langchain_community.embeddings.sambanova
.SambaStudioEmbeddingsยถ
- class langchain_community.embeddings.sambanova.SambaStudioEmbeddings[source]ยถ
Bases:
BaseModel
,Embeddings
SambaNova embedding models.
To use, you should have the environment variables
SAMBASTUDIO_EMBEDDINGS_BASE_URL
,SAMBASTUDIO_EMBEDDINGS_PROJECT_ID
,SAMBASTUDIO_EMBEDDINGS_ENDPOINT_ID
,SAMBASTUDIO_EMBEDDINGS_API_KEY
, set with your personal sambastudio variable or pass it as a named parameter to the constructor.Example
from langchain_community.embeddings import SambaStudioEmbeddings embeddings = SambaStudioEmbeddings(sambastudio_embeddings_base_url=base_url, sambastudio_embeddings_project_id=project_id, sambastudio_embeddings_endpoint_id=endpoint_id, sambastudio_embeddings_api_key=api_key) (or) embeddings = SambaStudioEmbeddings()
Create a new model by parsing and validating input data from keyword arguments.
Raises ValidationError if the input data cannot be parsed to form a valid model.
- param API_BASE_PATH = '/api/predict/nlp/'ยถ
Base path to use for the API usage
- param sambastudio_embeddings_api_key: str = ''ยถ
sambastudio api key
- param sambastudio_embeddings_base_url: str = ''ยถ
Base url to use
- param sambastudio_embeddings_endpoint_id: str = ''ยถ
endpoint id on sambastudio for model
- param sambastudio_embeddings_project_id: str = ''ยถ
Project id on sambastudio for model
- async aembed_documents(texts: List[str]) List[List[float]] ยถ
Asynchronous Embed search docs.
- Parameters
texts (List[str]) โ
- Return type
List[List[float]]
- async aembed_query(text: str) List[float] ยถ
Asynchronous Embed query text.
- Parameters
text (str) โ
- Return type
List[float]
- classmethod construct(_fields_set: Optional[SetStr] = None, **values: Any) Model ยถ
Creates a new model setting __dict__ and __fields_set__ from trusted or pre-validated data. Default values are respected, but no other validation is performed. Behaves as if Config.extra = โallowโ was set since it adds all passed values
- Parameters
_fields_set (Optional[SetStr]) โ
values (Any) โ
- Return type
Model
- copy(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, update: Optional[DictStrAny] = None, deep: bool = False) Model ยถ
Duplicate a model, optionally choose which fields to include, exclude and change.
- Parameters
include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ fields to include in new model
exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ fields to exclude from new model, as with values this takes precedence over include
update (Optional[DictStrAny]) โ values to change/add in the new model. Note: the data is not validated before creating the new model: you should trust this data
deep (bool) โ set to True to make a deep copy of the model
self (Model) โ
- Returns
new model instance
- Return type
Model
- dict(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False) DictStrAny ยถ
Generate a dictionary representation of the model, optionally specifying which fields to include or exclude.
- Parameters
include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ
exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ
by_alias (bool) โ
skip_defaults (Optional[bool]) โ
exclude_unset (bool) โ
exclude_defaults (bool) โ
exclude_none (bool) โ
- Return type
DictStrAny
- embed_documents(texts: List[str], batch_size: int = 32) List[List[float]] [source]ยถ
Returns a list of embeddings for the given sentences. :param texts: List of texts to encode :type texts: List[str] :param batch_size: Batch size for the encoding :type batch_size: int
- Returns
List of embeddings for the given sentences
- Return type
List[np.ndarray] or List[tensor]
- Parameters
texts (List[str]) โ
batch_size (int) โ
- embed_query(text: str) List[float] [source]ยถ
Returns a list of embeddings for the given sentences. :param sentences: List of sentences to encode :type sentences: List[str]
- Returns
List of embeddings for the given sentences
- Return type
List[np.ndarray] or List[tensor]
- Parameters
text (str) โ
- classmethod from_orm(obj: Any) Model ยถ
- Parameters
obj (Any) โ
- Return type
Model
- json(*, include: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, exclude: Optional[Union[AbstractSetIntStr, MappingIntStrAny]] = None, by_alias: bool = False, skip_defaults: Optional[bool] = None, exclude_unset: bool = False, exclude_defaults: bool = False, exclude_none: bool = False, encoder: Optional[Callable[[Any], Any]] = None, models_as_dict: bool = True, **dumps_kwargs: Any) unicode ยถ
Generate a JSON representation of the model, include and exclude arguments as per dict().
encoder is an optional function to supply as default to json.dumps(), other arguments as per json.dumps().
- Parameters
include (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ
exclude (Optional[Union[AbstractSetIntStr, MappingIntStrAny]]) โ
by_alias (bool) โ
skip_defaults (Optional[bool]) โ
exclude_unset (bool) โ
exclude_defaults (bool) โ
exclude_none (bool) โ
encoder (Optional[Callable[[Any], Any]]) โ
models_as_dict (bool) โ
dumps_kwargs (Any) โ
- Return type
unicode
- classmethod parse_file(path: Union[str, Path], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) Model ยถ
- Parameters
path (Union[str, Path]) โ
content_type (unicode) โ
encoding (unicode) โ
proto (Protocol) โ
allow_pickle (bool) โ
- Return type
Model
- classmethod parse_obj(obj: Any) Model ยถ
- Parameters
obj (Any) โ
- Return type
Model
- classmethod parse_raw(b: Union[str, bytes], *, content_type: unicode = None, encoding: unicode = 'utf8', proto: Protocol = None, allow_pickle: bool = False) Model ยถ
- Parameters
b (Union[str, bytes]) โ
content_type (unicode) โ
encoding (unicode) โ
proto (Protocol) โ
allow_pickle (bool) โ
- Return type
Model
- classmethod schema(by_alias: bool = True, ref_template: unicode = '#/definitions/{model}') DictStrAny ยถ
- Parameters
by_alias (bool) โ
ref_template (unicode) โ
- Return type
DictStrAny
- classmethod schema_json(*, by_alias: bool = True, ref_template: unicode = '#/definitions/{model}', **dumps_kwargs: Any) unicode ยถ
- Parameters
by_alias (bool) โ
ref_template (unicode) โ
dumps_kwargs (Any) โ
- Return type
unicode
- classmethod update_forward_refs(**localns: Any) None ยถ
Try to update ForwardRefs on fields based on this Model, globalns and localns.
- Parameters
localns (Any) โ
- Return type
None
- classmethod validate(value: Any) Model ยถ
- Parameters
value (Any) โ
- Return type
Model