ZhipuAIEmbeddings

class langchain_community.embeddings.zhipuai.ZhipuAIEmbeddings

Bases: BaseModel, Embeddings

ZhipuAI embedding model integration.

Setup:

To use, you should have the zhipuai python package installed, and the environment variable ZHIPU_API_KEY set with your API KEY.

More instructions about ZhipuAi Embeddings, you can get it from https://open.bigmodel.cn/dev/api#vector

pip install -U zhipuai
export ZHIPU_API_KEY="your-api-key"

Key init args — completion params:

model: Optional[str]

Name of ZhipuAI model to use.

api_key: str

Automatically inferred from env var ZHIPU_API_KEY if not provided.

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

Instantiate:

from langchain_community.embeddings import ZhipuAIEmbeddings

embed = ZhipuAIEmbeddings(
    model="embedding-2",
    # api_key="...",
)

Embed single text:

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

[-0.003832892, 0.049372625, -0.035413884, -0.019301128, 0.0068899863, 0.01248398, -0.022153955, 0.006623926, 0.00778216, 0.009558191, ...]

Embed multiple text:

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

[
    [0.0083934665, 0.037985895, -0.06684559, -0.039616987, 0.015481004, -0.023952313, ...],
    [-0.02713102, -0.005470169, 0.032321047, 0.042484466, 0.023290444, 0.02170547, ...]
]

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 api_key: str [Required]

Automatically inferred from env var ZHIPU_API_KEY if not provided.

param dimensions: int | None = None

The number of dimensions the resulting output embeddings should have.

Only supported in embedding-3 and later models.

param model: str = 'embedding-2'

Model name

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]]

Embeds a list of text documents using the AutoVOT algorithm.

Parameters:

texts (List[str]) – A list of text documents to embed.

Returns:

A list of embeddings for each document in the input list. Each embedding is represented as a list of float values.

Return type:

List[List[float]]

embed_query(text: str) → List[float]

Embeds a text using the AutoVOT algorithm.

Parameters:

text (str) – A text to embed.

Returns:

Input document’s embedded list.

Return type:

List[float]