Find answers from the community

Y
Yyh
Offline, last seen 3 months ago
Joined September 25, 2024
I create an Indexnode as follows:

Plain Text
indexnode = IndexNode.from_text_node(node, index_id=node.id_)
indexnode.id_ = str(uuid.uuid4())
indexnode.obj = node


Then, I use the following code:

Plain Text
from llama_index.core import StorageContext
storage_context = StorageContext.from_defaults()
index = VectorStoreIndex(
    storage_context=storage_context,
    objects=index_nodes,
)
index.set_index_id("index")
index.storage_context.docstore.add_documents(nodes)
index.storage_context.persist()


However, after running the above code, index.storage_context.docstore.docs['xxxx'].obj is None and cannot be restored by assignment.
This causes my Retriever to be unable to automatically enter into the textNode.
So what is the correct way to save an IndexNode with the obj attribute?
2 comments
Y
L
start_char_idx and end
The previous reason for deletion was: making development of new text splitters/node parsers more complicated than it was worth.
But will it continue to be maintained now or in the future?
2 comments
Y
L
Could you please guide me on how to persist multiple vector indices within the storage context?
11 comments
Y
L
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.

iI am just using the Openailike class, but this information keeps appearing in the terminal and I can't get rid of it. I just need an online model service. How can I remove this notification?
2 comments
L
I noticed that after llamaindex 0.10.20, you switched from Sphinx to MkDocs for documentation. Could you share why you made this change? What were the considerations? Thanks a lot!
3 comments
L
Y