databricks-python-sdk

Databricks 开发指南

本技能提供有关 Databricks SDK、Databricks Connect、CLI 和 REST API 的指导。

SDK 文档： https://databricks-sdk-py.readthedocs.io/en/latest/ GitHub 仓库： https://github.com/databricks/databricks-sdk-py

---

环境设置

• 使用现有的虚拟环境 .venv，或使用 uv 创建一个
• 对于 Spark 操作：uv pip install databricks-connect
• 对于 SDK 操作：uv pip install databricks-sdk
• Databricks CLI 版本应为 0.278.0 或更高

配置

• 默认配置文件名称：DEFAULT
• 配置文件：~/.databrickscfg
• 环境变量：DATABRICKS_HOST、DATABRICKS_TOKEN

---

Databricks Connect（Spark 操作）

使用 databricks-connect 在本地针对 Databricks 集群运行 Spark 代码。

from databricks.connect import DatabricksSession

# Auto-detects 'DEFAULT' profile from ~/.databrickscfg
spark = DatabricksSession.builder.getOrCreate()

# With explicit profile
spark = DatabricksSession.builder.profile("MY_PROFILE").getOrCreate()

# Use spark as normal
df = spark.sql("SELECT * FROM catalog.schema.table")
df.show()

**重要：**不要设置 .master("local[*]")，这会导致 Databricks Connect 出现问题。

---

直接访问 REST API

对于 SDK 尚不支持或通过 SDK 实现过于复杂的操作，可直接使用 REST API：

from databricks.sdk import WorkspaceClient

w = WorkspaceClient()

# Direct API call using authenticated client
response = w.api_client.do(
    method="GET",
    path="/api/2.0/clusters/list"
)

# POST with body
response = w.api_client.do(
    method="POST",
    path="/api/2.0/jobs/run-now",
    body={"job_id": 123}
)

**适用场景：**有可用的 SDK 方法时，优先使用 SDK 方法。以下情况可使用 api_client.do：

• SDK 尚未支持的新 API 端点
• SDK 抽象难以处理的复杂操作
• 调试或测试原始 API 响应

---

Databricks CLI

# Check version (should be >= 0.278.0)
databricks --version

# Use specific profile
databricks --profile MY_PROFILE clusters list

# Common commands
databricks clusters list
databricks jobs list
databricks workspace ls /Users/me

---

SDK 文档结构

SDK 文档遵循可预测的 URL 模式：

Base: https://databricks-sdk-py.readthedocs.io/en/latest/

Workspace APIs:  /workspace/{category}/{service}.html
Account APIs:    /account/{category}/{service}.html
Authentication:  /authentication.html
DBUtils:         /dbutils.html

Workspace API 类别

类别	服务
compute	clusters, cluster_policies, command_execution, instance_pools, libraries
catalog	catalogs, schemas, tables, volumes, functions, storage_credentials, external_locations
jobs	jobs
sql	warehouses, statement_execution, queries, alerts, dashboards
serving	serving_endpoints
vectorsearch	vector_search_indexes, vector_search_endpoints
pipelines	pipelines
workspace	repos, secrets, workspace, git_credentials
files	files, dbfs
ml	experiments, model_registry

---

身份验证

文档： https://databricks-sdk-py.readthedocs.io/en/latest/authentication.html

环境变量

DATABRICKS_HOST=https://your-workspace.cloud.databricks.com
DATABRICKS_TOKEN=dapi...  # Personal Access Token

代码模式

# Auto-detect credentials from environment
from databricks.sdk import WorkspaceClient
w = WorkspaceClient()

# Explicit token auth
w = WorkspaceClient(
    host="https://your-workspace.cloud.databricks.com",
    token="dapi..."
)

# Azure Service Principal
w = WorkspaceClient(
    host="https://adb-xxx.azuredatabricks.net",
    azure_workspace_resource_id="/subscriptions/.../resourceGroups/.../providers/Microsoft.Databricks/workspaces/...",
    azure_tenant_id="tenant-id",
    azure_client_id="client-id",
    azure_client_secret="secret"
)

# Use a named profile from ~/.databrickscfg
w = WorkspaceClient(profile="MY_PROFILE")

---

核心 API 参考

集群 API

文档： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/compute/clusters.html

# List all clusters
for cluster in w.clusters.list():
    print(f"{cluster.cluster_name}: {cluster.state}")

# Get cluster details
cluster = w.clusters.get(cluster_id="0123-456789-abcdef")

# Create a cluster (returns Wait object)
wait = w.clusters.create(
    cluster_name="my-cluster",
    spark_version=w.clusters.select_spark_version(latest=True),
    node_type_id=w.clusters.select_node_type(local_disk=True),
    num_workers=2
)
cluster = wait.result()  # Wait for cluster to be running

# Or use create_and_wait for blocking call
cluster = w.clusters.create_and_wait(
    cluster_name="my-cluster",
    spark_version="14.3.x-scala2.12",
    node_type_id="i3.xlarge",
    num_workers=2,
    timeout=timedelta(minutes=30)
)

# Start/stop/delete
w.clusters.start(cluster_id="...").result()
w.clusters.stop(cluster_id="...")
w.clusters.delete(cluster_id="...")

作业 API

文档： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/jobs/jobs.html

from databricks.sdk.service.jobs import Task, NotebookTask

# List jobs
for job in w.jobs.list():
    print(f"{job.job_id}: {job.settings.name}")

# Create a job
created = w.jobs.create(
    name="my-job",
    tasks=[
        Task(
            task_key="main",
            notebook_task=NotebookTask(notebook_path="/Users/me/notebook"),
            existing_cluster_id="0123-456789-abcdef"
        )
    ]
)

# Run a job now
run = w.jobs.run_now_and_wait(job_id=created.job_id)
print(f"Run completed: {run.state.result_state}")

# Get run output
output = w.jobs.get_run_output(run_id=run.run_id)

SQL 语句执行

文档： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/sql/statement_execution.html

# Execute SQL query
response = w.statement_execution.execute_statement(
    warehouse_id="abc123",
    statement="SELECT * FROM catalog.schema.table LIMIT 10",
    wait_timeout="30s"
)

# Check status and get results
if response.status.state == StatementState.SUCCEEDED:
    for row in response.result.data_array:
        print(row)

# For large results, fetch chunks
chunk = w.statement_execution.get_statement_result_chunk_n(
    statement_id=response.statement_id,
    chunk_index=0
)

SQL 仓库

文档： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/sql/warehouses.html

# List warehouses
for wh in w.warehouses.list():
    print(f"{wh.name}: {wh.state}")

# Get warehouse
warehouse = w.warehouses.get(id="abc123")

# Create warehouse
created = w.warehouses.create_and_wait(
    name="my-warehouse",
    cluster_size="Small",
    max_num_clusters=1,
    auto_stop_mins=15
)

# Start/stop
w.warehouses.start(id="abc123").result()
w.warehouses.stop(id="abc123").result()

Unity Catalog - 表

文档： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/catalog/tables.html

# List tables in a schema
for table in w.tables.list(catalog_name="main", schema_name="default"):
    print(f"{table.full_name}: {table.table_type}")

# Get table info
table = w.tables.get(full_name="main.default.my_table")
print(f"Columns: {[c.name for c in table.columns]}")

# Check if table exists
exists = w.tables.exists(full_name="main.default.my_table")

Unity Catalog - 目录和架构

文档（目录）： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/catalog/catalogs.html 文档（架构）： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/catalog/schemas.html

# List catalogs
for catalog in w.catalogs.list():
    print(catalog.name)

# Create catalog
w.catalogs.create(name="my_catalog", comment="Description")

# List schemas
for schema in w.schemas.list(catalog_name="main"):
    print(schema.name)

# Create schema
w.schemas.create(name="my_schema", catalog_name="main")

卷

文档： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/catalog/volumes.html

from databricks.sdk.service.catalog import VolumeType

# List volumes
for vol in w.volumes.list(catalog_name="main", schema_name="default"):
    print(f"{vol.full_name}: {vol.volume_type}")

# Create managed volume
w.volumes.create(
    catalog_name="main",
    schema_name="default",
    name="my_volume",
    volume_type=VolumeType.MANAGED
)

# Read volume info
vol = w.volumes.read(name="main.default.my_volume")

文件 API

文档： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/files/files.html

# Upload file to volume
w.files.upload(
    file_path="/Volumes/main/default/my_volume/data.csv",
    contents=open("local_file.csv", "rb")
)

# Download file
with w.files.download(file_path="/Volumes/main/default/my_volume/data.csv") as f:
    content = f.read()

# List directory contents
for entry in w.files.list_directory_contents("/Volumes/main/default/my_volume/"):
    print(f"{entry.name}: {entry.is_directory}")

# Upload/download with progress (parallel)
w.files.upload_from(
    file_path="/Volumes/main/default/my_volume/large.parquet",
    source_path="/local/path/large.parquet",
    use_parallel=True
)

w.files.download_to(
    file_path="/Volumes/main/default/my_volume/large.parquet",
    destination="/local/output/",
    use_parallel=True
)

服务端点（模型服务）

文档： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/serving/serving_endpoints.html

# List endpoints
for ep in w.serving_endpoints.list():
    print(f"{ep.name}: {ep.state}")

# Get endpoint
endpoint = w.serving_endpoints.get(name="my-endpoint")

# Query endpoint
response = w.serving_endpoints.query(
    name="my-endpoint",
    inputs={"prompt": "Hello, world!"}
)

# For chat/completions endpoints
response = w.serving_endpoints.query(
    name="my-chat-endpoint",
    messages=[{"role": "user", "content": "Hello!"}]
)

# Get OpenAI-compatible client
openai_client = w.serving_endpoints.get_open_ai_client()

向量搜索

文档（索引）： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/vectorsearch/vector_search_indexes.html 文档（端点）： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/vectorsearch/vector_search_endpoints.html

# List vector search indexes
for idx in w.vector_search_indexes.list_indexes(endpoint_name="my-vs-endpoint"):
    print(idx.name)

# Query index
results = w.vector_search_indexes.query_index(
    index_name="main.default.my_index",
    columns=["id", "text", "embedding"],
    query_text="search query",
    num_results=10
)
for doc in results.result.data_array:
    print(doc)

管道（Delta Live Tables）

文档： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/pipelines/pipelines.html

# List pipelines
for pipeline in w.pipelines.list_pipelines():
    print(f"{pipeline.name}: {pipeline.state}")

# Get pipeline
pipeline = w.pipelines.get(pipeline_id="abc123")

# Start pipeline update
w.pipelines.start_update(pipeline_id="abc123")

# Stop pipeline
w.pipelines.stop_and_wait(pipeline_id="abc123")

密钥

文档： https://databricks-sdk-py.readthedocs.io/en/latest/workspace/workspace/secrets.html

# List secret scopes
for scope in w.secrets.list_scopes():
    print(scope.name)

# Create scope
w.secrets.create_scope(scope="my-scope")

# Put secret
w.secrets.put_secret(scope="my-scope", key="api-key", string_value="secret123")

# Get secret (returns GetSecretResponse with value)
secret = w.secrets.get_secret(scope="my-scope", key="api-key")

# List secrets in scope (metadata only, not values)
for s in w.secrets.list_secrets(scope="my-scope"):
    print(s.key)

DBUtils

文档： https://databricks-sdk-py.readthedocs.io/en/latest/dbutils.html

# Access dbutils through WorkspaceClient
dbutils = w.dbutils

# File system operations
files = dbutils.fs.ls("/")
dbutils.fs.cp("dbfs:/source", "dbfs:/dest")
dbutils.fs.rm("dbfs:/path", recurse=True)

# Secrets (same as w.secrets but dbutils interface)
value = dbutils.secrets.get(scope="my-scope", key="my-key")

---

常见模式

重要：异步应用（FastAPI 等）

Databricks SDK 完全同步。 所有调用都会阻塞线程。在异步应用（FastAPI、asyncio）中，必须使用 asyncio.to_thread() 封装 SDK 调用，以避免阻塞事件循环。

import asyncio
from databricks.sdk import WorkspaceClient

w = WorkspaceClient()

# WRONG - blocks the event loop
async def get_clusters_bad():
    return list(w.clusters.list())  # BLOCKS!

# CORRECT - runs in thread pool
async def get_clusters_good():
    return await asyncio.to_thread(lambda: list(w.clusters.list()))

# CORRECT - for simple calls
async def get_cluster(cluster_id: str):
    return await asyncio.to_thread(w.clusters.get, cluster_id)

# CORRECT - FastAPI endpoint
from fastapi import FastAPI
app = FastAPI()

@app.get("/clusters")
async def list_clusters():
    clusters = await asyncio.to_thread(lambda: list(w.clusters.list()))
    return [{"id": c.cluster_id, "name": c.cluster_name} for c in clusters]

@app.post("/query")
async def run_query(sql: str, warehouse_id: str):
    # Wrap the blocking SDK call
    response = await asyncio.to_thread(
        w.statement_execution.execute_statement,
        statement=sql,
        warehouse_id=warehouse_id,
        wait_timeout="30s"
    )
    return response.result.data_array

注意： WorkspaceClient().config.host 不是网络调用，只会读取配置。无需封装属性访问。

---

等待长时间运行的操作

from datetime import timedelta

# Pattern 1: Use *_and_wait methods
cluster = w.clusters.create_and_wait(
    cluster_name="test",
    spark_version="14.3.x-scala2.12",
    node_type_id="i3.xlarge",
    num_workers=2,
    timeout=timedelta(minutes=30)
)

# Pattern 2: Use Wait object
wait = w.clusters.create(...)
cluster = wait.result()  # Blocks until ready

# Pattern 3: Manual polling with callback
def progress(cluster):
    print(f"State: {cluster.state}")

cluster = w.clusters.wait_get_cluster_running(
    cluster_id="...",
    timeout=timedelta(minutes=30),
    callback=progress
)

分页

# All list methods return iterators that handle pagination automatically
for job in w.jobs.list():  # Fetches all pages
    print(job.settings.name)

# For manual control
from databricks.sdk.service.jobs import ListJobsRequest
response = w.jobs.list(limit=10)
for job in response:
    print(job)

错误处理

from databricks.sdk.errors import NotFound, PermissionDenied, ResourceAlreadyExists

try:
    cluster = w.clusters.get(cluster_id="invalid-id")
except NotFound:
    print("Cluster not found")
except PermissionDenied:
    print("Access denied")

---

不确定时

如果我不确定某个方法，应当：

1. 检查文档 URL 模式：

   • https://databricks-sdk-py.readthedocs.io/en/latest/workspace/{category}/{service}.html

2. 常见类别：

   • 集群：/workspace/compute/clusters.html
   • 作业：/workspace/jobs/jobs.html
   • 表：/workspace/catalog/tables.html
   • 仓库：/workspace/sql/warehouses.html
   • 服务：/workspace/serving/serving_endpoints.html

3. 在提供有关参数或返回类型的指导之前，先获取并验证信息。

---

快速参考链接

API	文档 URL
身份验证	https://databricks-sdk-py.readthedocs.io/en/latest/authentication.html
集群	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/compute/clusters.html
作业	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/jobs/jobs.html
SQL 仓库	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/sql/warehouses.html
语句执行	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/sql/statement_execution.html
表	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/catalog/tables.html
目录	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/catalog/catalogs.html
架构	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/catalog/schemas.html
卷	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/catalog/volumes.html
文件	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/files/files.html
服务终结点	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/serving/serving_endpoints.html
向量搜索	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/vectorsearch/vector_search_indexes.html
流水线	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/pipelines/pipelines.html
密钥	https://databricks-sdk-py.readthedocs.io/en/latest/workspace/workspace/secrets.html
DBUtils	https://databricks-sdk-py.readthedocs.io/en/latest/dbutils.html

相关技能

• databricks-config - 配置 profile 和身份验证
• databricks-bundles - 通过 DAB 部署资源
• databricks-jobs - 作业编排模式
• databricks-unity-catalog - 目录治理
• databricks-model-serving - 服务终结点管理
• databricks-vector-search - 向量索引操作
• databricks-lakebase-provisioned - 通过 SDK 管理 PostgreSQL