o {q i@s ddlZddlmZddlmZmZmZddlmZddl m Z dddd d d d dd Z de fddZ de dee e ffddZddde dee dee e ffddZejee dde ddfddZddde dee dedeee eeefffddZd dgZdS)!N)util)AnyOptionalUnion) Embeddings)Runnablelangchain_openai langchain_awslangchain_coherelangchain_google_vertexailangchain_huggingfacelangchain_mistralailangchain_ollama) azure_openaibedrockcoheregoogle_vertexai huggingface mistralaiollamaopenaireturncCsdddtDS)z3Get formatted list of providers and their packages. css,|]\}}d|d|ddVqdS)z - z: _-N)replace).0ppkgr`/home/app/PaddleOCR-VL/.venv_paddleocr/lib/python3.10/site-packages/langchain/embeddings/base.py s z%_get_provider_list..)join_SUPPORTED_PROVIDERSitemsrrrr _get_provider_lists r% model_namecCsd|vrt}d|d|}t||dd\}}|}|}|tvr5d|dt}t||s=d}t|||fS)aParse a model string into provider and model name components. The model string should be in the format 'provider:model-name', where provider is one of the supported providers. Args: model_name: A model string in the format 'provider:model-name' Returns: A tuple of (provider, model_name) .. code-block:: python _parse_model_string("openai:text-embedding-3-small") # Returns: ("openai", "text-embedding-3-small") _parse_model_string("bedrock:amazon.titan-embed-text-v1") # Returns: ("bedrock", "amazon.titan-embed-text-v1") Raises: ValueError: If the model string is not in the correct format or the provider is unsupported :zInvalid model format 'z'. Model name must be in format 'provider:model-name' Example valid model strings: - openai:text-embedding-3-small - bedrock:amazon.titan-embed-text-v1 - cohere:embed-english-v3.0 Supported providers:  Provider 'E' is not supported. Supported providers and their required packages: Model name cannot be empty)r# ValueErrorsplitlowerstripr%)r& providersmsgprovidermodelrrr _parse_model_strings(  r4r2r3r2cCsz|s d}t||durd|vrt|\}}n|}|s(t}d|}t||tvr9d|dt}t|||fS)Nr+r'zMust specify either: 1. A model string in format 'provider:model-name' Example: 'openai:text-embedding-3-small' 2. Or explicitly set provider from: r)r*)r/r,r4r#r%)r3r2r1r&r0rrr _infer_model_and_providerQs(r6)maxsizercCs(t|sd|d|d}t|dS)z Check if a package is installed.zCould not import z5 python package. Please install it with `pip install `N)r find_spec ImportError)rr1rrr _check_pkgss r;kwargscKs|st}dd|}t|t||d\}}t|}t||dkr5ddlm}|dd|i|S|dkrHdd lm}|dd|i|S|d kr[dd l m } | dd|i|S|d krndd l m } | dd|i|S|dkrddl m} | dd|i|S|dkrddlm} | dd|i|S|dkrddlm} | dd|i|S|dkrddlm}|dd|i|Sd|dt}t|)aInitialize an embeddings model from a model name and optional provider. **Note:** Must have the integration package corresponding to the model provider installed. Args: model: Name of the model to use. Can be either: - A model string like "openai:text-embedding-3-small" - Just the model name if provider is specified provider: Optional explicit provider name. If not specified, will attempt to parse from the model string. Supported providers and their required packages: {_get_provider_list()} **kwargs: Additional model-specific parameters passed to the embedding model. These vary by provider, see the provider-specific documentation for details. Returns: An Embeddings instance that can generate embeddings for text. Raises: ValueError: If the model provider is not supported or cannot be determined ImportError: If the required provider package is not installed .. dropdown:: Example Usage :open: .. code-block:: python # Using a model string model = init_embeddings("openai:text-embedding-3-small") model.embed_query("Hello, world!") # Using explicit provider model = init_embeddings( model="text-embedding-3-small", provider="openai" ) model.embed_documents(["Hello, world!", "Goodbye, world!"]) # With additional parameters model = init_embeddings( "openai:text-embedding-3-small", api_key="sk-..." ) .. versionadded:: 0.3.9 z2Must specify model name. Supported providers are: z, r5rr)OpenAIEmbeddingsr3r)AzureOpenAIEmbeddingsr)VertexAIEmbeddingsr)BedrockEmbeddingsZmodel_idr)CohereEmbeddingsr)MistralAIEmbeddingsr)HuggingFaceEmbeddingsr&r)OllamaEmbeddingsr)r*Nr)r#keysr"r,r6r;rr=r>r r?r r@r rAr rBr rCrrDr%)r3r2r<r0r1r&rr=r>r?r@rArBrCrDrrr init_embeddings~sJ7        rFr) functools importlibrtypingrrrZlangchain_core.embeddingsrZlangchain_core.runnablesrr#strr%tupler4r6 lru_cachelenr;listfloatrF__all__rrrr sN    9  "  k