a
    ”˜ëjr  ã                   @   s’   d Z ddlZddlZddlmZ ddlmZ ddlmZ e 	e
¡� ddlZW d  ƒ n1 s`0    Y  G dd„ deeƒZG dd	„ d	eeƒZdS )
zAModule contains a few fake embedding models for testing purposes.é    N)Ú	BaseModel)Úoverride)Ú
Embeddingsc                   @   sd   e Zd ZU dZeed< ee dœdd„Ze	ee
 eee  dœdd„ƒZe	e
ee d	œd
d„ƒZdS )ÚFakeEmbeddingsaL  Fake embedding model for unit testing purposes.

    This embedding model creates embeddings by sampling from a normal distribution.

    Do not use this outside of testing, as it is not a real embedding model.

    Instantiate:
        .. code-block:: python

            from langchain_core.embeddings import FakeEmbeddings

            embed = FakeEmbeddings(size=100)

    Embed single text:
        .. code-block:: python

            input_text = "The meaning of life is 42"
            vector = embed.embed_query(input_text)
            print(vector[:3])

        .. code-block:: python

            [-0.700234640213188, -0.581266257710429, -1.1328482266445354]

    Embed multiple texts:
        .. code-block:: python

            input_texts = ["Document 1...", "Document 2..."]
            vectors = embed.embed_documents(input_texts)
            print(len(vectors))
            # The first 3 coordinates for the first vector
            print(vectors[0][:3])

        .. code-block:: python

            2
            [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257]

    Úsize)Úreturnc                 C   s   t tj ¡ j| jd�ƒS ©N)r   )ÚlistÚnpÚrandomÚdefault_rngÚnormalr   ©Úself© r   ú]/mnt/bigstor/www/usecases/.venv/lib/python3.9/site-packages/langchain_core/embeddings/fake.pyÚ_get_embedding<   s    zFakeEmbeddings._get_embedding©Útextsr   c                    s   ‡ fdd„|D ƒS )Nc                    s   g | ]}ˆ   ¡ ‘qS r   ©r   ©Ú.0Ú_r   r   r   Ú
<listcomp>A   ó    z2FakeEmbeddings.embed_documents.<locals>.<listcomp>r   ©r   r   r   r   r   Úembed_documents?   s    zFakeEmbeddings.embed_documents©Útextr   c                 C   s   |   ¡ S )Nr   ©r   r   r   r   r   Úembed_queryC   s    zFakeEmbeddings.embed_queryN)Ú__name__Ú
__module__Ú__qualname__Ú__doc__ÚintÚ__annotations__r	   Úfloatr   r   Ústrr   r    r   r   r   r   r      s   
(r   c                   @   sz   e Zd ZU dZeed< eee dœdd„Ze	e
edœdd„ƒZeee
 eee  d	œd
d„ƒZee
ee dœdd„ƒZdS )ÚDeterministicFakeEmbeddinga   Deterministic fake embedding model for unit testing purposes.

    This embedding model creates embeddings by sampling from a normal distribution
    with a seed based on the hash of the text.

    Do not use this outside of testing, as it is not a real embedding model.

    Instantiate:
        .. code-block:: python

            from langchain_core.embeddings import DeterministicFakeEmbedding

            embed = DeterministicFakeEmbedding(size=100)

    Embed single text:
        .. code-block:: python

            input_text = "The meaning of life is 42"
            vector = embed.embed_query(input_text)
            print(vector[:3])

        .. code-block:: python

            [-0.700234640213188, -0.581266257710429, -1.1328482266445354]

    Embed multiple texts:
        .. code-block:: python

            input_texts = ["Document 1...", "Document 2..."]
            vectors = embed.embed_documents(input_texts)
            print(len(vectors))
            # The first 3 coordinates for the first vector
            print(vectors[0][:3])

        .. code-block:: python

            2
            [-0.5670477847544458, -0.31403828652395727, -0.5840547508955257]

    r   )Úseedr   c                 C   s   t j |¡}t|j| jd�ƒS r   )r
   r   r   r	   r   r   )r   r*   Úrngr   r   r   r   u   s    z)DeterministicFakeEmbedding._get_embeddingr   c                 C   s   t t |  d¡¡ ¡ dƒd S )z@Get a seed for the random generator, using the hash of the text.zutf-8é   i áõ)r%   ÚhashlibÚsha256ÚencodeÚ	hexdigest)r   r   r   r   Ú	_get_seedz   s    z$DeterministicFakeEmbedding._get_seedr   c                    s   ‡ fdd„|D ƒS )Nc                    s   g | ]}ˆ j ˆ  |¡d �‘qS )©r*   ©r   r1   r   r   r   r   r   �   r   z>DeterministicFakeEmbedding.embed_documents.<locals>.<listcomp>r   r   r   r   r   r      s    z*DeterministicFakeEmbedding.embed_documentsc                 C   s   | j |  |¡d�S )Nr2   r3   r   r   r   r   r    ƒ   s    z&DeterministicFakeEmbedding.embed_queryN)r!   r"   r#   r$   r%   r&   r	   r'   r   Ústaticmethodr(   r1   r   r   r    r   r   r   r   r)   H   s   
)r)   )r$   Ú
contextlibr-   Zpydanticr   Ztyping_extensionsr   Zlangchain_core.embeddingsr   ÚsuppressÚImportErrorÚnumpyr
   r   r)   r   r   r   r   Ú<module>   s   &8