jina embeddings v4 vllm retrieval

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

Released June 2025128K context≈ 96,000 words

A specialist retrieval model that focuses on one job: turning text into dense vector representations for search and similarity tasks. It handles unusually long contexts up to 128k tokens, making it capable of embedding entire documents rather than just short passages. As an open-weight model, it runs on your own infrastructure via vLLM, giving full control over deployment.

Capabilities

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

Multilingual

Moderate

Creative Writing

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

jina embeddings v4 vllm retrieval

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

Released June 2025128K context≈ 96,000 words

A specialist retrieval model that focuses on one job: turning text into dense vector representations for search and similarity tasks. It handles unusually long contexts up to 128k tokens, making it capable of embedding entire documents rather than just short passages. As an open-weight model, it runs on your own infrastructure via vLLM, giving full control over deployment.

Capabilities

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

Multilingual

Moderate

Creative Writing

Use Case Fit

Fit scores are AI-generated based on model capabilities, intended use, and technical specifications. Learn more

Glossary

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.Open-Weight ModelA model whose trained weights are publicly released, allowing anyone to download and run it locally.RetrievalThe process of finding and returning relevant documents or information from a database based on a query.Retrieval ModelA model designed to find and rank the most relevant documents or passages from a large collection based on a query.TokensThe basic units of text that a language model processes, typically representing words or word fragments.vLLMAn inference engine optimized for running large language models efficiently by batching requests and managing memory intelligently.