GitHub

Vector Embedding

LogoHow I Made AI Assistants Do My Work For Me: CrewAIYouTube

What are Vector Embeddings

It is a popular technique to represent 'information' in a format that can be easily processed by algorithms, especially deep learning models. This 'information' can be text, pictures, video and audio.

Each word gets its own vector with a lot of numbers. And the vector depends on the Model that generated them.

  • OpenAI

  • Word2vec

  • GloVe

These vectors help finding data similar to them.

What they are used for?

  • Recommendation systems

  • Anomaly detection

  • Transfer learning

  • Visualizations

  • Information retrieval

  • Audio + Speech processing

  • Facial recognition

Langchain

An open source framework that allows AI developers to have better interactions with several large language models LLMs.

pip install cassio datasets langchain openai tiktoken

  • cassio is a Database solution

PreviousRAG

Last updated