Completed
- Basics of Vector Search with Pinecone
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
The Magic of Multilingual Search with Pinecone Serverless and Inference
Automatically move to the next video in the Classroom when playback concludes
- 1 - Introduction
- 2 - Tatoeba and Multilingual Semantic Search
- 3 - What is Multilingual Semantic Search?
- 4 - Applications of Multilingual Semantic Search
- 5 - How do we achieve multilingual semantic search?
- 6 - A Crash Course in LLMs
- 7 - What are Vectors and Vector Embeddings?
- 8 - Distributional Hypothesis
- 9 - What are LLMs anyway?
- 10 - How does XLM-RoBERTA work?
- 11 - XLM-R: Big Multilingual Datasets
- 12 - XLM-R: Tokenization
- 13 - XLM-R: Masked Language Modeling
- 14 - Getting Doc embeddings
- 15 - Why XLM-R Isn't Enough
- 16 - Multilingual E5 for Multilingual Search Embeddings
- 17 - mE5: Training Data
- 18 - mE5: Weakly Supervised Contrastive Pretraining
- 19 - mE5: Supervised Finetuning and Dataset Distribution
- 20 - Basics of Vector Search with Pinecone
- 21 - Using Pinecone Inference
- 22 - Querying with Pinecone
- 23 - Demo Time: Language Learning with Multilingual Semantic Search
- 24 - Demo Architecture
- 25 - Live walkthrough of Notebook
- 26 - Embedding with Pinecone Inference
- 27 - Batch Embedding and Upsertion
- 28 - Query Embeddings, and cross-lingual search
- 29 - Tips and Tricks for Multilingual Semantic Search
- 30 - QA Time
- 31 - Evaluating Semantic Search
- 32 - Language Embedding Theory
- 33 - What happens for Out of Domain Languages? Transfer Theory
- 34 - Why isn't Translation Sufficient?
- 35 - Handling Negation in Queries
- 36 - Handling Cultural Nuance
- 37 - Low Resource Languages