LlamaIndex
Log in

Find answers from the community

Home
Members
Turtles
T
Turtles
Offline, last seen 3 months ago
Joined September 25, 2024
TTurtles
·

Is llama index threadsafe

Is llama-index threadsafe?
1 comment
L
TTurtles
·

What s the difference between `doc id`

What's the difference between doc_id, ref_doc_id, and document_id as it looks like all vectors are stored with all three, but the difference isn't documented? Additionally, I'm only ever seeing one relationship (id="1") stored for every node, despite next and previous being set on the node object.
71 comments
T
L
TTurtles
·

Found a fun one during

Found a fun one during WeaviateVectorStore construction, but only if the index_name/class_name is included:
3 comments
L
T
TTurtles
·

Batch size

Getting a "batch size should not be larger than 2048" error, but only when use_async=True

Offending Line:
Plain Text
VectorStoreIndex(nodes, storage_context=storage_context, use_async=True)


Error:
Plain Text
File ~/superwallet/env/lib/python3.11/site-packages/tenacity/_asyncio.py:50, in AsyncRetrying.__call__(self, fn, *args, **kwargs)
     49 try:
---> 50     result = await fn(*args, **kwargs)
     51 except BaseException:  # noqa: B902

File ~/superwallet/env/lib/python3.11/site-packages/llama_index/embeddings/openai.py:167, in aget_embeddings(list_of_text, engine, **kwargs)
    158 """Asynchronously get embeddings.
    159 
    160 NOTE: Copied from OpenAI's embedding utils:
   (...)
    165 
    166 """
--> 167 assert len(list_of_text) <= 2048, "The batch size should not be larger than 2048."
    169 # replace newlines, which can negatively affect performance.

AssertionError: The batch size should not be larger than 2048.
10 comments
L
T
j