[Question]: Consistently getting rate l...

Question

Hi ! I keep getting rate limit error for Azure Open Ai embedding models ! Anyone has any suggestions to help remove this error I tired following the github issues but none have worked for me so far
https://github.com/run-llama/llama_index/issues/7879

Logan M · Answer

Don't embed things too fast? 😅 You can either ramp up the number of max retries, or ingest things more slowlyembed_model = AzureOpenAIEmbedding(..., max_retries=10) index = VectorStoreIndex(nodes=[], embed_model=embed_model, ...)
for doc in documents: index.insert(doc)

Tush · Answer

Ah ! I did try the max_retries, that did not work. But let me give ingest doc wise. I have 2048 nodes is that a lot to ingest at once, just curious to know ?

Logan M · Answer

I mean, its not a ton per-say. But it really depends on your rate limits

Tush · Answer

Thanks for replying ! I tried doing this way but I am still some error for text nodes.

index = VectorStoreIndex(
nodes = [], storage_context=storage_context, show_progress=True
)
for node in text_nodes[1:]:
index.insert(node)

error : AttributeError: 'TextNode' object has no attribute 'get_doc_id'. Did you mean: 'ref_doc_id'?

Logan M · Answer

insert is for documents

Logan M · Answer

for nodesindex.insert_nodes(...)but you'll probably want to do it one node at a time? or you can batch them (1 at a time will be kinda slow, but not too bad)

Find answers from the community

[Question]: Consistently getting rate l...