Jerry Liu
@jerryjliu0
Followers
64K
Following
8K
Media
1K
Statuses
6K
co-founder/CEO @llama_index Careers: https://t.co/EUnMNmbCtx Enterprise: https://t.co/Ht5jwxSrQB
Joined September 2011
Workshop: Build Document-based AI Agents in Finance ๐๐ฆ. Thereโs a lot of great finance agent tools out there (rogo/hebbia/perplexity); this workshop will help provide a code-based foundation so you can build your own custom finance automation workflows - whether itโs deep
Join us for our next webinar!. Transform complex financial documents into actionable data with AI-powered document agents that handle real-world formats like 10-Ks, earnings reports, and regulatory filings. ๐ Build document agents using LlamaCloud's enterprise-grade parsing and
0
8
48
RT @llama_index: Using @claudeai you now have search results as content blocks, bringing citations to agent applications - no more documentโฆ.
0
4
0
RT @llama_index: How @11xAIbuild built Alice, the AI SDR ๐.Onboarding SDRs can take a long time, 11x shrunk this time to days by solving aโฆ.
0
2
0
Automated code reviews with GPT-5 ๐ค. This is an awesome day 0 coding agent by @itsclelia that provides code reviews directly on your @github PRs. The bonus ๐ก: You get direct side-by-side comparisons between GPT-5 and Opus 4.1 by running both models at the same time. Check it
๐ GPT-5 has just been launched and I was really eager to test it :). โ
Test's why I tried it with the new dev tool I built,.๐ฝ๐ฟ-๐ฐ๐ต๐ฒ๐ฐ๐ธ๐ฒ๐ฟ-๐ฎ๐ถ (, which reviews and comments on your PRs on @github using @OpenAI and @AnthropicAI models side-by-side,
1
2
11
RT @llama_index: Improve retrieval accuracy by reranking your LlamaParse PDF results with @ZeroEntropy_AI rerankers ๐. Learn how to enhanceโฆ.
0
2
0
RT @itsclelia: ๐ GPT-5 has just been launched and I was really eager to test it :). โ
Test's why I tried it with the new dev tool I built,โฆ.
0
1
0
We are actively evaluating GPT-5 models on document understanding capabilities ๐๐ - specifically screenshotting the page and feeding it into the model. A WIP preliminary finding is that even though on paper GPT-5 is $1.25 per 1M tokens, it uses 4-5x more tokens than GPT-4.1,
5
3
56
RT @llama_index: Build realtime AI agents that can process live voice data from @Zoom meetings using RTMS and LlamaIndex ๐๏ธ๐ค. Join us for aโฆ.
0
9
0
Coinciding with GPT-5, we're excited to release a fun benchmark called Agent Maze ๐ค๐งฉ - where an agent with minimal tools is expected to solve a procedurally generated maze of varying difficulty. You can toggle various settings like maze depth, branching factor, and various
Hello GPT-5! @OpenAI just announced their latest model ๐ฅ. We have day-0 support: ๐ฝ๐ถ๐ฝ ๐ถ๐ป๐๐๐ฎ๐น๐น -๐จ ๐น๐น๐ฎ๐บ๐ฎ-๐ถ๐ป๐ฑ๐ฒ๐
-๐น๐น๐บ๐-๐ผ๐ฝ๐ฒ๐ป๐ฎ๐ถ. Can GPT-5 find treasure in a maze? Try it out with Agent Maze: an agent with minimal tools, tasked to solve a maze (that we
1
3
12
RT @llama_index: Hello GPT-5! @OpenAI just announced their latest model ๐ฅ. We have day-0 support: ๐ฝ๐ถ๐ฝ ๐ถ๐ป๐๐๐ฎ๐น๐น -๐จ ๐น๐น๐ฎ๐บ๐ฎ-๐ถ๐ป๐ฑ๐ฒ๐
-๐น๐น๐บ๐-๐ผ๐ฝ๐ฒ๐ป๐ฎ๐ถ. Cโฆ.
0
1
0
RT @llama_index: Build enterprise AI applications with LlamaCloud Index and connect them to intelligent tool calling agents that can handleโฆ.
0
7
0
Weโre excited to introduce a new parsing mode within LlamaCloud that lets you get complex visual recognition capabilities over documents ๐ผ๏ธ๐ at a cheaper price compared to pretty much anything else out there โก๏ธ. Thereโs a variety of VLM-enabled document parsing solutions out
0
8
35
RT @llama_index: ๐ค @AnthropicAI just dropped Claude Opus 4.1 and we have day-zero support for it, you just have to run:. ๐ฑ๐ช๐ฑ ๐ช๐ฏ๐ด๐ต๐ข๐ญ๐ญ -๐ ๐ญ๐ญ๐ขโฆ.
0
5
0
RT @llama_index: Build automated invoice processing systems using LlamaIndex document agents and LlamaCloud. Extract, validate, and processโฆ.
0
11
0
RT @MarcusSchiesser: @AnthropicAI released Claude 4.1 Opus and here's how to use it with @llama_index TS:
0
2
0
Delphi (@withdelphi) solves a core need that I find myself struggling with when trying to write with AI - it is extremely hard and tedious getting ChatGPT/Claude to not only generate relevant content, but also match the style and tone of my blogs ๐. Delphi offers a concept of
LlamaCloud's parsing capabilities help AI companies scale from prototype to production with complex document ingestion. See how @withdelphi built their "digital minds" mentorship platform using our document intelligence:. ๐ง Best-in-class parsing handles malformed PDFs, embedded
2
6
26
Frontier models, capable of agentic reasoning, can now run on your Macbook Pro ๐งโ๐ป. @OpenAI's release of GPT-OSS 20B and 120B are the biggest releases in open-source this year. Build agentic workflows with @llama_index that run 100% locally! . Huge props to @LoganMarkewich and
๐ @OpenAI just dropped their first open-source LLM since GPT-2!. GPT-OSS-120B & GPT-OSS-20B are here with:. โ
Reasoning that matches o4-mini.โ
Apache 2.0 license.โ
Runs locally.โ
Ready to use with LlamaIndex.The open-source AI game just changed ๐ฅ. Try it out now with
1
25
97
RT @llama_index: ๐ @OpenAI just dropped their first open-source LLM since GPT-2!. GPT-OSS-120B & GPT-OSS-20B are here with:. โ
Reasoning thโฆ.
0
38
0
RT @llama_index: Ready to see how Document Agents handle messy financial documents?. Our upcoming webinar in just 1๏ธโฃ week shows you exactlโฆ.
0
1
0