How to Benchmark Embedding Models On Your Own Data

Learn really to benchmark embedding models connected your ain information successful this people for beginners. In this course, you will learn: - The limitations of extracting matter from PDF files pinch Python libraries and to lick that pinch the thief of VLMs (Vision Language Models). - How to disagreement the extracted matter into chunks that sphere context. - Generation questions for each chunk utilizing LLMs (Large Language Models). - Use embedding models to create vector representations of the chunks and questions. - Use some unfastened root and proprietary embedding models. - Use llama.cpp to tally models successful the GGUF format locally connected your machine. - Perform the benchmarking of different embedding models utilizing various metrics and statistical tests pinch the thief of ranx. - Plot the vector representations to visualize if clusters are being formed. - Understand really to construe the p-value that a statistical trial provides. - And overmuch more! You tin find the slides, notebook, and scripts successful this GitHub repository: https://github.com/ImadSaddik/Benchmark_Embedding_Models The dataset is disposable here: https://huggingface.co/datasets/ImadSaddik/BenchmarkEmbeddingModelsCourse To link pinch Imad Saddik, cheque retired his societal accounts: LinkedIn: https://www.linkedin.com/in/imadsaddik/ YouTube: https://www.youtube.com/@3CodeCampers Website: https://imadsaddik.com/ ⭐️ Course Contents ⭐️ (0:00:00) About the course (0:06:05) Introduction (0:17:58) Extracting matter from PDF documents (1:01:08) Divide matter into coherent chunks (1:23:10) Generate question-answer pairs from matter chunks (1:38:48) Embed matter chunks and questions (2:17:06) Statistical tests and metrics (3:12:01) Expanding the dataset and adding much languages (3:45:24) Conclusion