Text2vecEmbeddings#
- class langchain_community.embeddings.text2vec.Text2vecEmbeddings[source]#
Bases:
Embeddings
,BaseModel
text2vec embedding models.
Install text2vec first, run ‘pip install -U text2vec’. The gitbub repository for text2vec is : shibing624/text2vec
Example
from langchain_community.embeddings.text2vec import Text2vecEmbeddings embedding = Text2vecEmbeddings() embedding.embed_documents([ "This is a CoSENT(Cosine Sentence) model.", "It maps sentences to a 768 dimensional dense vector space.", ]) embedding.embed_query( "It can be used for text matching or semantic search." )
- param device: str | None = None#
- param encoder_type: Any = 'MEAN'#
- param max_seq_length: int = 256#
- param model: Any = None#
- param model_name_or_path: str | None = None#
- 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]