数据与 AI技能

Set up reusable AWS Glue connections to databases, Redshift, Snowflake, and BigQuery. Discover existing connections, configure credentials and networking, then test access through Glue and the intended processing engine to diagnose connection problems.

中文简介正在准备中。当前显示英语简介。

• Register a database connection in AWS Glue
• Connect Glue to Snowflake or BigQuery
• Test an existing connection before use

Design relationship-based applications with Amazon Neptune, from fraud detection and recommendations to knowledge graphs. Get guidance on engine selection, graph modeling, queries, Neo4j migration, and troubleshooting, with resource creation and supported changes requiring explicit confirmation.

中文简介正在准备中。当前显示英语简介。

• Model shared identifiers to detect fraud rings
• Choose an engine for recommendations or knowledge graphs
• Review Neo4j query compatibility before migration

Plan migrations and configure Amazon OpenSearch Service or Serverless for search and analytics. Explore semantic search, which finds meaning beyond keywords, analyze logs and distributed traces, and investigate incidents through natural language questions.

中文简介正在准备中。当前显示英语简介。

• Plan a migration from Solr or Elasticsearch
• Set up semantic search or document retrieval for AI answers
• Analyze logs to investigate errors

Inventory AWS Glue Data Catalog assets across S3 Tables, Redshift-federated catalogs, and remote Iceberg catalogs. Summarize databases, tables, storage locations, formats, and schemas, and flag unregistered or stale tables without running queries.

中文简介正在准备中。当前显示英语简介。

• Taking inventory of catalogs across an AWS account
• Reviewing tables and schemas in a specific database
• Checking data formats and S3 storage locations

Find AWS datasets using a table name, business keyword, column name, or S3 path. Search Glue Data Catalog, S3, S3 Tables, and Redshift to return matching table references, data formats, and storage locations.

中文简介正在准备中。当前显示英语简介。

• Locate a table by name or business keyword
• Find tables containing a specific column
• Look up a catalog table from an S3 path

Run SQL queries with Amazon Athena across Glue, S3 Tables, and Redshift catalogs. Inspect table contents, select query execution settings, and review results alongside query costs, scanned data, and execution time.

中文简介正在准备中。当前显示英语简介。

• Query sales data with SQL
• Inspect unfamiliar tables and sample rows
• Query data across multiple catalogs

Write SQL and troubleshoot Amazon Redshift using its own behavior rather than PostgreSQL assumptions. Covers slow queries, connection and permission errors, data loading, storage growth, and operations for both provisioned clusters and Serverless environments.

中文简介正在准备中。当前显示英语简介。

• Write SQL that follows Redshift-specific behavior
• Investigate slow queries and queue waits
• Diagnose storage growth and disk-full errors

Build and troubleshoot Cloudflare Basin workflows that collect and transform events, store them in R2 tables, manage table metadata, and query data with SQL. Covers Basin Pipelines, Basin Catalog, and Basin SQL.

中文简介正在准备中。当前显示英语简介。

• Collect and transform events into R2 tables
• Manage Iceberg table metadata and maintenance
• Analyze stored events with SQL

Query and analyze logs, device telemetry, and time series in Azure Data Explorer using KQL, its query language. Explore table structures, locate data across candidate sources, summarize events, and investigate trends or related errors.

中文简介正在准备中。当前显示英语简介。

• Summarizing application errors by time period
• Tracking sensor readings over time
• Correlating logs to investigate failures

Helps you use Azure AI services for keyword and vector search, which finds similar meanings, speech transcription, spoken audio generation, and text extraction from documents. Includes service operations and SDK references for implementation.

中文简介正在准备中。当前显示英语简介。

• Combine keyword search with searches for similar meanings
• Transcribe audio and identify who spoke when
• Turn text into spoken audio

Build and deploy AI agents and models in Microsoft Foundry, then evaluate responses, improve instructions, and fine-tune models. The skill also guides troubleshooting, access permissions, and capacity management throughout development and operation.

中文简介正在准备中。当前显示英语简介。

• Build and deploy a Foundry agent
• Evaluate responses and improve agent instructions
• Fine-tune a model with training data

Make local or Azure Blob documents searchable through Foundry IQ knowledge bases. The skill guides setup, retrieval with source citations, connections to existing agents, and diagnosis of configuration problems or unsupported source requests.

中文简介正在准备中。当前显示英语简介。

• Make local documents searchable
• Build a knowledge base from Azure Blob documents
• Retrieve information with source citations

Deploy Azure OpenAI models using defaults or custom settings for version, deployment type, capacity, and content filtering. Check model support and available quota, meaning the subscription's usage allowance, to identify suitable regions and projects.

中文简介正在准备中。当前显示英语简介。

• Deploy a model using default settings
• Choose a model version, capacity, and content filter
• Find regions with enough available capacity

Fine-tune models on Microsoft Foundry with guidance for choosing a training method, preparing and validating datasets, submitting and monitoring jobs, and evaluating and deploying trained models. Compare results with the original model and track token costs.

中文简介正在准备中。当前显示英语简介。

• Choose a fine-tuning method
• Prepare and validate training datasets
• Diagnose poor training results

Implement document processing in TypeScript with Azure Document Intelligence. Extract text, tables, and fields from invoices, receipts, and IDs, or build custom models and classifiers to handle specialized documents and distinguish document types.

中文简介正在准备中。当前显示英语简介。

• Extracting vendor names, totals, and due dates from invoices
• Reading merchant names and line items from receipts
• Extracting text and tables from PDFs

Build AI applications in TypeScript with the Azure AI Projects SDK. The skill guides agent creation and execution, OpenAI client access, and management of connected resources, model deployments, datasets, and search indexes.

中文简介正在准备中。当前显示英语简介。

• Create and run agents with search or code execution tools
• Upload datasets and manage their versions
• Inspect connected resources and deployed models

Build real-time voice assistants in JavaScript or TypeScript with Azure AI. Covers two-way audio streaming, text responses, speech boundary detection, and calling application functions during conversations in Node.js or browsers.

中文简介正在准备中。当前显示英语简介。

• Build a voice-enabled chatbot
• Stream spoken responses alongside text
• Connect application functions to voice conversations

Build document search features in Python with Azure AI Search. Create indexes, upload documents, combine keyword matching with vector search that finds similar meaning, and configure semantic ranking, filters, and search suggestions.

中文简介正在准备中。当前显示英语简介。

• Build document search using keywords and meaning
• Create indexes and upload documents in batches
• Add result filters and search suggestions

Build AI applications on Microsoft Foundry with Python. Create and version agents, connect tools, run response evaluations, and manage project resources such as connections and datasets through the SDK or an OpenAI-compatible client.

中文简介正在准备中。当前显示英语简介。

• Create and version customer support agents
• Add code execution and file search to agents
• Evaluate response fluency and task adherence

Manage Azure Machine Learning resources with Python, from registering data and trained models to creating compute clusters and running training jobs. Includes patterns for pipelines that connect multiple processing steps and reusable training environments.

中文简介正在准备中。当前显示英语简介。

• Register training data and model versions
• Create compute clusters for training
• Run training jobs and monitor logs

Helps implement Python workflows that extract information from documents, images, audio, and video using Azure AI Content Understanding. Covers document text, timed transcripts, video frames, and custom invoice fields for search and automated processing.

中文简介正在准备中。当前显示英语简介。

• Extract document text for search
• Transcribe audio with timestamps
• Retrieve video transcripts and key frames

Build Python features that identify user intent and extract information such as names from conversation text using Azure AI Language. Includes guidance on authentication, request structure, error handling, and proper cleanup of client resources.

中文简介正在准备中。当前显示英语简介。

• Identify user intent in conversation text
• Extract names and other entities from requests
• Add language understanding to a Python application

Implement text analysis in Python with Azure AI Language. Covers sentiment detection, extracting names and key phrases, identifying languages, masking personal information, and extracting medical terms, with examples for batch processing and asynchronous clients.

中文简介正在准备中。当前显示英语简介。

• Analyze sentiment and specific opinions in customer reviews
• Detect and mask personal information in text
• Extract names, organizations, and key phrases from documents

Add text and image moderation to Python applications using Azure AI Content Safety. Analyze harmful content by category and severity, manage custom text blocklists, and use the results to apply thresholds for user submissions or AI outputs.

中文简介正在准备中。当前显示英语简介。

• Check user-submitted text and images
• Analyze AI outputs before displaying them
• Manage custom lists of blocked terms