Embeddings
Embeddings are dense numerical vector representations of data — such as words, sentences, images, or documents — learned so that semantically similar items are positioned close together in vector space. Produced by a neural network trained on large datasets, embeddings let machines compare, search, and reason about…
20 resources across 1 library
Glossary Terms(20)
Deep Learning
Deep Learning is a subset of machine learning that uses artificial neural networks with many layers ('deep' architectures) to automatically learn hierarchical…
Neural Network
A neural network is a computational model composed of interconnected layers of simple processing units called neurons, loosely inspired by biological brains. E…
RAG
Retrieval-Augmented Generation (RAG) is a technique that combines a language model with an external retrieval system: relevant documents or passages are fetche…
Embeddings
Embeddings are dense numerical vector representations of data — such as words, sentences, images, or documents — learned so that semantically similar items are…
Pinecone
Pinecone is a fully managed, cloud-based vector database designed for storing and querying high-dimensional embeddings at scale. It provides fast approximate n…
ChromaDB
ChromaDB (Chroma) is an open-source embedding/vector database designed to be simple to run locally or embed directly in an application, commonly used for stori…
LlamaIndex
LlamaIndex is an open-source data framework that helps developers connect large language models to external data sources, primarily by building indexes for ret…
Chroma
Chroma is an open-source embedding database designed for storing and querying vector embeddings, commonly used to power retrieval-augmented generation and sema…
Cohere Command
Command is Cohere's family of large language models built for enterprise use cases, particularly retrieval-augmented generation, tool use, and multilingual tex…
Vector Database
A vector database is a database purpose-built to store, index, and search high-dimensional vector embeddings, retrieving items by semantic similarity rather th…
Latent Space
Latent space is the compressed, lower-dimensional vector space a neural network learns internally to represent the underlying (latent) factors of variation in…
AnythingLLM
AnythingLLM is an open-source, full-stack application that turns any set of documents into a chat-with-your-data assistant using retrieval-augmented generation…
PrivateGPT
PrivateGPT is an open-source project that lets users ask questions about their own documents using large language models running entirely on local hardware, wi…
GloVe Embeddings
GloVe (Global Vectors for Word Representation) is an unsupervised word embedding algorithm developed at Stanford that learns dense vector representations of wo…
TF-IDF
TF-IDF (Term Frequency-Inverse Document Frequency) is a numerical statistic used to measure how important a word is to a specific document within a larger coll…
Bag of Words
Bag of Words is a simple text representation technique that converts a document into a vector of word counts or frequencies, disregarding grammar, word order,…
Retrieval-Augmented Fine-Tuning
Retrieval-Augmented Fine-Tuning (RAFT) is a training technique that fine-tunes a language model specifically to answer questions using retrieved documents, tea…
ChatPDF
ChatPDF is a web application that lets users upload a PDF document and ask questions about its contents in a conversational chat interface, using a retrieval-a…
Humata AI
Humata AI is a document analysis platform that allows users to upload files — including PDFs, spreadsheets, and presentations — and ask questions across them i…
PDF.ai
PDF.ai is a web-based tool that turns any uploaded PDF into an interactive chatbot, allowing users to ask questions, request summaries, and extract information…