Hacker News Clone
new
|
comments
|
show
|
ask
|
jobs
|
submit
|
github repo
login
Late Chunking: Balancing Precision and Cost in Long Context Retrieval
(
weaviate.io
)
1 points
by
handfuloflight
2 hours ago
|
hide
|
past
|
web
|
1 comment
| favorite
jpcom
1 hour ago
[-]
this is like performing RAG after the query pipeline is done? I'm not sure I understand the mechanisms at work here...
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
reply