菜单
Use for Azure AI in Python: Search, Speech, OpenAI, and Document Intelligence. Helps with search, vector or hybrid search, speech-to-text, text-to-speech, transcription, and OCR using Python-first guidance.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Evaluate agent question/answer behavior with Azure AI Evaluation SDK for Python. Use when: azure-ai-evaluation, Azure AI Evaluation, agent eval, Q/A evaluation, RAG eval, grounded QA evaluation, relevance, groundedness, coherence, fluency, similarity, safety evaluators, simulator, 질문 답변 평가.
Implement, review, migrate, or troubleshoot Microsoft Agent Framework Python observability with OpenTelemetry, traces, logs, metrics, Azure Monitor Application Insights, Aspire Dashboard, console exporters, MCP trace propagation, configure_otel_providers, enable_instrumentation, and GenAI semantic conventions.
Create, update, refactor, explain, or review Microsoft Agent Framework solutions for Python.
| name | azure-ai |
| description | Use for Azure AI in Python: Search, Speech, OpenAI, and Document Intelligence. Helps with search, vector or hybrid search, speech-to-text, text-to-speech, transcription, and OCR using Python-first guidance. |
| license | MIT |
| metadata | {"author":"Microsoft","version":"1.0.1"} |
This skill is Python-only.
| Service | Use When | MCP Tools | CLI |
|---|---|---|---|
| AI Search | Full-text, vector, hybrid search | azure__search | az search |
| Speech | Speech-to-text, text-to-speech | azure__speech | - |
| OpenAI | GPT models, embeddings, DALL-E | - | az cognitiveservices |
| Document Intelligence | Form extraction, OCR | - | - |
When Azure MCP is enabled:
azure__search with command search_index_list - List search indexesazure__search with command search_index_get - Get index detailsazure__search with command search_query - Query search indexazure__speech with command speech_transcribe - Speech to textazure__speech with command speech_synthesize - Text to speechIf Azure MCP is not enabled: Run /azure:setup or enable via /mcp.
| Feature | Description |
|---|---|
| Full-text search | Linguistic analysis, stemming |
| Vector search | Semantic similarity with embeddings |
| Hybrid search | Combined keyword + vector |
| AI enrichment | Entity extraction, OCR, sentiment |
| Feature | Description |
|---|---|
| Speech-to-text | Real-time and batch transcription |
| Text-to-speech | Neural voices, SSML support |
| Speaker diarization | Identify who spoke when |
| Custom models | Domain-specific vocabulary |
For programmatic access to these services, see the condensed SDK guides:
For deep documentation on specific services: