Welcome to the Databricks AI Search Python SDK
The Python SDK for Databricks AI Search — the fully managed vector and keyword search service in the Databricks platform. AI Search is the new name for the product previously known as Databricks Vector Search.
Install the canonical package:
pip install databricks-ai-search
The legacy databricks-vectorsearch package continues to work as a thin
re-export shim that emits a DeprecationWarning on import.
API reference
- databricks.ai_search package
AISearchClientAISearchClient.create_delta_sync_index()AISearchClient.create_delta_sync_index_and_wait()AISearchClient.create_direct_access_index()AISearchClient.create_endpoint()AISearchClient.create_endpoint_and_wait()AISearchClient.delete_endpoint()AISearchClient.delete_index()AISearchClient.endpoint_exists()AISearchClient.get_async_index()AISearchClient.get_endpoint()AISearchClient.get_index()AISearchClient.index_exists()AISearchClient.list_endpoints()AISearchClient.list_indexes()AISearchClient.update_endpoint()AISearchClient.update_endpoint_budget_policy()AISearchClient.update_endpoint_usage_policy()AISearchClient.update_index_budget_policy()AISearchClient.update_index_usage_policy()AISearchClient.validate()AISearchClient.wait_for_endpoint()
AISearchIndexAsyncAISearchIndexDatabricksRerankerExperimentalDatabricksFinetunedRerankerAISearchExceptionBadRequestInvalidInputExceptionNotFoundPermissionDeniedResourceConflictResourceDoesNotExistTooManyRequestsVectorSearchExceptionCredentialStrategy