Embeddings¶

classibm_watsonx_ai.foundation_models.embeddings.Embeddings(*,model_id,params=None,credentials=None,project_id=None,space_id=None,api_client=None,verify=None,persistent_connection=True,batch_size=1000,concurrency_limit=5,max_retries=None,delay_time=None,retry_status_codes=None)[source]¶

Bases:BaseEmbeddings,WMLResource

Instantiate the embeddings service.

Parameters:

• model_id (str,optional) – the type of model to use

• params (dict,optional) – parameters to use during generate requests, useibm_watsonx_ai.metanames.EmbedTextParamsMetaNames().show() to view the list of MetaNames

• credentials (dict,optional) – credentials for the Watson Machine Learning instance

• project_id (str,optional) – ID of the Watson Studio project

• space_id (str,optional) – ID of the Watson Studio space

• api_client (APIClient,optional) – initialized APIClient object with a set project ID or space ID. If passed,credentials andproject_id/space_id are not required.

• verify (bool orstr,optional) –

  You can pass one of following as verify:

  • the path to a CA_BUNDLE file

  • the path of a directory with certificates of trusted CAs

  • True - default path to truststore will be taken

  • False - no verification will be made

• persistent_connection (bool,optional) – defines whether to keep a persistent connection when evaluating thegenerate, ‘embed_query’, and ‘embed_documents` methods with one promptor batch of prompts that meet the length limit. For more details, seeGenerate embeddings.To close the connection, runembeddings.close_persistent_connection(), defaults to True. Added in 1.1.2.

• batch_size (int,optional) – Number of elements to be embedded sending in one call (used only for sync methods), defaults to 1000

• concurrency_limit (int,optional) – number of requests to be sent in parallel when generating embedding vectors (used only for sync methods), max is 10, defaults to 5

• max_retries (int,optional) – number of retries performed when request was not successful and status code is in retry_status_codes, defaults to 10

• delay_time (float,optional) – delay time to retry request, factor in exponential backoff formula: wx_delay_time * pow(2.0, attempt), defaults to 0.5s

• retry_status_codes (list[int],optional) – list of status codes which will be considered for retry mechanism, defaults to [429, 503, 504, 520]

Note

When thecredentials parameter is passed, one of these parameters is required: [project_id,space_id].

Hint

You can copy the project_id from the Project’s Manage tab (Project -> Manage -> General -> Details).

Example:

fromibm_watsonx_aiimportCredentialsfromibm_watsonx_ai.foundation_modelsimportEmbeddingsfromibm_watsonx_ai.metanamesimportEmbedTextParamsMetaNamesasEmbedParamsfromibm_watsonx_ai.foundation_models.utils.enumsimportEmbeddingTypesembed_params={EmbedParams.TRUNCATE_INPUT_TOKENS:3,EmbedParams.RETURN_OPTIONS:{'input_text':True}}embedding=Embeddings(model_id=EmbeddingTypes.IBM_SLATE_30M_ENG,params=embed_params,credentials=Credentials(api_key=IAM_API_KEY,url="https://us-south.ml.cloud.ibm.com"),project_id="*****")

asyncaembed_documents(texts,params=None)[source]¶

Returns list of embedding vectors for provided texts in an asynchronous manner.

Parameters:

• texts (list[str]) – list of texts for which embedding vectors will be generated, max length is determined by API (for more information, please refer to the documentation:https://cloud.ibm.com/apidocs/watsonx-ai#text-embeddings)

• params (ParamsType |None,optional) – MetaProps for the embedding generation, useibm_watsonx_ai.metanames.EmbedTextParamsMetaNames().show() to view the list of MetaNames, defaults to None

Returns:

list of embedding vectors

Return type:

list[list[float]]

Example:

q=["What is a Generative AI?","Generative AI refers to a type of artificial intelligence that can original content."]embedding_vectors=awaitembedding.aembed_documents(texts=q)print(embedding_vectors)

asyncaembed_query(text,params=None)[source]¶

Returns an embedding vector for a provided text in an asynchronous manner.

Parameters:

• text (str) – text for which embedding vector will be generated

• params (ParamsType |None,optional) – MetaProps for the embedding generation, useibm_watsonx_ai.metanames.EmbedTextParamsMetaNames().show() to view the list of MetaNames, defaults to None

Returns:

embedding vector

Return type:

list[float]

Example:

q="What is a Generative AI?"embedding_vector=awaitembedding.aembed_query(text=q)print(embedding_vector)

asyncagenerate(inputs,params=None)[source]¶

Generate embeddings vectors for the given input with the givenparameters in an asynchronous manner. Returns a REST API response.

Parameters:

• inputs (list[str]) – list of texts for which embedding vectors will be generated, max length is determined by API (for more information, please refer to the documentation:https://cloud.ibm.com/apidocs/watsonx-ai#text-embeddings)

• params (ParamsType |None,optional) – MetaProps for the embedding generation, useibm_watsonx_ai.metanames.EmbedTextParamsMetaNames().show() to view the list of MetaNames, defaults to None

Returns:

scoring results containing generated embeddings vectors

Return type:

dict

close_persistent_connection()[source]¶

Only applicable if persistent_connection was set to True in Embeddings initialization.Calling this method closes the currenthttpx.Client and recreates a newhttpx.Client with default values:timeout: httpx.Timeout(read=30 * 60, write=30 * 60, connect=10, pool=30 * 60)limit: httpx.Limits(max_connections=10, max_keepalive_connections=10, keepalive_expiry=HTTPX_KEEPALIVE_EXPIRY)

embed_documents(texts,params=None,concurrency_limit=5)[source]¶

Returns list of embedding vectors for provided texts.

Parameters:

• texts (list[str]) – list of texts for which embedding vectors will be generated

• params (ParamsType |None,optional) – MetaProps for the embedding generation, useibm_watsonx_ai.metanames.EmbedTextParamsMetaNames().show() to view the list of MetaNames, defaults to None

• concurrency_limit (int,optional) – number of requests to be sent in parallel, max is 10, defaults to 5

Returns:

list of embedding vectors

Return type:

list[list[float]]

Example:

q=["What is a Generative AI?","Generative AI refers to a type of artificial intelligence that can original content."]embedding_vectors=embedding.embed_documents(texts=q)print(embedding_vectors)

embed_query(text,params=None)[source]¶

Returns an embedding vector for a provided text.

Parameters:

• text (str) – text for which embedding vector will be generated

• params (ParamsType |None,optional) – MetaProps for the embedding generation, useibm_watsonx_ai.metanames.EmbedTextParamsMetaNames().show() to view the list of MetaNames, defaults to None

Returns:

embedding vector

Return type:

list[float]

Example:

q="What is a Generative AI?"embedding_vector=embedding.embed_query(text=q)print(embedding_vector)

generate(inputs,params=None,concurrency_limit=5)[source]¶

Generate embeddings vectors for the given input with the givenparameters. Returns a REST API response.

Parameters:

• inputs (list[str]) – list of texts for which embedding vectors will be generated

• params (ParamsType |None,optional) – MetaProps for the embedding generation, useibm_watsonx_ai.metanames.EmbedTextParamsMetaNames().show() to view the list of MetaNames, defaults to None

• concurrency_limit (int,optional) – number of requests to be sent in parallel, max is 10, defaults to 5

Returns:

scoring results containing generated embeddings vectors

Return type:

dict

to_dict()[source]¶

Serialize Embeddings.

Returns:

serializes this Embeddings so that it can be reconstructed byfrom_dict class method.

Return type:

dict

BaseEmbeddings¶

classibm_watsonx_ai.foundation_models.embeddings.base_embeddings.BaseEmbeddings[source]¶

Bases:ABC

LangChain-like embedding function interface.

abstractmethodembed_documents(texts)[source]¶

Embed search docs.

abstractmethodembed_query(text)[source]¶

Embed query text.

classmethodfrom_dict(data,**kwargs)[source]¶

DeserializeBaseEmbeddings into a concrete one using arguments.

Returns:

concrete Embeddings or None if data is incorrect

Return type:

BaseEmbeddings | None

to_dict()[source]¶

Serialize Embeddings.

Returns:

serializes this Embeddings so that it can be reconstructed byfrom_dict class method.

Return type:

dict

Enums¶

classmetanames.EmbedTextParamsMetaNames[source]¶

Set of MetaNames for Foundation Model Embeddings Parameters.

Available MetaNames:

MetaName	Type	Required	Example value
TRUNCATE_INPUT_TOKENS	int	N	2
RETURN_OPTIONS	dict	N	{'input_text':True}

classEmbeddingModels¶

Bases:StrEnum

This represents a dynamically generated Enum for Embedding Models.

Example of getting EmbeddingModels

# GET EmbeddingModels ENUMclient.foundation_models.EmbeddingModels# PRINT dict of Enumsclient.foundation_models.EmbeddingModels.show()

Example Output:

{'SLATE_125M_ENGLISH_RTRVR':'ibm/slate-125m-english-rtrvr',...'SLATE_30M_ENGLISH_RTRVR':'ibm/slate-30m-english-rtrvr'}

Example of initialising Embeddings with EmbeddingModels Enum:

fromibm_watsonx_ai.foundation_modelsimportEmbeddingsembeddings=Embeddings(model_id=client.foundation_models.EmbeddingModels.SLATE_30M_ENGLISH_RTRVR,credentials=Credentials(...),project_id=project_id,)

classibm_watsonx_ai.foundation_models.utils.enums.EmbeddingTypes(value)[source]¶

Bases:Enum

Deprecated since version 1.0.5:UseEmbeddingModels() instead.

Supported embedding models.

Note

You can check the current list of supported embeddings model types of various environments withget_embeddings_model_specs()or by referring to thewatsonx.aidocumentation.