Jina AI / jina-embeddings-v2-base-code

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.

What is jina-embeddings-v2-base-code

jina-embeddings-v2-base-code is a multilingual embedding model that understands English and 30 popular programming languages, supporting sequences up to 8192 tokens long. It utilizes a BERT-based architecture, specifically JinaBERT, which includes a symmetric bidirectional variant of ALiBi for managing longer sequences. Initially pre-trained on GitHub's code dataset, this model has been further enhanced with Jina AI’s extensive collection of over 150 million coding question-answer pairs and docstring source code pairs from various domains.

Comparing jina-embeddings-v2-base-code with other Jina embedding models.

Model	Parameter Size	Embedding Dimension	Text
jina-embeddings-v3	570M	flexible embedding size (Default: 1024)	multilingual text embeddings; supports 94 language in total
jina-embeddings-v2-small-en	33M	512	English monolingual embeddings
jina-embeddings-v2-base-en	137M	768	English monolingual embeddings
jina-embeddings-v2-base-zh	161M	768	Chinese-English Bilingual embeddings
jina-embeddings-v2-base-de	161M	768	German-English Bilingual embeddings
jina-embeddings-v2-base-code	161M	768	English and programming languages

How to create embeddings using jina-embeddings-v2-base-code

There are two primary ways to generate vector embeddings:

1. PyMilvus: the Python SDK for Milvus that seamlessly integrates the jina-embeddings-v2-base-code model.
2. SentenceTransformer library: the Python library sentence-transformer.

Once the vector embeddings are created, they can be stored in a vector database like Zilliz Cloud (a fully managed vector database powered by Milvus) and used for semantic similarity search.

Here are four key steps:

• Sign up for a Zilliz Cloud account for free.
• Set up a serverless cluster and obtain the Public Endpoint and API Key.
• Create a vector collection and insert your vector embeddings.
• Run a semantic search on the stored embeddings.

Create embeddings via PyMilvus and insert them into Zilliz Cloud for semantic search

from pymilvus.model.dense import SentenceTransformerEmbeddingFunction
from pymilvus import MilvusClient

ef = SentenceTransformerEmbeddingFunction("jinaai/jina-embeddings-v2-base-code", 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 details, refer to our [PyMilvus Embedding Model documentation](For more information, refer to our PyMilvus Embedding Model documentation.).

Create embeddings via the SentenceTransformer library and insert them into Zilliz Cloud for semantic search

from sentence_transformers import SentenceTransformer
from pymilvus import MilvusClient

model = SentenceTransformer("jinaai/jina-embeddings-v2-base-code", 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=768,
    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"])