SparkLLMTextEmbeddings#

class langchain_community.embeddings.sparkllm.SparkLLMTextEmbeddings[source]#

Bases: BaseModel, Embeddings

SparkLLM embedding model integration.

Setup:

To use, you should have the environment variable “SPARK_APP_ID”,”SPARK_API_KEY” and “SPARK_API_SECRET” set your APP_ID, API_KEY and API_SECRET or pass it as a name parameter to the constructor.

export SPARK_APP_ID="your-api-id"
export SPARK_API_KEY="your-api-key"
export SPARK_API_SECRET="your-api-secret"

Key init args — completion params:

api_key: Optional[str]: Automatically inferred from env var SPARK_API_KEY if not provided.
app_id: Optional[str]: Automatically inferred from env var SPARK_APP_ID if not provided.
api_secret: Optional[str]: Automatically inferred from env var SPARK_API_SECRET if not provided.
base_url: Optional[str]: Base URL path for API requests.

See full list of supported init args and their descriptions in the params section.

Instantiate:

from langchain_community.embeddings import SparkLLMTextEmbeddings

embed = SparkLLMTextEmbeddings(
    api_key="...",
    app_id="...",
    api_secret="...",
    # other
)

Embed single text:

input_text = "The meaning of life is 42"
embed.embed_query(input_text)

[-0.4912109375, 0.60595703125, 0.658203125, 0.3037109375, 0.6591796875, 0.60302734375, ...]

Embed multiple text:

input_texts = ["This is a test query1.", "This is a test query2."]
embed.embed_documents(input_texts)

[
    [-0.1962890625, 0.94677734375, 0.7998046875, -0.1971435546875, 0.445556640625, 0.54638671875, ...],
    [  -0.44970703125, 0.06585693359375, 0.7421875, -0.474609375, 0.62353515625, 1.0478515625, ...],
]

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param base_url: str = 'https://emb-cn-huabei-1.xf-yun.com/'#: Base URL path for API requests

param domain: Literal['para', 'query'] = 'para'#: This parameter is used for which Embedding this time belongs to. If “para”(default), it belongs to document Embedding. If “query”, it belongs to query Embedding.

param spark_api_key: SecretStr | None [Optional] (alias 'api_key')#: Automatically inferred from env var SPARK_API_KEY if not provided.

param spark_api_secret: SecretStr | None [Optional] (alias 'api_secret')#: Automatically inferred from env var SPARK_API_SECRET if not provided.

param spark_app_id: SecretStr [Optional] (alias 'app_id')#: Automatically inferred from env var SPARK_APP_ID if not provided.

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_documents(texts: List[str]) → List[List[float]] | None[source]#

Public method to get embeddings for a list of documents.

Parameters:: texts (List[str]) – The list of texts to embed.
Returns:: A list of embeddings, one for each text, or None if an error occurs.
Return type:: List[List[float]] | None

embed_query(text: str) → List[float] | None[source]#

Public method to get embedding for a single query text.

Parameters:: text (str) – The text to embed.
Returns:: Embeddings for the text, or None if an error occurs.
Return type:: List[float] | None

Examples using SparkLLMTextEmbeddings