Log in
Log into community
Find answers from the community
Most posts
Powered by
Hall
Home
Members
Emanuel Ferreira
E
Emanuel Ferreira
Offline
, last seen 3 months ago
Joined September 25, 2024
Contributions
Comments
Replies
E
Emanuel Ferreira
last year
·
https://x.com/jerryjliu0/status/
https://x.com/jerryjliu0/status/1737516362451554696?s=20
Multi doc auto retrieval is siiick 🔥
2 comments
E
L
E
Emanuel Ferreira
last year
·
very interesting
very interesting
7 comments
E
S
L
M
E
Emanuel Ferreira
last year
·
do we have an evaluation for this would
do we have an evaluation for this? would be cool to see it and explore more
https://gpt-index.readthedocs.io/en/stable/examples/node_postprocessor/LongContextReorder.html
@Logan M @jerryjliu0 @disiok
1 comment
L
E
Emanuel Ferreira
last year
·
Preparing for the era of 32K context: Ea...
https://together.ai/blog/llama-2-7b-32k?utm_source=bensbites&utm_medium=newsletter&utm_campaign=llms-are-making-robots-smarter
17 comments
L
E
E
Emanuel Ferreira
2 years ago
·
Function calling and other API updates
https://openai.com/blog/function-calling-and-other-api-updates
16k context length option for GPT 3.5
embedding-ada-002 cost reduction by 75%
GPT3.5 25% cost reduction on input tokens
Better functionality for describing how to call a plugind
1 comment
E
E
Emanuel Ferreira
2 years ago
·
OpenAI's plans according to Sam Altman
@jerryjliu0 @Logan M any thoughts about this for the future of llama-index?
reference:
https://humanloop.com/blog/openai-plans
2 comments
j
E
E
Emanuel Ferreira
2 years ago
·
Would be cool to have a way to find the
Would be cool to have a way to find the best practices to query, what's cheaper, how to avoid costs, when to save indexes to disk
2 comments
L
E
E
Emanuel Ferreira
2 years ago
·
have any content about how to index
have any content about how to index faster?
16 comments
E
L
