Maverick

just got curious why the previous global

just got curious why the previous global variables (like index, ...) aren't working after the introduction of Settings?

2 comments

MMaverick

@Logan M for Groq what could be the

for Groq what could be the optimal embed_model and tokenizer be?

8 comments

MMaverick

When executing ...

Plain Text

for doc in documents:
    index.insert(doc)

Why do we get stuck w/ ...

Plain Text

2024-01-11 22:49:04,713:INFO - Retrying request to /chat/completions in 0.974549 seconds
2024-01-11 22:49:04,714:INFO - Retrying request to /chat/completions in 0.958529 seconds
2024-01-11 22:50:05,681:INFO - Retrying request to /chat/completions in 1.951599 seconds
2024-01-11 22:50:05,695:INFO - Retrying request to /chat/completions in 1.896280 seconds

Is there any workaround for this?

17 comments

MMaverick

just curious if

just curious if YoutubeTranscriptReader extracts the timestamps, if so how can one access it?

5 comments

MMaverick

Recursive

Found some issues w/ recursive in SimpleDirectoryReader ... does it work out of the box, or does it need any tweaks to make it work?

4 comments

MMaverick

tried multiple RSS links, but it returns

tried multiple RSS links, but it returns [] at all times

9 comments

MMaverick

can v use `tokenizer = GemmaTokenizer.

can v use tokenizer = GemmaTokenizer.from_pretrained(llama2-70b-4096) for a model from Groq

1 comment

MMaverick

I'm on v0.10.x, and doing this, but get

I'm on v0.10.x, and doing this, but get a strange error ...
from llama_index.llms.openai import OpenAI
... and get this ...
ImportError: cannot import name 'LLM' from 'llama_index.core.llms' (unknown location)

9 comments

MMaverick

where can we find the

where can we find the SimpleDirectoryReader now in v0.10.14?

14 comments

MMaverick

I got this `Error: Vector store

I got this Error: Vector store integrations that store text in the vector store are not supported by ref_doc_info yet. does Qdrant not support this?

40 comments

MMaverick