I’m trying to build a RAG system using a vector search index from GCP services on Python.
I have already created the vector search index and deployed the endpoint. Im using below code:

from langchain_google_vertexai import (
    VectorSearchVectorStore,
    VectorSearchVectorStoreDatastore,
)
# TODO : replace 1234567890123456789 with your acutial index ID
my_index = aiplatform.MatchingEngineIndex("1234567890123456789")

# TODO : replace 1234567890123456789 with your acutial endpoint ID
my_index_endpoint = aiplatform.MatchingEngineIndexEndpoint("1234567890123456789")

# Input texts
chunk_texts= [
    "The cat sat on",
    "the mat.",
    "I like to",
    "eat pizza for",
    "dinner.",
    "The sun sets",
    "in the west.",
]

# Create a Vector Store
vector_store = VectorSearchVectorStore.from_components(
    project_id=PROJECT_ID,
    region=REGION,
    gcs_bucket_name=BUCKET,
    index_id=my_index.name,
    endpoint_id=my_index_endpoint.name,
    embedding=embedding_model,
    stream_update=True,
)

# Add vectors and mapped text chunks to your vectore store
vector_store.add_texts(texts=chunk_texts,is_complete_overwrite=True)

Full Error:

AttributeError                            Traceback (most recent call last)

<ipython-input-22-5aa9b7d77460> in <cell line: 19>()
     17 
     18 # Add vectors and mapped text chunks to your vectore store
---> 19 vector_store.add_texts(texts=text_chunks,is_complete_overwrite=True)

3 frames

/usr/local/lib/python3.10/dist-packages/langchain_google_vertexai/vectorstores/vectorstores.py in add_texts(self, texts, metadatas, is_complete_overwrite, **kwargs)
    198         ]
    199 
--> 200         self._document_storage.mset(list(zip(ids, documents)))
    201 
    202         embeddings = self._embeddings.embed_documents(texts)

/usr/local/lib/python3.10/dist-packages/langchain_google_vertexai/vectorstores/document_storage.py in mset(self, key_value_pairs)
     98                 # the input list, in order.
     99                 if isinstance(result, Exception):
--> 100                     raise result
    101         else:
    102             for key, value in key_value_pairs:

/usr/lib/python3.10/concurrent/futures/thread.py in run(self)
     56 
     57         try:
---> 58             result = self.fn(*self.args, **self.kwargs)
     59         except BaseException as exc:
     60             self.future.set_exception(exc)

/usr/local/lib/python3.10/dist-packages/google/cloud/storage/transfer_manager.py in _call_method_on_maybe_pickled_blob(maybe_pickled_blob, method_name, *args, **kwargs)
   1276     else:
   1277         blob = pickle.loads(maybe_pickled_blob)
-> 1278     return getattr(blob, method_name)(*args, **kwargs)
   1279 
   1280 

AttributeError: 'Blob' object has no attribute '_prep_and_do_upload'

langchain_google_vertexai == 1.0.10

The pipeline works when I create a new vector search and deploy a new endpoint, but I encounter an error when attempting to use it from a prebuilt ID.