DatabricksEmbeddings#
- class langchain_community.embeddings.databricks.DatabricksEmbeddings[source]#
Bases:
MlflowEmbeddings
Deprecated since version 0.3.3: Use
:class:`~langchain_databricks.DatabricksEmbeddings`
instead. It will be removed in None==1.0.Databricks embeddings.
To use, you should have the
mlflow
python package installed. For more information, see https://mlflow.org/docs/latest/llms/deployments.Example
from langchain_community.embeddings import DatabricksEmbeddings embeddings = DatabricksEmbeddings( target_uri="databricks", endpoint="embeddings", )
- param documents_params: Dict[str, str] = {}#
- param endpoint: str [Required]#
The endpoint to use.
- param query_params: Dict[str, str] = {}#
The parameters to use for documents.
- param target_uri: str = 'databricks'#
The target URI to use. Defaults to
databricks
.
- async aembed_documents(texts: list[str]) list[list[float]] #
Asynchronous Embed search docs.
- Parameters:
texts (list[str]) – List of text to embed.
- Returns:
List of embeddings.
- Return type:
list[list[float]]
- async aembed_query(text: str) list[float] #
Asynchronous Embed query text.
- Parameters:
text (str) – Text to embed.
- Returns:
Embedding.
- Return type:
list[float]
- embed(texts: List[str], params: Dict[str, str]) List[List[float]] #
- Parameters:
texts (List[str])
params (Dict[str, str])
- Return type:
List[List[float]]
- embed_documents(texts: List[str]) List[List[float]] #
Embed search docs.
- Parameters:
texts (List[str]) – List of text to embed.
- Returns:
List of embeddings.
- Return type:
List[List[float]]
- embed_query(text: str) List[float] #
Embed query text.
- Parameters:
text (str) – Text to embed.
- Returns:
Embedding.
- Return type:
List[float]
Examples using DatabricksEmbeddings