haive.core.models.vectorstore.VectorStoreConfig

class haive.core.models.vectorstore.VectorStoreConfig(*, name=None, embedding_model=HuggingFaceEmbeddingConfig(provider=<EmbeddingProvider.HUGGINGFACE: 'huggingface'>, model='sentence-transformers/all-mpnet-base-v2', api_key=SecretStr(''), model_kwargs={'device': 'cpu'}, encode_kwargs={}, query_encode_kwargs={}, multi_process=False, cache_folder='/home/will/Projects/haive/resources/embeddings_cache', show_progress=False, use_cache=True), vector_store_provider=VectorStoreProvider.FAISS, vector_store_path='vector_store', vector_store_kwargs=<factory>, documents=<factory>, docstore_path='docstore')[source]

Configuration model for a vector store.

Parameters:
classmethod create_vs_config_from_documents(documents, embedding_model=HuggingFaceEmbeddingConfig(provider=<EmbeddingProvider.HUGGINGFACE: 'huggingface'>, model='sentence-transformers/all-mpnet-base-v2', api_key=SecretStr(''), model_kwargs={'device': 'cpu'}, encode_kwargs={}, query_encode_kwargs={}, multi_process=False, cache_folder='/home/will/Projects/haive/resources/embeddings_cache', show_progress=False, use_cache=True), **kwargs)[source]

Create a VectorStoreConfig from a list of documents.

Parameters:
Return type:

VectorStoreConfig

classmethod create_vs_from_documents(documents, embedding_model=HuggingFaceEmbeddingConfig(provider=<EmbeddingProvider.HUGGINGFACE: 'huggingface'>, model='sentence-transformers/all-mpnet-base-v2', api_key=SecretStr(''), model_kwargs={'device': 'cpu'}, encode_kwargs={}, query_encode_kwargs={}, multi_process=False, cache_folder='/home/will/Projects/haive/resources/embeddings_cache', show_progress=False, use_cache=True), **kwargs)[source]

Create a VectorStore from a list of documents.

Parameters:
Return type:

VectorStoreConfig

add_document(document)[source]

Add a single document to the vector store config.

Parameters:

document (Document)

create_retriever(async_mode=False)[source]

Create a retriever from the vector store.

Parameters:

async_mode (bool)

create_vectorstore(async_mode=False)[source]

Create a vector store instance from this configuration.

Parameters:

async_mode (bool)

docstore_path: str
documents: list[Document]
embedding_model: BaseEmbeddingConfig
model_config: ClassVar[ConfigDict] = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

name: str | None
vector_store_kwargs: dict[str, Any]
vector_store_path: str
vector_store_provider: VectorStoreProvider