Databricks AI Bridge Python API

class databricks_ai_bridge.genie.GenieResponse(result: str | pandas.core.frame.DataFrame, query: str | None = '', description: str | None = '', conversation_id: str | None = None, suggested_questions: List[str] | None = None, text_attachment_content: str | None = '')

Bases: object

result: str | DataFrame

query: str | None = ''

description: str | None = ''

conversation_id: str | None = None

suggested_questions: List[str] | None = None

text_attachment_content: str | None = ''

class databricks_ai_bridge.genie.Genie(space_id, client: WorkspaceClient | None = None, truncate_results=False, return_pandas: bool = False)

Bases: object

start_conversation(content)

create_message(conversation_id, content)

poll_for_result(conversation_id, message_id)

ask_question(question, conversation_id: str | None = None)

databricks_ai_bridge.vector_search_retriever_tool.vector_search_retriever_tool_trace(func)

Decorator factory to trace VectorSearchRetrieverTool with the tool name

class databricks_ai_bridge.vector_search_retriever_tool.FilterItem(*, key: str, value: Any)

Bases: BaseModel

key: str

value: Any

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class databricks_ai_bridge.vector_search_retriever_tool.VectorSearchRetrieverToolInput(*, query: str, filters: List[FilterItem] | None = None, **extra_data: Any)

Bases: BaseModel

model_config = {'extra': 'allow'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

query: str

filters: List[FilterItem] | None

class databricks_ai_bridge.vector_search_retriever_tool.VectorSearchRetrieverToolMixin(*, index_name: str, num_results: int = 5, columns: List[str] | None = None, filters: Dict[str, Any] | None = None, query_type: str = 'ANN', tool_name: str | None = None, tool_description: str | None = None, resources: List[Resource] | None = None, workspace_client: WorkspaceClient | None = None, doc_uri: str | None = None, primary_key: str | None = None, include_score: bool | None = False, dynamic_filter: bool = False, reranker: Reranker | None = None, **extra_data: Any)

Bases: BaseModel

Mixin class for Databricks Vector Search retrieval tools. This class provides the common structure and interface that framework-specific implementations should follow.

model_config = {'arbitrary_types_allowed': True, 'extra': 'allow'}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

index_name: str

num_results: int

columns: List[str] | None

filters: Dict[str, Any] | None

query_type: str

tool_name: str | None

tool_description: str | None

resources: List[Resource] | None

workspace_client: WorkspaceClient | None

doc_uri: str | None

primary_key: str | None

include_score: bool | None

dynamic_filter: bool

reranker: Reranker | None

validate_filter_configuration()

Validate that dynamic_filter and filters are not both enabled.

classmethod validate_tool_name(tool_name)