LlamaIndex 🦙

@llama_index

Turn any doc into AI-ready context. The AI research lab for document parsing and extraction. Developer-first APIs. LlamaParse: cloud.llamaindex.ai

llamaindex.ai

加入于 2022年12月

39 正在关注

12.2万关注者

8 附属账号

回复转帖媒体

LlamaIndex 🦙
@llama_index
12小时
OpenDocRouter provides a simple API and SDKs for integrating into your apps. Read our docs (or copy-paste them to your agent) to integrate into any existing codebase in minutes. opendocrouter.ai
2
LlamaIndex 🦙
@llama_index
17小时
We got OCRia-1 generating tokens nearly 10× faster on a single B200. Getting there meant making much better use of the same GPU. We tuned how OCRia-1 runs for the demands of document parsing, testing every change for both speed and accuracy. Some improvements were only 2–5%.
10
LlamaIndex 🦙
@llama_index
10月30日
Agentic Plus now has a new setting: max effort. It's built for your gnarliest documents, where extraction accuracy matters the most. With max effort, Agentic Plus can spend additional compute when needed, zooming in on tricky details like dense charts and diagrams to extract
14
LlamaIndex 🦙
@llama_index
10月29日
We built a haunted house for doc parsers 🎃 Boo Bench is 179 pages that push parsers into repetition loops. One model saw 246 redaction x’s on a page and wrote 23,004 of them. Results in thread! Leaderboard + paper: llamaindex.ai/benchmarks/boo… Dataset: huggingface.co/datasets/llama…
16
LlamaIndex 🦙
@llama_index
10月28日
Is that a table, or just text that happens to line up? If a table has two header rows, should the output preserve both? Parsers make these judgment calls differently. Those differences shape what your agent understands about a document. We built the Document Parsing Protocol
17