github Azure/azure-sdk-for-python azure-search-documents_12.2.0b1

pre-release48 minutes ago

12.2.0b1 (2026-11-14)

Features Added

  • Added ApiVersion.V2026_11_01_PREVIEW and made 2026-11-01-preview the default.
    Previously advertised API versions remain selectable.
  • Restored explicit ApiVersion.V2026_10_01 selection without changing the November default.
  • Added indexes.types.KnowledgeBaseInput and KnowledgeBaseModelInput for all
    three model variants in dictionary-style knowledge-base inputs, while preserving
    the callable GA indexes.types.KnowledgeBaseModel alias and the legacy
    indexes.types.KnowledgeBase.models list type.
  • Below operations and models are added for graph querying, index configuration, and retrieval:
    • SearchClient.graph (synchronous and asynchronous), including typed provenance,
      diagnostics, evidence, statistics, and explain results.
    • indexes.models.GraphFieldMappings and indexes.models.GraphProfile.
    • indexes.models.KnowledgeSourceGraphExtractionParameters, grounding, and ontology models.
    • knowledgebases.models.AgentRuntimeGraphParams, graph hydration and provenance parameters.
    • knowledgebases.models.KnowledgeBaseGraphSearchActivityRecord and
      knowledgebases.models.KnowledgeBaseGraphSearchReference.
  • Below models and properties are added for retrieval and query configuration:
    • indexes.models.KnowledgeBaseMicrosoftRetriever1Model and
      indexes.models.KnowledgeBaseOpenAICompatibleModel.
    • indexes.models.KnowledgeBaseTool and knowledge-source tool references.
    • indexes.models.OpenAICompatibleVectorizer.
    • indexes.models.SearchIndexKnowledgeSourceFilterHint.auto_configuration and
      SearchIndexKnowledgeSourceFilterHintAutoConfiguration for facet-grounded hints.
    • indexes.models.VectorSearchTopicGraphProfile and none, diverse, and balanced
      vector-query topic-graph models in documents.models.
    • knowledgebases.models.KnowledgeSourceCache and
      knowledgebases.models.KnowledgeSourceOpenAICompatibleVectorizer.
    • models.AgenticSearchOptions, agentic debug information, and QueryType.AGENTIC.
  • Below operations and models are added for asynchronous File knowledge-source ingestion:
    • SearchIndexClient.begin_ingest_knowledge_source_file_multipart and
      SearchIndexClient.begin_ingest_knowledge_source_file_replacement, including async clients.
    • File ingestion operation status/listing, capacity, and error models.
  • Added indexes.models.RandomScoringFunction and RandomScoringParameters.
  • Added indexes.types.ScoringFunctionInput, ScoringProfileInput, and SearchIndexInput
    for random scoring in dictionary-style inputs, while preserving the classic
    ScoringFunction alias and legacy scoring-profile and index field types.
  • Added more_like_this and agentic_options to synchronous and asynchronous
    SearchClient.search. Restored preview query, skill, knowledge-source, and indexer
    surfaces remain present in the generated package.

Breaking Changes

These changes do not impact the API of stable versions such as 12.1.0.
Only code written against a beta version such as 12.1.0b2 may be affected.

  • The service removes stored query_hints and request-time query_hint_overrides
    from indexed knowledge sources other than search-index knowledge sources.
  • The service removes query_hint_processing from knowledge-base activity models
    other than search-index activity models.
  • KnowledgeBaseRetrievalClient.retrieve_stream and its asynchronous equivalent now
    yield typed payloads directly instead of KnowledgeBaseRetrievalEvent envelopes,
    matching the October GA contract.

Bugs Fixed

  • Removed obsolete retrieval TypedDict annotation overrides that advertised unsupported
    queryHintOverrides fields and prevented resolution of the generated search-index query-hint type.
  • Serialized asynchronous buffered uploads and waited for active uploads before
    closing the client.
  • Closed typed retrieval streams when a response callback raises, including
    awaiting asynchronous response cleanup.
  • Corrected graph query samples to pass request identifiers and content negotiation
    through HTTP headers.
  • Preserved existing resource get_* list wrappers after generated method renames.
  • Preserved ScoringFunction.field_name and boost compatibility without adding
    those fields to random scoring.
  • Corrected generated File-ingestion poller namespace references through the
    package's reproducible post-generation workaround.
  • Preserved all buffered indexing actions after request failures and prevented
    asynchronous auto-flush from cancelling its own task.
  • Kept batch wire values synchronized and accepted dictionary batches, including
    custom error mappings during oversized-batch splitting.
  • Preserved the first search response's metadata and continuation across page iteration.
  • Corrected semantic answer and caption enum encoding and threshold separators.
  • Forwarded conditional-delete options for resource names and extra field-helper properties.
  • Preserved buffered client audience, API version, transport options, and schema-client ownership.
  • Restored registered GA model-name aliases, TypedDict and sequence inputs, constructor overloads,
    and the callable indexes.types.KnowledgeBaseModel alias.

Don't miss a new azure-sdk-for-python release

NewReleases is sending notifications on new releases.