LlamaIndex has gotten much faster with a big new update (v0.4.6)! 🦙🔥
- Added async support for “tree_summarize” queries; get responses 3-5x faster ⚡️
- Added embedding batching to make vector index construction blazing fast 🏎️💨
run-llama/llama_index
v0.4.6
LlamaIndex v0.4.6
on GitHub
latest releases:
v0.11.11, v0.11.10, v0.11.9...
19 months ago