LlamaIndex Blog
llamaindex.ai · Company blog · on HN since 2023
LlamaIndex's company blog covers its open-source framework and LlamaParse document parsing for building LLM and agent applications over private data.
What HN saysHN commenters compare it with similar tools and point out a parsing error in the sample on its LlamaParse landing page.
21HN people shared it
7linked it in comments
18stories submitted
97story points
5 months agolast shared
2023people per year2026
Most-shared posts
- 1LlamaIndex: Unleash the power of LLMs over your data4 people · 2 points · first shared 2023 · discussion on HN
- 2Show HN: Local Document Parsing for Agents2 people · 12 points · first shared 2026 · 1 comments on HN
- 3RAG is dead, long live agentic retrieval2 people · 6 points · first shared 2025 · 1 comments on HN
- 4LlamaParse Premium2 people · 1 points · first shared 2024 · discussion on HN
- 5Llamaparse2 people · first shared 2025
- 6Python Tooling at Scale: LlamaIndex’s Monorepo Overhaul1 people · 38 points · first shared 2025 · 11 comments on HN
- 7Workflows 1.0: A Lightweight Framework for Agentic systems1 people · 10 points · first shared 2025 · 2 comments on HN
- 8Llama Index: Open-Source RAG Observability with Langfuse1 people · 8 points · first shared 2024 · discussion on HN
- 9Bending without Breaking: optimal design patterns for effective agents1 people · 6 points · first shared 2025 · discussion on HN
- 10Advanced RAG Cheat Sheet from LlamaIndex1 people · 5 points · first shared 2024 · discussion on HN
- 11Markdown Comes to Liteparse1 people · 2 points · first shared 2026 · 1 comments on HN
- 12Data Agents (2023)1 people · 2 points · first shared 2025 · discussion on HN
- 13Is grep all you need? Lexical VS Sematic Search for Agents1 people · 1 points · first shared 2026 · discussion on HN
- 14Streamlining knowledge work with LlamaIndex, Fireworks and MongoDB1 people · 1 points · first shared 2024 · discussion on HN
- 15The Incoming Slopocalypse and the Death(?) Of Open Source1 people · 1 points · first shared 2026 · discussion on HN
What HN people wrote when they linked it
bdcs · 2024-02-09
https://www.llamaindex.ai/ is much better IMO, but it's definitely a case of boilerplate-y, well-supported incumbent vs smaller, better, less supported (e.g. Java vs Python in the 00s or something like that). Depends on your team and your needs.
Also Autogen seems popular and well-ish liked https://microsoft.github.io/autogen/
LangChain definitely has the most market-/mind- share. For example, GCP has a blog post on supporting it: https://cloud.google.com/blog/products/ai-machine-learning/deploy-lang…
rmonvfer · 2023-11-22
How is this any different from LlamaIndex [1]?
[1] https://www.llamaindex.ai
M4v3R · 2025-02-06
The very first (and probably hand-picked & checked) example on your website [0] suffers from the very problem people are talking about here - in "Fiscal 2024" row it contains an error for CEO CAP column. On the image it says "$234.1" but the parsed result says "$234.4". A small error, but error nonetheless. I wonder if we can ever fix these kind of errors with LLM parsing.
[0] https://www.llamaindex.ai/llamaparse
sensanaty · 2025-02-06
There's an error right on your landing page [1] with the parsed document...
It's supposed to say 234.1, not 234.4
https://www.llamaindex.ai/llamaparse
ed · 2024-09-23
I'm on:
Image
- Terminus Research Group, from bghira of SimpleTuner/diffusers https://discord.gg/cSmvcU9Me9
- AI Toolkit https://github.com/ostris/ai-toolkit https://discord.gg/VXmU2f5WEU
- Stable Diffusion https://discord.gg/stablediffusion
LLM
- LLamaIndex https://www.llamaindex.ai https://discord.com/invite/eN6D2HQ4aX
- Nous research https://discord.gg/nousresearch
- LangChain https://discord.gg/hMrfPpUk
Platforms
- Replicate https://discord.gg/replicate
- Fal https://discord.gg/fal-ai
pierre · 2024-09-22
Parsing docs using LVM is the way forward (also see OCR2 paper released last week, people are having ablot of success parsing with fine tunned Qwen2).
The hard part is to prevent the model ignoring some part of the page and halucinations (see some of the gpt4o sample here like the xanax notice:https://www.llamaindex.ai/blog/introducing-llamaparse-premium)
However this model will get better and we may soon have a good pdf to md model.
siquick · 2024-07-30
Llamaparse by LlamaIndex is probably SOTA at the moment and seems to have no problems with tables. Pricing is good at the moment too.
https://www.llamaindex.ai/enterprise