LlamaIndex
Log in

Find answers from the community

Home
Members
doughboy
d
doughboy
Offline, last seen 2 months ago
Joined September 25, 2024
ddoughboy
·

Why does LlamaIndex make requests to

Why does LlamaIndex make requests to huggingface.co for config files every single time I fire it up? How can I disable this?
Plain Text
DEBUG:urllib3.connectionpool:Starting new HTTPS connection (1): huggingface.co:443
Starting new HTTPS connection (1): huggingface.co:443
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "HEAD /TheBloke/WestSeverus-7B-DPO-AWQ/resolve/main/config.json HTTP/1.1" 200 0
https://huggingface.co:443 "HEAD /TheBloke/WestSeverus-7B-DPO-AWQ/resolve/main/config.json HTTP/1.1" 200 0
INFO:datasets:PyTorch version 2.1.2 available.
PyTorch version 2.1.2 available.
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "HEAD /TheBloke/WestSeverus-7B-DPO-AWQ/resolve/main/generation_config.json HTTP/1.1" 200 0
https://huggingface.co:443 "HEAD /TheBloke/WestSeverus-7B-DPO-AWQ/resolve/main/generation_config.json HTTP/1.1" 200 0
DEBUG:urllib3.connectionpool:https://huggingface.co:443 "HEAD /TheBloke/WestSeverus-7B-DPO-AWQ/resolve/main/tokenizer_config.json HTTP/1.1" 200 0
https://huggingface.co:443 "HEAD /TheBloke/WestSeverus-7B-DPO-AWQ/resolve/main/tokenizer_config.json HTTP/1.1" 200 0
init took 4.84630s
3 comments
d
L
ddoughboy
·

All this time I thought llama index was

All this time, I thought llama-index was supposed to be a less-bloated alternative to langchain, but, after doing pip install llama-index, I see that langchain is a dependency of llama-index?!? Ugh.
2 comments
b
L
ddoughboy
·

@Logan M TEI is much, much faster when

TEI is much, much faster when using its gRPC interface. Is this supported by LlamaIndex? I can't seem to find any evidence that it is.
1 comment
L
ddoughboy
·

When I reduce `Settings.chunk_size` to

When I reduce Settings.chunk_size to 128, it slows down my TEI embeddings waaay too much, from 2s to 40s.
14 comments
L
d
ddoughboy
·

For each query, I'd like to perform

For each query, I'd like to perform several custom vector retrievals...and control which nodes are selected for the prompt. Would it be best to sublcass VectorIndexRetriever to achieve this?
15 comments
L
d
B
ddoughboy
·

Query

Can I ask LlamaIndex for just its answer—without the prompt, context, Answer: prefix, etc?
22 comments
L
d
ddoughboy
·

Overview

Your docs say that LanceDB doesn't offer hybrid search, but that isn't true anymore. Will changes need to be made to LlamaIndex before we can use LanceDB's new hybrid search feature? https://lancedb.github.io/lancedb/hybrid_search/hybrid_search/
2 comments
d
L
ddoughboy
·

Semantic

Is it possible to integrate a semantic text splitter with LlamaIndex? https://pypi.org/project/semantic-text-splitter/
13 comments
M
L
d
ddoughboy
·

Release v2.6.0 - Embedding Quantization,...

Quantized text embeddings are here! However, I'm not sure how to take advantage of them when using LlamaIndex + TEI. https://github.com/UKPLab/sentence-transformers/releases/tag/v2.6.0
1 comment
L
ddoughboy
·

I see `Using default LlamaCPP llama2 13b

I see Using default LlamaCPP=llama2-13b-chat when following the tutorial. What if I want to use TheBloke/Platypus2-70B-Instruct-GPTQ instead? Having a hard time finding any info on llama-index + GPTQ.
20 comments
d
b
L
ddoughboy
·

So the name changed from gpt index to

So the name changed from gpt-index to llama-index, yet all the documentation's examples require an OpenAI API key?
13 comments
d
b
L