[Feature Request]: Unable to read the created vector database, it needs to rebuild the collection every time.

[mggger]

Do you need to file an issue?

• [X] I have searched the existing issues and this feature is not already filed.
• [X] My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
• [X] I believe this is a legitimate feature request, not just a question. If this is a question, please use the Discussions area.

Is your feature request related to a problem? Please describe.

As shown in the code, each query execution will rebuild the vector store and generate a new local file.

def store_entity_semantic_embeddings(
    entities: list[Entity],
    vectorstore: BaseVectorStore,
) -> BaseVectorStore:
    """Store entity semantic embeddings in a vectorstore."""
    documents = [
        VectorStoreDocument(
            id=entity.id,
            text=entity.description,
            vector=entity.description_embedding,
            attributes=(
                {"title": entity.title, **entity.attributes}
                if entity.attributes
                else {"title": entity.title}
            ),
        )
        for entity in entities
    ]
    vectorstore.load_documents(documents=documents)
    return vectorstore
    
    
def load_documents(
        self, documents: list[VectorStoreDocument], overwrite: bool = True
    ) -> None:
        """Load documents into vector storage."""
        data = [
            {
                "id": document.id,
                "text": document.text,
                "vector": document.vector,
                "attributes": json.dumps(document.attributes),
            }
            for document in documents
            if document.vector is not None
        ]

        if len(data) == 0:
            data = None

        schema = pa.schema([
            pa.field("id", pa.string()),
            pa.field("text", pa.string()),
            pa.field("vector", pa.list_(pa.float64())),
            pa.field("attributes", pa.string()),
        ])
        if overwrite:
            if data:
                self.document_collection = self.db_connection.create_table(
                    self.collection_name, data=data, mode="overwrite"
                )
            else:
                self.document_collection = self.db_connection.create_table(
                    self.collection_name, schema=schema, mode="overwrite"
                )
        else:
            # add data to existing table
            self.document_collection = self.db_connection.open_table(
                self.collection_name
            )
            if data:
                self.document_collection.add(data)
        

Describe the solution you'd like

It is possible to link to an existing vector database and directly retrieve all the documents inside the collection.

Additional context

If necessary, I can provide specific implementation.