Uploaded June 2024 | Updated September 2026, 2 hours ago
Hey everyone! Thank you so much for watching the 97th Weaviate Podcast featuring Nils Reimers, Director of Machine Learning at Cohere, and Erika Cardenas, Technology Partner Manager at Weaviate! Erika and I have been super excited about Cohere's latest works to advance RAG and Search and it was amazing getting to pick Nils' brain about all these topics!
We began with the development of Compass! Nils explains the current problem with embeddings as a soup!! For example, imagine embedding this video description, the first part is about the launch of a podcast, whereas this part is about an embedding algorithm -- how do we form representations of multi-aspect chunks of text?
We dove into all the details of this from the distinction of multi-aspect embeddings with LLM or "smart" chunkers, ColBERT, "Embed Small, Retrieve Big", and many other topics as well from Cross Encoder Re-rankers to Data Cleaning with Generative Feedback Loops, RAG Evaluation, Vector Quantization, and more!
Learn more about Nils Reimers: nils-reimers.de
Chapters
0:00 Welcome Nils and Erika!
1:15 Cohere Compass and Embeddings Soup
6:08 Distinction from Embed Small, Retrieve Big
8:55 ColBERT and One Document, Variable-Length Embeddings
10:45 Connected Understanding
14:24 Separating Semantic Chunking with Relationship Embeddings
17:45 The Future of Cross Encoders
22:22 Listwise Rerankers and Ranking Expressions
26:48 More on LLM Chunkers and Multi-Aspect
29:28 Data Cleaning with Generative Feedback Loops
34:20 Synthetic Queries for Reranker Fine-tuning
38:48 RAG Arena and Elo Rating Evaluation
41:30 Eval Advice for RAG in Production
46:53 Evaluation Dashboards in Fine-tuning APIs
52:00 Vector Quantization
Hey everyone! Thank you so much for watching the 97th Weaviate Podcast featuring Nils Reimers, Director of Machine Learning at Cohere, and Erika Cardenas, Technology Partner Manager at Weaviate! Erika and I have been super excited about Cohere's latest works to advance RAG and Search and it was amazing getting to pick Nils' brain about all these topics!
We began with the development of Compass! Nils explains the current problem with embeddings as a soup!! For example, imagine embedding this video description, the first part is about the launch of a podcast, whereas this part is about an embedding algorithm -- how do we form representations of multi-aspect chunks of text?
We dove into all the details of this from the distinction of multi-aspect embeddings with LLM or "smart" chunkers, ColBERT, "Embed Small, Retrieve Big", and many other topics as well from Cross Encoder Re-rankers to Data Cleaning with Generative Feedback Loops, RAG Evaluation, Vector Quantization, and more!
Learn more about Nils Reimers: nils-reimers.de
Chapters
0:00 Welcome Nils and Erika!
1:15 Cohere Compass and Embeddings Soup
6:08 Distinction from Embed Small, Retrieve Big
8:55 ColBERT and One Document, Variable-Length Embeddings
10:45 Connected Understanding
14:24 Separating Semantic Chunking with Relationship Embeddings
17:45 The Future of Cross Encoders
22:22 Listwise Rerankers and Ranking Expressions
26:48 More on LLM Chunkers and Multi-Aspect
29:28 Data Cleaning with Generative Feedback Loops
34:20 Synthetic Queries for Reranker Fine-tuning
38:48 RAG Arena and Elo Rating Evaluation
41:30 Eval Advice for RAG in Production
46:53 Evaluation Dashboards in Fine-tuning APIs
52:00 Vector Quantization
