MultiModalVectorStoreIndex
based on an in-memory ChromaDB instance. I'm using an AzureOpenAI embedding model and I would like to understand why when I'm retrieving my nodes using as_retriever().retrieve(...)
, all the retrieved nodes have null
embeddings value. I've checked that the related chroma db collection is containing embeddings value (using chroma_collection.query
method )my_nodes_wth_score_lst = my_index.as_retriever().retrieve(my_query)
nodes_lst = [n.node for n in my_nodes_wth_score_lst]
nodes_lst = my_index._get_node_with_embedding(nodes_lst)