Hi HN,<p>We recently launched ColiVara - a state of the art RAG API that is based on vision LLMs with a state of art performance on both text-heavy documents and visually-complex pages.<p>It outperforms OCR-based pipelines by up to 30%+ on public benchmarks
Benchmark Comparison Chart<p>We thought it might be of interest to you. If you're looking/exploring or know others who are we'd love for you to try it out.<p>Try it out: ColiVara.com<p>View the code: <a href="https://github.com/tjmlabs/ColiVara">https://github.com/tjmlabs/ColiVara</a>