The guide to gte-large-en-v1.5

Model
Alibaba / gte-large-en-v1.5

Alibaba / gte-large-en-v1.5

AI Model Milvus Integrated

Task: Embedding

Modality: Text

Similarity Metric: Cosine

License: Apache 2.0

Dimensions: 1024

Max Input Tokens: 8192

Price: Free

Introduction to gte-large-en-v1.5

The gte-large-en-v1.5 is an English text embedding model developed by Alibaba's Institute for Intelligent Computing. It is part of the GTE (General Text Embeddings) model series, which is based on the transformer++ encoder backbone (BERT + RoPE + GLU) and trained on a large-scale corpus of relevant text pairs.

Comparing gte-base-en-v1.5 and gte-large-en-v1.5:

Feature	gte-base-en-v1.5	gte-large-en-v1.5
Parameter Size	137 million	434 million
Embedding Dimension	768	1024
Max Sequence Length	8192	8192
MTEB Score	64.11	65.39
LoCo Score	87.44	86.71

How to create vector embeddings with gte-large-en-v1.5

There are two primary ways to create vector embeddings:

PyMilvus: the Python SDK for Milvus that seamlessly integrates the gte-large-en-v1.5 model.
SentenceTransformer library: the python library of sentence-transformer.

Once the vector embeddings are generated, they can be stored in Zilliz Cloud (a fully managed vector database service 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.

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

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

ef = SentenceTransformerEmbeddingFunction("Alibaba-NLP/gte-large-en-v1.5", 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.

Generate vector embeddings via SentenceTransformer library and insert them into Zilliz Cloud for semantic search

from sentence_transformers import SentenceTransformer
from pymilvus import MilvusClient

model = SentenceTransformer("Alibaba-NLP/gte-large-en-v1.5", 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=1024,
    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"])