txt file breakdown

Databricks llms.txt

A directly retrieved Markdown index for Databricks's documentation, with 267 links across 16 detected headings.

The actual file

Source Markdown

The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.

Open saved text ↗

Showing the first 18000 characters. Load the complete file to read the remainder.

# Databricks Documentation
> Comprehensive documentation for the Databricks Data Intelligence Platform, including guides for data engineering, machine learning, AI, analytics, governance, and administration across all supported cloud platforms.

## Overview and getting started
- [Main documentation index](https://docs.databricks.com/) - How-to guides and reference documentation for data teams using the Databricks Data Intelligence Platform to solve analytics and AI challenges in the Lakehouse.
- [What is Databricks?](https://docs.databricks.com/introduction/) - Learn what is the Databricks Data Intelligence Platform.
- [Databricks components](https://docs.databricks.com/getting-started/concepts/) - Learn fundamental Databricks components such as workspaces, data objects, clusters, machine learning models, and access.
- [Get started tutorials on Databricks](https://docs.databricks.com/getting-started/) - Learn how to get started using Databricks with step-by-step tutorials.
- [Query and visualize data](https://docs.databricks.com/getting-started/quick-start) - Learn data science basics on Databricks. Using a notebook, query and visualize data stored in Unity Catalog by using SQL, Python, Scala, and R.
- [Import and visualize CSV data from a notebook](https://docs.databricks.com/getting-started/import-visualize-data) - Learn how to import CSV data into a notebook and create visualizations.
- [Create a table](https://docs.databricks.com/getting-started/create-table) - Learn how to create tables in Databricks.
- [Build an ETL pipeline (Lakeflow pipelines)](https://docs.databricks.com/getting-started/data-pipeline-get-started) - Learn how to create and deploy an ETL (extract, transform, and load) pipeline with Lakeflow pipelines.
- [Build an ETL pipeline (Apache Spark)](https://docs.databricks.com/getting-started/etl-quick-start) - Learn how to build an ETL pipeline using Apache Spark on Databricks.
- [Train and deploy an ML model](https://docs.databricks.com/getting-started/ml-get-started) - Learn how to build a simple machine learning classification model on Databricks using the scikit-learn library.
- [Query LLMs and prototype gen AI agents](https://docs.databricks.com/getting-started/gen-ai-llm-agent) - Learn how to query large language models and prototype generative AI agents on Databricks.
- [Get started as a business analyst with Genie](https://docs.databricks.com/getting-started/analyst-get-started) - Get started as a business analyst by viewing dashboards, asking natural language data questions with Genie, and discovering shared assets.
- [Customer segmentation with Genie Code](https://docs.databricks.com/getting-started/genie-code-customer-segmentation) - Use Genie Code to run end-to-end customer segmentation in a Databricks notebook, from data profiling to K-means clustering.
- [Free trial setup](https://docs.databricks.com/getting-started/free-trial) - Learn how to set up a Databricks free trial.
- [Free edition](https://docs.databricks.com/getting-started/free-edition) - Learn how to sign up for Databricks Free Edition and start using Databricks today.
- [Load and transform data using Spark DataFrames](https://docs.databricks.com/getting-started/dataframes/) - Learn how to load and transform data using the Apache Spark Python (PySpark) DataFrame API, the Scala DataFrame API, and the SparkR SparkDataFrame API in Databricks.

## Core platform
- [Data lakehouse](https://docs.databricks.com/lakehouse/) - Use Databricks in a data lakehouse paradigm for generative AI, ACID transactions, data governance, ETL, BI, and machine learning.
- [Delta Lake](https://docs.databricks.com/delta/) - Learn about the Delta storage protocol used to power the Databricks lakehouse.
- [Unity Catalog](https://docs.databricks.com/data-governance/unity-catalog/) - Learn how to perform data governance in Databricks using Unity Catalog.
- [Database objects](https://docs.databricks.com/database-objects/) - Learn about database objects including catalogs, schemas, tables, volumes, and views in Databricks.
- [Catalogs](https://docs.databricks.com/catalogs/) - Learn how to create catalogs in Unity Catalog using Catalog Explorer or SQL statements.
- [Volumes](https://docs.databricks.com/volumes/) - Learn how Unity Catalog volumes govern access to non-tabular data, with managed and external options for different storage needs.
- [Schemas](https://docs.databricks.com/schemas/) - Learn about schemas (databases) in Databricks and how they work in Unity Catalog.
- [Lakebase Postgres](https://docs.databricks.com/oltp/projects) - Learn how to work with Lakebase Postgres, a managed Postgres online transaction processing (OLTP) database for the Databricks platform.
- [Workspace navigation](https://docs.databricks.com/workspace/) - Learn how to navigate a Databricks workspace and access features using the Databricks unified navigation experience.
- [Search for workspace objects](https://docs.databricks.com/search/) - Learn how to search for Databricks workspace objects, including notebooks, queries, dashboards, alerts, files, folders, libraries, tables, jobs, and repos.
- [Catalog Explorer](https://docs.databricks.com/catalog-explorer/) - Use Catalog Explorer to discover and manage data and AI assets on Databricks.
- [Genie](https://docs.databricks.com/genie/) - Learn about Genie, the Databricks AI experience family that includes Genie One for business users, Genie Agents for configuring trusted data and metrics, and Genie Code for developers.
- [Genie One](https://docs.databricks.com/genie-one/) - Learn about Genie One, the simplified Databricks UI for business users that unifies access to AI/BI dashboards, natural language data questions, and Databricks Apps.
- [Genie Agents](https://docs.databricks.com/genie-agents/) - Genie Agents (formerly Genie Spaces) are domain-specific natural-language interfaces where data analysts configure datasets, SQL examples, and instructions so business users can ask questions of their data in plain English.
- [Genie Code](https://docs.databricks.com/genie-code/) - An introduction to Genie Code in Databricks, a data-intelligent AI partner integrated across the workspace and Genie.
- [Genie Code CLI](https://docs.databricks.com/genie-code/genie-code-cli) - Genie Code CLI is a terminal coding agent for data and AI work on Databricks. It works with local files and your Unity Catalog data.
- [Use Genie on mobile](https://docs.databricks.com/genie-one/mobile) - The Databricks Genie mobile app lets business users view dashboards, chat with data, and run Databricks Apps from iOS and Android devices.
- [Use Genie One on desktop](https://docs.databricks.com/genie-one/desktop) - The Genie One desktop app is a native macOS app that opens Genie One on the desktop, so business users can chat with data and work with Genie without a browser.
- [Databricks Genie app for Slack](https://docs.databricks.com/genie-one/genie-slack/) - The Databricks Genie app for Slack lets users ask natural-language data questions in a Slack DM, group, or channel by mentioning @Genie, with channel owners pinning a specific Genie Agent for consistent answers.
- [Databricks AI assistive features](https://docs.databricks.com/databricks-ai/) - Learn about Databricks AI assistive features, ready-to-use capabilities including Genie Code and Genie Agents that provide intelligent support across Databricks workspaces.
- [Notebooks](https://docs.databricks.com/notebooks/) - Overview of Databricks notebooks for data science, machine learning, and collaborative development.
- [Notebook widgets](https://docs.databricks.com/notebooks/widgets) - Learn how to use input widgets to add parameters to your notebooks and dashboards.
- [Compute resources](https://docs.databricks.com/compute/) - Learn about the types of Databricks compute available in your workspace.
- [Compute configuration reference](https://docs.databricks.com/compute/configure) - Learn about the compute configuration settings available in Databricks.
- [Instance pools](https://docs.databricks.com/compute/pool-index) - Learn what Databricks pools are and how to use them.
- [GPU compute](https://docs.databricks.com/compute/gpu) - Learn about GPU-enabled Databricks compute, when to use them, what they require, and how to create them.
- [Serverless compute](https://docs.databricks.com/compute/serverless/) - On-demand compute without infrastructure management
- [Photon engine](https://docs.databricks.com/compute/photon) - Learn about Photon, the Databricks native vectorized query engine that runs SQL workloads faster and reduces your total cost per workload.
- [Files](https://docs.databricks.com/files/) - Learn about options for working with files on Databricks.
- [What are workspace files?](https://docs.databricks.com/files/workspace) - Learn what workspace files are and how to interact with them on Databricks.
- [Libraries](https://docs.databricks.com/libraries/) - Learn how to make third-party or custom code available in Databricks using libraries. Learn about the different modes for installing libraries on Databricks.
- [Databricks Artifact Registry](https://docs.databricks.com/artifact-registry/) - Store and govern container images in Databricks Artifact Registry, discover image versions, and check image acceleration status.
- [Databricks Runtime](https://docs.databricks.com/release-notes/runtime/) - Explore Databricks runtime releases and maintenance updates for runtime releases.
- [Spark overview](https://docs.databricks.com/spark/) - Find links to resources for working with Apache Spark on Databricks, including DataFrames, streaming, language APIs, and configuration options.

## Data sources and formats
- [Data guides](https://docs.databricks.com/guides/) - Learn how to find, access, and work with data on the Databricks Data Intelligence Platform.
- [Data sources overview](https://docs.databricks.com/query/formats/) - Learn how to use Databricks to query data in the lakehouse and external systems.
- [Tables](https://docs.databricks.com/tables/) - Navigate table types, storage formats, and management features in Databricks.
- [Table types](https://docs.databricks.com/tables/types) - Summary of Unity Catalog table types — managed, external, and foreign — and how they differ in storage, management, and governance.
- [Delta change data feed](https://docs.databricks.com/tables/features/change-data-feed) - Learn how to get row-level change information from Delta tables using the Delta change data feed.
- [Apache Iceberg](https://docs.databricks.com/iceberg/) - Learn about the Apache Iceberg table format and how it is supported on Databricks.
- [Managed tables](https://docs.databricks.com/tables/managed) - Learn how to create, query, update, and drop managed tables on Databricks for Delta Lake and Apache Iceberg.
- [External tables](https://docs.databricks.com/tables/external) - Learn how to create, query, update, and drop external tables on Databricks.
- [Transactions](https://docs.databricks.com/transactions/) - Execute multiple SQL statements as a single atomic transaction on Unity Catalog tables on Databricks.
- [Model semi-structured data](https://docs.databricks.com/semi-structured/) - Learn considerations and best practices for storing and modeling semi-structured data on Databricks.
- [Work with unstructured data](https://docs.databricks.com/unstructured/) - Learn how to store, govern, and process unstructured data such as documents, images, and audio on Databricks.
- [OpenSharing](https://docs.databricks.com/query/formats/opensharing) - Learn how to read OpenSharing shared tables using Apache Spark DataFrames in Databricks.
- [Share data between SAP Business Data Cloud (BDC) and Databricks](https://docs.databricks.com/opensharing/sap-bdc/) - Share data bidirectionally between Databricks and SAP Business Data Cloud (BDC) using the SAP BDC Connector over OpenSharing.
- [External access](https://docs.databricks.com/external-access/) - Learn how to access Databricks data from external systems using the Unity REST API and the Iceberg REST catalog.
- [Parquet](https://docs.databricks.com/query/formats/parquet) - Learn how to read data from Apache Parquet files using Databricks.
- [CSV](https://docs.databricks.com/query/formats/csv) - Learn how to read CSV files using Databricks.
- [JSON](https://docs.databricks.com/query/formats/json) - Learn how to read data from JSON files using Databricks.
- [Avro](https://docs.databricks.com/query/formats/avro) - Learn how to read and write data to Avro files using Databricks.
- [ORC](https://docs.databricks.com/query/formats/orc) - Learn how to read data from Apache ORC files using Databricks.
- [XML](https://docs.databricks.com/query/formats/xml) - This article describes how to read and write XML files.
- [Binary files](https://docs.databricks.com/query/formats/binary) - Learn how to read data from binary files using Databricks.
- [Discover data](https://docs.databricks.com/discover/) - Learn how to find datasets, list files, explore data descriptions, and discover tables on Databricks.
- [Sample datasets](https://docs.databricks.com/discover/databricks-datasets) - Learn how to find and use sample datasets within your existing Databricks workspaces.

## Data engineering
- [Data engineering overview](https://docs.databricks.com/data-engineering/) - Learn about engineering data pipelines with Databricks.
- [Change data capture and snapshots](https://docs.databricks.com/data-engineering/what-is-cdc) - Understand change data capture (CDC), snapshots, and slowly changing dimensions (SCD Type 1 and Type 2), and how to process each with AUTO CDC in Lakeflow pipelines.
- [Lakeflow pipelines](https://docs.databricks.com/ldp/) - Learn about Databricks Lakeflow pipelines.
- [Lakeflow pipelines concepts](https://docs.databricks.com/ldp/concepts) - Learn what Databricks Lakeflow pipelines are and the data processing concepts that define them.
- [How to use Lakeflow pipelines](https://docs.databricks.com/ldp/concepts/how-to-use-pipelines) - Learn how you use Lakeflow pipelines across their lifecycle (plan, ingest, transform, operationalize, run, and scale) and the trade-offs behind each stage.
- [Pipeline developer reference](https://docs.databricks.com/ldp/developer/) - Developer reference for Lakeflow pipelines: implement pipelines with the Python or SQL interface, manage dependencies, develop locally, and use metaprogramming.
- [Monitor pipelines](https://docs.databricks.com/ldp/observability/) - Monitor Lakeflow pipelines using the pipeline UI, event log, query history, and event hooks to track updates, data quality, lineage, and streaming metrics.
- [Lakeflow pipelines tutorials](https://docs.databricks.com/ldp/tutorials/) - Step-by-step tutorials for building batch and streaming data pipelines with Lakeflow pipelines, from your first pipeline to CDC, geospatial, and source-controlled bundles.
- [Lakeflow Connect](https://docs.databricks.com/ingestion/overview) - Learn about Databricks Lakeflow Connect, which offers efficient connectors to ingest data from enterprise applications, databases, cloud storage, local files, and more.
- [Standard connectors](https://docs.databricks.com/ingestion/) - Learn about the standard connectors in Databricks Lakeflow Connect, which offer higher levels of ingestion pipeline customization compared to the managed connectors.
- [Managed connectors](https://docs.databricks.com/ingestion/lakeflow-connect/) - Learn about how Databricks Lakeflow Connect managed connectors enable you to ingest data from SaaS applications and databases.
- [Structured streaming](https://docs.databricks.com/structured-streaming/concepts) - Learn core concepts for configuring incremental and near real-time workloads with Structured Streaming.
- [Run your first Structured Streaming workload](https://docs.databricks.com/structured-streaming/tutorial/) - Learn the basics of near real-time and incremental processing with Structured Streaming on Databricks.
- [Real-time mode in Structured Streaming](https://docs.databricks.com/structured-streaming/real-time/) - Real-time mode (RTM) is a Structured Streaming trigger for ultra-low-latency operational workloads, with end-to-end latency as low as five milliseconds.
- [Lakeflow Jobs](https://docs.databricks.com/jobs/) - Learn how to orchestrate data processing, machine learning, and data analysis workflows with Lakeflow Jobs.
- [Job tasks](https://docs.databricks.com/jobs/configure-task) - Learn how to create, configure, and edit tasks in Lakeflow Jobs to orchestrate data processing, machine learning, and analytics pipelines.
- [Job schedules and triggers](https://docs.databricks.com/jobs/triggers) - Run Lakeflow Jobs on a schedule or automatically when files arrive, source tables update, or models update, and combine multiple triggers on one job.
- [Lakeflow Designer](https://docs.databricks.com/designer/) - Learn how to use Lakeflow Designer to visually build data transformation workflows on Databricks with a drag-and-drop canvas.
- [Ingest data from cloud object storage](https://docs.databricks.com/ingestion/cloud-object-storage/) - Learn about options for data ingestion from cloud object storage, including Auto Loader and COPY INTO.
- [Auto Loader](https://docs.databricks.com/ingestion/cloud-object-storage/auto-loader/) - Learn how to ingest data from cloud object storage to the lakehouse with Auto Loader.
- [Lakeflow Connect SaaS connectors](https://docs.databricks.com/ingestion/lakeflow-connect/saas-overview/) - Learn about the SaaS connectors in Lakeflow Connect for ingesting data from enterprise applications.
- [Lakeflow Connect database connectors](https://docs.databricks.com/ingestion/lakeflow-connect/cdc-overview/) - Learn about the database connectors in Lakeflow Connect for ingesting data from relational databases using change data capture (CDC).
- [Managed file source connectors](https://docs.databricks.com/ingestion/lakeflow-connect/file-connectors-overv

Measured from the saved file

Linked document

UTF-8 text size
49.9 KB51086 bytes
Token count
11454o200k_base encoding
Markdown links
267265 distinct URLs
Fenced code blocks
0299 lines in the file

Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.

Project H1
Databricks Documentation

Opening blockquote

Comprehensive documentation for the Databricks Data Intelligence Platform, including guides for data engineering, machine learning, AI, analytics, governance, and administration across all supported cloud platforms.

Context architecture

How the content is divided

15 H2 sections organize 267 parsed Markdown links. 0 links point to .md or .markdown paths; 4 link occurrences use another hostname. Linked destinations have not been recursively validated.

H2 sectionLinksUTF-8 bytesTokens
Overview and getting startedLine 4163117731
Core platformLine 223462611405
Data sources and formatsLine 58233556855
Data engineeringLine 832451311094
Machine learning and AILine 1093677181728
SQL and analyticsLine 147193450762
Data governance and securityLine 1682447781039
Specialized featuresLine 19461217257
AdministrationLine 202142680573
Developer toolsLine 2182751541207
Reference and language-specific guidesLine 247131984464
Troubleshooting and supportLine 2625891194
Migration and best practicesLine 26971279284
Integrations and connectorsLine 278101926455
Additional resourcesLine 29091300288

Nested indexes

1 distinct links point to other llms.txt paths. These are routes to more indexes, not proof their contents were included in this file.

Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.

Embedded material

Code, installation and API examples

Fenced blocks
0 closed
Declared languages
No fenced blocks detected
Package-install commands
0 detected in fenced or inline code
Authentication examples
0 fenced lines match API-key, Authorization, Bearer, OAuth or access-token patterns
HTTP request examples
0 fenced lines match request-method patterns
Authentication links
0 links have authentication-related labels

Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.

Publisher prioritization

The Optional section

No H2 section named “Optional” was detected in this file.

The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.

Machine-readable routes

MCP references and configuration text

MCP-related text was detected in the captured file. 1 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.

These are text and link observations. No MCP server connection, authentication or tool call was tested.

Index and bundle

llms-full.txt companion

Not found at checked URLs

A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.

Change evidence

What can be said about freshness

This capture establishes a baseline. Update frequency cannot be determined from one observation.

Linked release and migration material

4 links have release, changelog, deprecation or migration terms in their labels or paths. These provide places to investigate product changes separately.

File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.

Capture identity and measurement method
Requested endpoint
https://docs.databricks.com/llms.txt
Final endpoint
https://docs.databricks.com/llms.txt
HTTP status
200
Content type
text/plain
Text retrieval
Firecrawl literal text capture
Tokenizer
tiktoken 0.14.0 · o200k_base
SHA-256 of saved UTF-8 text
bd69fa595b9631500ca88b05ddfcb604cab62a15e339aabe98f94c0eef74cd3e

Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.

Related tools and resources

Contact Jon