FZfzysingularity·Feb 27, 2025
We’re adding this as we speak. Ollama support is already there, and here’s vLLM inference: https://github.com/vlm-run/vlmrun-hub/pull/120
In Replace OCR with Vision Language Modelsvlm-run
vlmrun-hub
Python2025–2025
vlm-run / vlmrun-hub
vlmrun-hub
A hub for various industry-specific schemas to be used with VLMs.
2Distinct people
9Mentions
0Explicit recommenders
555GitHub stars
What to know before exploring
What it is
A hub for various industry-specific schemas to be used with VLMs.
GitHub
Where it is used
No documented product use has been verified yet.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by 6-hour interval9 dated mentions
Observed mentions: 2025-02-20 01:54:10 UTC to 2025-02-27 05:01:36 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| Feb 20, 00:00 | 2025-02-20 00:00:00 UTC | 2025-02-20 06:00:00 UTC | 1 | 1 | 0 |
| Feb 20, 06:00 | 2025-02-20 06:00:00 UTC | 2025-02-20 12:00:00 UTC | 3 | 0 | 3 |
| Feb 20, 12:00 | 2025-02-20 12:00:00 UTC | 2025-02-20 18:00:00 UTC | 0 | 0 | 0 |
| Feb 20, 18:00 | 2025-02-20 18:00:00 UTC | 2025-02-21 00:00:00 UTC | 0 | 0 | 0 |
| Feb 21, 00:00 | 2025-02-21 00:00:00 UTC | 2025-02-21 06:00:00 UTC | 0 | 0 | 0 |
| Feb 21, 06:00 | 2025-02-21 06:00:00 UTC | 2025-02-21 12:00:00 UTC | 0 | 0 | 0 |
| Feb 21, 12:00 | 2025-02-21 12:00:00 UTC | 2025-02-21 18:00:00 UTC | 0 | 0 | 0 |
| Feb 21, 18:00 | 2025-02-21 18:00:00 UTC | 2025-02-22 00:00:00 UTC | 0 | 0 | 0 |
| Feb 22, 00:00 | 2025-02-22 00:00:00 UTC | 2025-02-22 06:00:00 UTC | 0 | 0 | 0 |
| Feb 22, 06:00 | 2025-02-22 06:00:00 UTC | 2025-02-22 12:00:00 UTC | 0 | 0 | 0 |
| Feb 22, 12:00 | 2025-02-22 12:00:00 UTC | 2025-02-22 18:00:00 UTC | 1 | 0 | 1 |
| Feb 22, 18:00 | 2025-02-22 18:00:00 UTC | 2025-02-23 00:00:00 UTC | 0 | 0 | 0 |
| Feb 23, 00:00 | 2025-02-23 00:00:00 UTC | 2025-02-23 06:00:00 UTC | 0 | 0 | 0 |
| Feb 23, 06:00 | 2025-02-23 06:00:00 UTC | 2025-02-23 12:00:00 UTC | 0 | 0 | 0 |
| Feb 23, 12:00 | 2025-02-23 12:00:00 UTC | 2025-02-23 18:00:00 UTC | 0 | 0 | 0 |
| Feb 23, 18:00 | 2025-02-23 18:00:00 UTC | 2025-02-24 00:00:00 UTC | 0 | 0 | 0 |
| Feb 24, 00:00 | 2025-02-24 00:00:00 UTC | 2025-02-24 06:00:00 UTC | 0 | 0 | 0 |
| Feb 24, 06:00 | 2025-02-24 06:00:00 UTC | 2025-02-24 12:00:00 UTC | 0 | 0 | 0 |
| Feb 24, 12:00 | 2025-02-24 12:00:00 UTC | 2025-02-24 18:00:00 UTC | 0 | 0 | 0 |
| Feb 24, 18:00 | 2025-02-24 18:00:00 UTC | 2025-02-25 00:00:00 UTC | 0 | 0 | 0 |
| Feb 25, 00:00 | 2025-02-25 00:00:00 UTC | 2025-02-25 06:00:00 UTC | 0 | 0 | 0 |
| Feb 25, 06:00 | 2025-02-25 06:00:00 UTC | 2025-02-25 12:00:00 UTC | 0 | 0 | 0 |
| Feb 25, 12:00 | 2025-02-25 12:00:00 UTC | 2025-02-25 18:00:00 UTC | 0 | 0 | 0 |
| Feb 25, 18:00 | 2025-02-25 18:00:00 UTC | 2025-02-26 00:00:00 UTC | 0 | 0 | 0 |
| Feb 26, 00:00 | 2025-02-26 00:00:00 UTC | 2025-02-26 06:00:00 UTC | 0 | 0 | 0 |
| Feb 26, 06:00 | 2025-02-26 06:00:00 UTC | 2025-02-26 12:00:00 UTC | 0 | 0 | 0 |
| Feb 26, 12:00 | 2025-02-26 12:00:00 UTC | 2025-02-26 18:00:00 UTC | 0 | 0 | 0 |
| Feb 26, 18:00 | 2025-02-26 18:00:00 UTC | 2025-02-27 00:00:00 UTC | 2 | 0 | 2 |
| Feb 27, 00:00 | 2025-02-27 00:00:00 UTC | 2025-02-27 06:00:00 UTC | 2 | 0 | 2 |
What Hacker News says
9 sourcesBTW Check out the Gemini qualitative results here in our hub: https://github.com/vlm-run/vlmrun-hub?tab=readme-ov-file#-qu....
It gives you an idea of where today's models fail (Gemini Flash, OpenAI gpt4o+mini, open-source ones like Llama 3.2 Vision, Qwen VL 2.5 etc).
In Replace OCR with Vision Language ModelsYou can try out some of our schemas with Ollama if you want: https://github.com/vlm-run/vlmrun-hub (instructions in Readme)
In Replace OCR with Vision Language ModelsYou can! it works with Ollama https://github.com/vlm-run/vlmrun-hub
At the end of the day its just schemas. You can decide for yourself if its work upgrading to a larger, more expensive model.
In Replace OCR with Vision Language ModelsJust ran them for Qwen2.5-VL: https://github.com/vlm-run/vlmrun-hub/blob/main/tests/benchm...
In Run structured extraction on documents/images locally with Ollama and PydanticAh cool, care to share a few examples? We can probably add those schemas in the next few days if there's enough folks who could benefit from this. A basic invoice schema is already there: https://github.com/vlm-run/vlmrun-hub/blob/main/vlmrun/hub/s...
You can see some of the qualitative results on GPT4o, Gemini, Llama 3.2 11B, Phi-4 here: https://github.com/vlm-run/vlmrun-hub?tab=readme-ov-file#-qu...
In Run structured extraction on documents/images locally with Ollama and PydanticYes, good catch. We'll be adding several more schemas for videos in the next few weeks.
A few video schemas are already added to the main catalog: https://github.com/vlm-run/vlmrun-hub/blob/main/vlmrun/hub/c...
In Run structured extraction on documents/images locally with Ollama and PydanticIs Qwen2.5-VL on Ollama? Could give it a try with a few of the schemas we have.
We’ve locally tested with Llama 3.2 11B Vision on Ollama: https://github.com/vlm-run/vlmrun-hub/blob/main/tests/benchm...
FWIW I think Ollama structured outputs API is quite buggy compared to the HF transformers variant.
In Run structured extraction on documents/images locally with Ollama and PydanticRun structured extraction on documents/images locally with Ollama and Pydantic
170 points · Open discussion