jina-embeddings-v2-base-en | Jina AI

METRIC

cosine

DIMENSION

768

MAX INPUT TOKENS

8192

TASK

embedding

Overview

Ideal for text embeddings where short queries are expected to return large passages of text. Works well with messy data. Can be used via Jina Embeddings API - users can get an API key here https://jina.ai/embeddings/.

Using the model

Installation:

!pip install pinecone

Create Index

from pinecone import Pinecone, ServerlessSpec

pc = Pinecone(api_key="API_KEY")

# Create Index
index_name = "jina-embeddings-v2-base-en"

if not pc.has_index(index_name):
    pc.create_index(
        name=index_name,
        dimension=768,
        metric="cosine",
        spec=ServerlessSpec(
            cloud='aws',
            region='us-east-1'
        )
    )

index = pc.Index(index_name)

Embed & Upsert

# Embed data
data = [
    {"id": "vec1", "text": "Apple is a popular fruit known for its sweetness and crisp texture."},
    {"id": "vec2", "text": "The tech company Apple is known for its innovative products like the iPhone."},
    {"id": "vec3", "text": "Many people enjoy eating apples as a healthy snack."},
    {"id": "vec4", "text": "Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces."},
    {"id": "vec5", "text": "An apple a day keeps the doctor away, as the saying goes."},
]

import requests
url = 'https://api.jina.ai/v1/embeddings'


def get_embeddings(texts):
  # returns embeddings given list of texts
  headers = {
      'Content-Type': 'application/json',
      'Authorization': f'Bearer {JINA_API_KEY}'
  }
  data = {
      'input': texts,
      'model': 'jina-embeddings-v2-base-en'
  }
  response = requests.post(url, headers=headers, json=data)
  return response.json()


embeddings = get_embeddings([d["text"] for d in data])

print(embeddings)

embeddings = [e["embedding"] for e in embeddings["data"]]

vectors = []
for d, e in zip(data, embeddings):
    vectors.append({
        "id": d['id'],
        "values": e,
        "metadata": {'text': d['text']}
    })

index.upsert(
    vectors=vectors,
    namespace="ns1"
)

Query

query = "Tell me about the tech company known as Apple"

x = get_embeddings([query])["data"][0]["embedding"]

results = index.query(
    namespace="ns1",
    vector=x,
    top_k=3,
    include_values=False,
    include_metadata=True
)

print(results)

Lorem Ipsum

Was this page helpful?