# jina-embeddings-v2-small-en Source: https://zilliz.com/ai-models/jina-embeddings-v2-small-en Published: 2024-08-25T22:16:45.525Z ## Model attributes | Attribute | Value | | --- | --- | | Provider | Jina AI | | Integration | Milvus Integrated | | Task | Embedding | | Modality | Text | | Similarity metric | Any (Normalized) | | License | Apache 2.0 | | Dimensions | 512 | | Max input tokens | 8192 | | Price | Free | ## Introduction to Jina Embedding v2 Models Jina Embeddings v2 models are designed to handle long documents with an expanded max input size of 8,192 tokens. As of October 2024, Jina AI Embedding V2 has the following variants, each catering to different embedding needs: - [jina-embeddings-v2-small-en](https://zilliz.com/ai-models/jina-embeddings-v2-small-en) - [jina-embeddings-v2-base-en](https://zilliz.com/ai-models/jina-embeddings-v2-base-en) - [jina-embeddings-v2-base-zh](https://zilliz.com/ai-models/jina-embeddings-v2-base-zh) - [jina-embeddings-v2-base-de](https://zilliz.com/ai-models/jina-embeddings-v2-base-de) - [jina-embeddings-v2-base-code](https://zilliz.com/ai-models/jina-embeddings-v2-base-code) ## Introduction to jina-embeddings-v2-small-en **jina-embeddings-v2-small-en** is an English monolingual embedding model designed for a sequence length of up to 8192 tokens. It is the smallest variant in the Jina Embeddings v2 family, which has been trained with 33 million parameters and generates 512-dimensional embeddings. Comparing jina-embeddings-v2-small-en with other Jina embedding models. | Model | Parameter Size | Embedding Dimension | Text | | ---------------------------- | -------------- | --------------------------------------- | ----------------------------------------------------------- | | [jina-embeddings-v3](https://zilliz.com/ai-models/jina-embeddings-v3) | 570M | flexible embedding size (Default: 1024) | multilingual text embeddings; supports 94 language in total | | [jina-embeddings-v2-small-en](https://zilliz.com/ai-models/jina-embeddings-v2-small-en) | 33M | 512 | English monolingual embeddings | | [jina-embeddings-v2-base-en](https://zilliz.com/ai-models/jina-embeddings-v2-base-en) | 137M | 768 | English monolingual embeddings | | [jina-embeddings-v2-base-zh](https://zilliz.com/ai-models/jina-embeddings-v2-base-zh) | 161M | 768 | Chinese-English Bilingual embeddings | | [jina-embeddings-v2-base-de](https://zilliz.com/ai-models/jina-embeddings-v2-base-de) | 161M | 768 | German-English Bilingual embeddings | | [jina-embeddings-v2-base-code](https://zilliz.com/ai-models/jina-embeddings-v2-base-code) | 161M | 768 | English and programming languages | ## How to create embeddings with jina-embeddings-v2-small-en There are two primary ways to generate vector embeddings: - [PyMilvus](https://github.com/milvus-io/pymilvus): the Python SDK for [Milvus](https://zilliz.com/what-is-milvus) that seamlessly integrates the `jina-embeddings-v2-small-en` model. - SentenceTransformer library: the Python library `sentence-transformer`. Once the vector embeddings are generated, they can be stored in [Zilliz Cloud](https://zilliz.com/cloud) (a fully managed vector database service powered by Milvus) and used for [semantic similarity search](https://zilliz.com/glossary/semantic-search). Here are four key steps: - [Sign up](https://cloud.zilliz.com/signup) for a Zilliz Cloud account for free. - [Set up a serverless cluster](https://docs.zilliz.com/docs/create-cluster#set-up-a-free-cluster) and obtain the [Public Endpoint and API Key](https://docs.zilliz.com/docs/on-zilliz-cloud-console#free-cluster-details). - Create a vector collection and insert your vector embeddings. - Run a semantic search on the stored embeddings. ### Create embeddings via PyMilvus ``` from pymilvus.model.dense import SentenceTransformerEmbeddingFunction from pymilvus import MilvusClient ef = SentenceTransformerEmbeddingFunction("jinaai/jina-embeddings-v2-small-en", trust_remote_code=True) docs = [ "Artificial intelligence was founded as an academic discipline in 1956.", "Alan Turing was the first person to conduct substantial research in AI.", "Born in Maida Vale, London, Turing was raised in southern England." ] # Generate embeddings for documents docs_embeddings = ef(docs) queries = ["When was artificial intelligence founded", "Where was Alan Turing born?"] # Generate embeddings for queries query_embeddings = ef(queries) # Connect to Zilliz Cloud with Public Endpoint and API Key client = MilvusClient( uri=ZILLIZ_PUBLIC_ENDPOINT, token=ZILLIZ_API_KEY) COLLECTION = "documents" if client.has_collection(collection_name=COLLECTION): client.drop_collection(collection_name=COLLECTION) client.create_collection( collection_name=COLLECTION, dimension=ef.dim, auto_id=True) for doc, embedding in zip(docs, docs_embeddings): client.insert(COLLECTION, {"text": doc, "vector": embedding}) results = client.search( collection_name=COLLECTION, data=query_embeddings, consistency_level="Strong", output_fields=["text"]) ``` For more information, refer to our [PyMilvus Embedding Model documentation](https://milvus.io/docs/embeddings.md). ### Create embeddings via sentence-transformer ``` from sentence_transformers import SentenceTransformer from pymilvus import MilvusClient model = SentenceTransformer("jinaai/jina-embeddings-v2-small-en", trust_remote_code=True) docs = [ "Artificial intelligence was founded as an academic discipline in 1956.", "Alan Turing was the first person to conduct substantial research in AI.", "Born in Maida Vale, London, Turing was raised in southern England." ] # Generate embeddings for documents docs_embeddings = model.encode(docs, normalize_embeddings=True) queries = ["query: When was artificial intelligence founded", "query: Wo wurde Alan Turing geboren?" ] # Generate embeddings for queries query_embeddings = model.encode(queries, normalize_embeddings=True) # Connect to Zilliz Cloud with Public Endpoint and API Key client = MilvusClient( uri=ZILLIZ_PUBLIC_ENDPOINT, token=ZILLIZ_API_KEY) COLLECTION = "documents" if client.has_collection(collection_name=COLLECTION): client.drop_collection(collection_name=COLLECTION) client.create_collection( collection_name=COLLECTION, dimension=512, auto_id=True) for doc, embedding in zip(docs, docs_embeddings): client.insert(COLLECTION, {"text": doc, "vector": embedding}) results = client.search( collection_name=COLLECTION, data=query_embeddings, consistency_level="Strong", output_fields=["text"]) ``` Refer to [Hugging Face documentation](https://huggingface.co/jinaai/jina-embeddings-v2-small-en) for more details.