--- title: "Azure AI Search for Python: review, setup & limitations · Undominated.ai" canonical: https://undominated.ai/skills/microsoft-azure-search-documents-py/ description: "Create vector-capable indexes and combine keyword, vector and semantic queries." --- # Azure AI Search for Python: review, setup & limitations · Undominated.ai > Create vector-capable indexes and combine keyword, vector and semantic queries. [← Explore all skills](/skills/) CLOUD DEVELOPMENT / microsoft # Azure AI Search for Python Create vector-capable indexes and combine keyword, vector and semantic queries. [See setup guidance ↓](#setup)[Original source ↗](https://github.com/microsoft/skills/tree/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-search-documents-py) SOURCE REVIEW Reviewed 2026-10-15 Evidence 5 linked sources Publisher microsoft Licence [MIT ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/LICENSE) Revision fc164ba1d7a0 [Read what was—and wasn’t—checked ↓](#review) “Azure AI Search SDK for Python. Use for vector search, hybrid search, semantic ranking, indexing, and skillsets. Triggers: "azure-search-documents", "SearchClient", "SearchIndexClient", "vector search", "hybrid search", "semantic search". ” [microsoft · upstream description ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-search-documents-py/SKILL.md) Our analysis follows below. 01 / THE REASONING ## Why this made the selection. - New code is told to use DefaultAzureCredential. An API key is only for a deployment that has not moved to Entra yet. - Suggesters have to exist when the index is created. The skill says they cannot be added later. - The definition covers field/profile wiring, separate index/query clients and hybrid queries. The setup helper constructs an index and calls create_or_update_index; no index was created. - Build a search schema aligned with the embedding dimension ### A good fit for - Creating a vector index with the bundled script when the search endpoint and, if used, Azure OpenAI deployment already exist. - Keeping an old API-key client only for a service that is not on Entra yet. - Build a search schema aligned with the embedding dimension - Use filters and projections with hybrid retrieval - Choose between direct document upload, merge, upsert and deletion, or use the buffered sender for batch uploads. ### Weigh up before choosing - setup_vector_index.py creates or updates an index in the named service. It does not upload documents. - The default vector width in the script is 1536. A different embedding model needs a different dimension, which the script exposes as a flag rather than detecting. - Integrated vectorization also reads Azure OpenAI endpoint variables. Without --no-vectorizer those are part of the setup. - This review did not execute the resource. - Embedding generation is a placeholder, not a bundled implementation; vector dimensions must match the model and index. - Index writes and schema updates differ from query permissions; create_or_update does not make every schema change valid or nondestructive. - The main pip line omits azure-identity although token-auth examples import it. Agentic retrieval has additional service/version requirements outside this bounded review. - The setup example uses require_envvar=True, so AZURE_TOKEN_CREDENTIALS is required even for local use despite the adjacent prose. Choose and verify the credential chain explicitly. 02 / THE REVIEW RECORD ## What we actually inspected. Source review has boundaries. A clear record is more useful than a “safe” badge. ### Material inspected - .github/plugins/azure-sdk-python/skills/azure-search-documents-py/SKILL.md - .github/plugins/azure-sdk-python/skills/azure-search-documents-py/scripts/setup_vector_index.py - LICENSE - README.md ### Our findings - The script uses DefaultAzureCredential and requires AZURE_SEARCH_ENDPOINT. That is a write to the search service, not a local file. - API keys remain in the skill only as a legacy path. The script itself does not read AZURE_SEARCH_API_KEY. - It does not add a suggester to an index that already exists, and it does not upload or query documents. - The definition covers field/profile wiring, separate index/query clients and hybrid queries. The setup helper constructs an index and calls create_or_update_index; no index was created. ### Not established by this review - The resource was not executed and its tools were not called. - setup_vector_index.py was not run. - No skill execution, authenticated service operation, or outcome benchmark was performed. - Not executed: it was not installed or run. The review applies to the material and revision named here. A newer upstream release can change its behavior. 03 / PUT IT TO WORK ## Add a skill to your workflow. [Upstream setup instructions ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/README.md) DOCUMENTED COMMAND npx skills add microsoft/skills/.github/plugins/azure-sdk-python/skills/azure-search-documents-py Copy command ↗ Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above. Optional: install the reviewed revision Keeps the original source and installer version where recorded, while leaving your AI tools and installation scope for you to choose. npx skills add https://github.com/microsoft/skills/tree/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-search-documents-py Copy reviewed-revision command ↗ - Install the pinned skill directory interactively, retaining its bundled references and scripts. - Install both search and identity dependencies, configure index/data roles and choose actual embedding dimensions. - Validate field capabilities, semantic configuration and per-document indexing results before evaluating query quality. ### Before you start - Python, matching Azure SDK packages and azure-identity - Authorized Azure resources and operation-specific roles ### Compatibility Agents supporting directory-based SKILL.md instructions ### Local instructions; runtime access depends on the workflow - Create/update index schemas, upload documents and query indexed content; optional enrichment/vectorization calls other paid Azure services. ### Cost model The skill is free; service usage and infrastructure can incur charges. 04 / FOLLOW THE EVIDENCE ## The source trail. Our notes are separate from the original resource. Check upstream before adopting a new version. - [Pinned skill definition ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-search-documents-py/SKILL.md) Checked 2026-10-14 https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-search-documents-py/SKILL.md Supports: summary, whySelected, bestFor, limitations, install, access, review - [Publisher repository and installation guidance ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/README.md) Checked 2026-10-14 https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/README.md Supports: install - [MIT licence ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/LICENSE) Checked 2026-10-14 https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/LICENSE Supports: license - [.github/plugins/azure-sdk-python/skills/azure-search-documents-py/scripts/setup_vector_index.py ↗](https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-search-documents-py/scripts/setup_vector_index.py) Checked 2026-10-14 https://github.com/microsoft/skills/blob/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-search-documents-py/scripts/setup_vector_index.py Supports: review, limitations, access, install - [Pinned source sections reviewed in continuation W30 on 2026-10-15 ↗](https://raw.githubusercontent.com/microsoft/skills/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-search-documents-py/SKILL.md) Checked 2026-10-15 https://raw.githubusercontent.com/microsoft/skills/fc164ba1d7a0c10377dbcc1c9ac07253b9329fdb/.github/plugins/azure-sdk-python/skills/azure-search-documents-py/SKILL.md Supports: upstreamDescription, bestFor, review.reviewedAt, review.notTested KEEP COMPARING ## Other approaches to consider. Related by category or shared topics. These are alternatives to inspect, not a measured quality order. [### Azure Blob Storage for Python ↗ Upload, stream and manage blobs using explicit overwrite, metadata and delegated-access choices.](/skills/microsoft-azure-storage-blob-py/)[### Azure Event Hubs for Python ↗ Publish partitioned events and consume streams with explicit checkpoint ownership.](/skills/microsoft-azure-eventhub-py/)[### Azure Identity for Python ↗ Select and diagnose Entra credential chains across development, hosted workloads and delegated access.](/skills/microsoft-azure-identity-py/) [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/) ## Continue your investigation - [Choose a toolkit](/tools/) - [Inspect execution hosts](/agents/) - [Check tool access](/mcp-servers/) - [Check project dependencies](/check-repo/)