Keep on to blur preview images; turn off to show them clearly
DeepSeek OCR is powerful but do you even need OCR models for RAG? This vision-based system answers questions directly from PDF images using VLMs and reasoning-based retrieval. No OCR. No chunking. No vectors. Just reasoning. 100% open-source.
More such AI tools and projects in https://t.co/BvTc8nQQW5: Get access to 100+ AI Agent, RAG, LLM, and MCP tutorials with opensource code - All for FREE.
(in this case i would bet on a creative variant of v3: like many experts dropped to maximize throughput).
Reasoning models coming (very) soon. Co-founder @pleiasfr
I figured out something: parents who dress up for Halloween with their kids = 👍🏻👍🏻 Believe me. A lot of parents don’t in a place like Hong Kong
Dad to 2 Girls. Husband. Educator. Builder. Taught "build in public" for 5 years. Now, my mind is on education x kids learning.
https://t.co/bdf7d6SohO
We're sharing/showcasing best of @github projects/repos. Follow to stay in loop. Promoting Open-Source Contributions. UNOFFICIAL, but followed by github
https://t.co/bdf7d6SohO
We're sharing/showcasing best of @github projects/repos. Follow to stay in loop. Promoting Open-Source Contributions. UNOFFICIAL, but followed by github
Since token injection has been likely protected, tokenvestigation continues with alternative methods (token counts/splits). Composer-1 could well be deepseek-derived.
Reasoning models coming (very) soon. Co-founder @pleiasfr