昺hITddlmZmZmZddlmZddlmZmZGddeeZ dS))AnyDictList) Embeddings) BaseModelroot_validatorceZdZUdZeed<dZeed<ede de fdZ dedd fd Z d e ede e e fd Zd ede e fdZd S) AwaEmbeddingszEmbedding documents and queries with Awa DB. Attributes: client: The AwaEmbedding client. model: The name of the model used for embedding. Default is "all-mpnet-base-v2". clientzall-mpnet-base-v2modelvaluesreturnct ddlm}n"#t$r}td|d}~wwxYw||d<|S)z)Validate that awadb library is installed.r) AwaEmbeddingzJCould not import awadb library. Please install it with `pip install awadb`Nr )awadbr ImportError)clsr rexcs j/var/www/html/services/rag-service/venv/lib/python3.11/site-packages/langchain_community/embeddings/awa.pyvalidate_environmentz"AwaEmbeddings.validate_environmentsn  * * * * * * *   =   (<>>x s (#( model_nameNc,||_||j_dS)zSet the model used for embedding. The default model used is all-mpnet-base-v2 Args: model_name: A string which represents the name of model. N)r r r)selfrs r set_modelzAwaEmbeddings.set_model!s  !+ textsc6|j|S)zEmbed a list of documents using AwaEmbedding. Args: texts: The list of texts need to be embedded Returns: List of embeddings, one for each text. )r EmbeddingBatch)rrs rembed_documentszAwaEmbeddings.embed_documents+s{))%000rtextc6|j|S)zCompute query embeddings using AwaEmbedding. Args: text: The text to embed. Returns: Embeddings for the text. )r Embedding)rr s r embed_queryzAwaEmbeddings.embed_query6s{$$T***r)__name__ __module__ __qualname____doc__r__annotations__r strrrrrrfloatrr#rrr r s KKK$E3$$$^ $ 4    ,C,D,,,, 1T#Y 14U 3D 1 1 1 1 + +U + + + + + +rr N) typingrrrlangchain_core.embeddingsrlangchain_core.pydantic_v1rrr r+rrr/s""""""""""000000@@@@@@@@8+8+8+8+8+Iz8+8+8+8+8+r