jina embeddings v2 base en

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released September 20238K context≈ 6,144 words

A focused text embedding specialist that converts English sentences and passages into dense vector representations, supporting an unusually long 8192-token context window — far beyond what most embedding models handle. It trades multilingual breadth for depth in English, producing embeddings well-suited for semantic search and retrieval tasks. Built on a BERT-style architecture with ALiBi positional encoding to handle that extended context gracefully.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Creative Writing

Moderate

Multimodal

jina embeddings v2 base en

Open WeightModel weights are publicly available — can be downloaded and self-hosted

Released September 20238K context≈ 6,144 words

A focused text embedding specialist that converts English sentences and passages into dense vector representations, supporting an unusually long 8192-token context window — far beyond what most embedding models handle. It trades multilingual breadth for depth in English, producing embeddings well-suited for semantic search and retrieval tasks. Built on a BERT-style architecture with ALiBi positional encoding to handle that extended context gracefully.

Capabilities

Capability scores are AI-generated based on model documentation, benchmarks, and technical specifications. Learn more

Creative Writing

Moderate

Multimodal

Glossary

ALiBi Positional EncodingA technique that helps the model understand the order and position of words in long sequences without needing to add extra position information to each word.ArchitectureThe underlying structural design of a neural network that defines how data flows through layers and components.BERTA foundational neural network architecture designed to understand the meaning of words in context by learning from large amounts of text.BERT-Style ArchitectureA neural network design based on the BERT model that uses transformer layers to understand relationships between words in text by looking at context from all directions.Context WindowThe maximum number of tokens a model can process in a single conversation or prompt.Dense VectorA compact numerical representation where most values are non-zero, used to efficiently store and compare the meaning of text.EmbeddingA dense numerical vector that represents a word, sentence, or concept in a high-dimensional space.EmbeddingsNumerical representations of text that capture semantic meaning, allowing the model to measure similarity between different words or phrases.MultilingualA model trained to understand and generate text in multiple languages, not just English.Positional EncodingA technique that adds explicit time or position information to a model's input to help it understand sequence order and timing.RetrievalThe process of finding and returning relevant documents or information from a database based on a query.Semantic SearchA search method that finds results based on the meaning of text rather than just matching keywords, using embeddings to understand intent.Text EmbeddingA technique that converts text into numerical vectors that capture semantic meaning, allowing the model to understand and compare text similarity.TokenA small unit of text (a word, subword, or punctuation mark) that a language model breaks input into for processing.

Capabilities

Capabilities

Use Case Fit

Glossary