3fiZddlmZddlmZmZmZmZddlmZddl m Z m Z Gdde Z y)) annotations)AnyListLiteralOptional) Embeddings) DocArrayIndex_check_docarray_importceZdZdZe d ddZe d ddZy) DocArrayHnswSearchz`HnswLib` storage using `DocArray` package. To use it, you should have the ``docarray`` package with version >=0.32.0 installed. You can install it with `pip install docarray`. c tddlm} |jd||||||| | | d | }| ||}|||S)aInitialize DocArrayHnswSearch store. Args: embedding (Embeddings): Embedding function. work_dir (str): path to the location where all the data will be stored. n_dim (int): dimension of an embedding. dist_metric (str): Distance metric for DocArrayHnswSearch can be one of: "cosine", "ip", and "l2". Defaults to "cosine". max_elements (int): Maximum number of vectors that can be stored. Defaults to 1024. index (bool): Whether an index should be built for this field. Defaults to True. ef_construction (int): defines a construction time/accuracy trade-off. Defaults to 200. ef (int): parameter controlling query time/accuracy trade-off. Defaults to 10. M (int): parameter that defines the maximum number of outgoing connections in the graph. Defaults to 16. allow_replace_deleted (bool): Enables replacing of deleted elements with new added ones. Defaults to True. num_threads (int): Sets the number of cpu threads to use. Defaults to 1. **kwargs: Other keyword arguments to be passed to the get_doc_cls method. r)HnswDocumentIndex) dimspace max_elementsindexef_constructionefMallow_replace_deleted num_threads)work_dir)r docarray.indexr _get_doc_cls)cls embeddingrn_dim dist_metricrrrrrrrkwargsrdoc_cls doc_indexs l/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/langchain_community/vectorstores/docarray/hnsw.py from_paramszDocArrayHnswSearch.from_paramsskN  4"#""  %+"7#    /%g.A 9i((Nc | td| td|j|||fi|}|j|||S)a<Create an DocArrayHnswSearch store and insert data. Args: texts (List[str]): Text data. embedding (Embeddings): Embedding function. metadatas (Optional[List[dict]]): Metadata for each text if it exists. Defaults to None. work_dir (str): path to the location where all the data will be stored. n_dim (int): dimension of an embedding. **kwargs: Other keyword arguments to be passed to the __init__ method. Returns: DocArrayHnswSearch Vector Store z&`work_dir` parameter has not been set.z#`n_dim` parameter has not been set.)texts metadatas) ValueErrorr$ add_texts)rr'rr(rrr stores r# from_textszDocArrayHnswSearch.from_textsMsU2  EF F =BC C 8UEfE ey9 r%)cosineiT T)rrrstrrintrzLiteral['cosine', 'ip', 'l2']rr3rboolrr3rr3rr3rr4rr3r rreturnr )NNN)r'z List[str]rrr(zOptional[List[dict]]rz Optional[str]rz Optional[int]r rr5r )__name__ __module__ __qualname____doc__ classmethodr$r,rr%r#r r s  6> "&*6)6)6) 6) 3 6)  6)6)6) 6) 6) $6)6)6) 6)6)p +/"&# (      r%r N) __future__rtypingrrrrlangchain_core.embeddingsr.langchain_community.vectorstores.docarray.baser r r rr%r#r?s$"//0 ``r%