本页尚未翻译

本页内容仍为英文原文，源自官方文档 integrations/embedding/jina。中文翻译正在分批进行中。

Jina

Text Embedding Models

Jina embeddings are used to generate embeddings for text and image data. You also need to set the JINA_API_KEY environment variable to use the Jina API.

You can find a list of supported models under https://jina.ai/embeddings/

Supported parameters (to be passed in create method) are:

Parameter	Type	Default Value	Description
name	str	"jina-clip-v1"	The model ID of the jina model to use

Usage Example:

Replace your-api-key with your Jina API key. This provider reads it from JINA_API_KEY; the example sets it explicitly. In application code, supply it through your environment or a secrets manager.

import os
import tempfile
from pathlib import Path

import lancedb
from lancedb.embeddings import EmbeddingFunctionRegistry
from lancedb.pydantic import LanceModel, Vector

os.environ["JINA_API_KEY"] = "your-api-key"

jina_embed = (
    EmbeddingFunctionRegistry.get_instance()
    .get("jina")
    .create(name="jina-embeddings-v2-base-en")
)

class TextModel(LanceModel):
    text: str = jina_embed.SourceField()
    vector: Vector(jina_embed.ndims()) = jina_embed.VectorField()

data = [{"text": "hello world"}, {"text": "goodbye world"}]

db = lancedb.connect(str(Path(tempfile.mkdtemp()) / "jina-text"))
tbl = db.create_table("test", schema=TextModel, mode="overwrite")

tbl.add(data)

Multimodal Embedding Models

Jina embeddings can also be used to embed both text and image data, only some of the models support image data and you can check the list under https://jina.ai/embeddings/

Supported parameters (to be passed in create method) are:

Parameter	Type	Default Value	Description
name	str	"jina-clip-v1"	The model ID of the jina model to use

Usage Example:

import os
import tempfile
from pathlib import Path

import lancedb
import pandas as pd
import requests
from lancedb.embeddings import get_registry
from lancedb.pydantic import LanceModel, Vector

os.environ["JINA_API_KEY"] = "your-api-key"

db = lancedb.connect(str(Path(tempfile.mkdtemp()) / "jina-images"))
func = get_registry().get("jina").create()

class Images(LanceModel):
    label: str
    image_uri: str = func.SourceField()
    image_bytes: bytes = func.SourceField()
    vector: Vector(func.ndims()) = func.VectorField()
    vec_from_bytes: Vector(func.ndims()) = func.VectorField()

table = db.create_table("images", schema=Images)
labels = ["cat", "cat", "dog", "dog", "horse", "horse"]
uris = [
    "http://farm1.staticflickr.com/53/167798175_7c7845bbbd_z.jpg",
    "http://farm1.staticflickr.com/134/332220238_da527d8140_z.jpg",
    "http://farm9.staticflickr.com/8387/8602747737_2e5c2a45d4_z.jpg",
    "http://farm5.staticflickr.com/4092/5017326486_1f46057f5f_z.jpg",
    "http://farm9.staticflickr.com/8216/8434969557_d37882c42d_z.jpg",
    "http://farm6.staticflickr.com/5142/5835678453_4f3a4edb45_z.jpg",
]
image_bytes = [requests.get(uri).content for uri in uris]
table.add(
    pd.DataFrame({"label": labels, "image_uri": uris, "image_bytes": image_bytes})
)