text-embedding-3-large

OpenAI’s text-embedding-3-large is its largest text embedding model, and you can use it for integrated embedding on Pinecone document indexes.

​

When to use it

text-embedding-3-large is the largest dense text embedding model from OpenAI. Pinecone offers it for integrated embedding on document indexes, so you upsert and search with text and Pinecone embeds it through Microsoft Azure.

​

Inputs, limits, and pricing

Input	Limits	Price
Text	8192 tokens per input, 96 inputs per request, 10,000 bytes per search query	$0.13 per 1M tokens in `global`, $0.143 in us

Monthly and per-minute limits depend on your plan. See Rate limits.

​

Quickstart

​

Installation

Integrated embedding on document indexes requires Python SDK 10.1.0, Node.js SDK 9.1.0, or Go SDK 7.1.0 or later.

Python

pip install --upgrade pinecone

​

Create index

This creates a document index whose chunk_text field embeds with text-embedding-3-large at 1,024 dimensions, shortened from its default 3,072.

Python

import time
from pinecone import Pinecone, SchemaBuilder

pc = Pinecone(api_key="YOUR_API_KEY")

schema = (
    SchemaBuilder()
      .add_string_field(
          name="chunk_text",
          embed={"model": "text-embedding-3-large", "dimension": 1024},
      )
      .build()
)
pc.indexes.create(name="text-embedding-3-large", schema=schema)

while not pc.indexes.describe(name="text-embedding-3-large").status.ready:
    time.sleep(2)

index = pc.index(name="text-embedding-3-large")

​

Embed & upsert

Upsert documents with plain text on the embedded field. Pinecone embeds each value on write, up to 96 documents per request.

Python

index.documents.upsert(
    namespace="example-namespace",
    documents=[
        {"_id": "doc1", "chunk_text": "Apple is a popular fruit known for its sweetness and crisp texture."},
        {"_id": "doc2", "chunk_text": "The tech company Apple is known for its innovative products like the iPhone."},
        {"_id": "doc3", "chunk_text": "Many people enjoy eating apples as a healthy snack."},
        {"_id": "doc4", "chunk_text": "Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces."},
        {"_id": "doc5", "chunk_text": "An apple a day keeps the doctor away, as the saying goes."},
        {"_id": "doc6", "chunk_text": "Apple Computer Company was founded on April 1, 1976, by Steve Jobs, Steve Wozniak, and Ronald Wayne as a partnership."},
    ],
)

​

Query

Search with an embed clause, and Pinecone embeds the query text with the same model.

Python

response = index.documents.search(
    namespace="example-namespace",
    top_k=3,
    score_by=[
        {"type": "embed", "fields": ["chunk_text"], "query": "Tell me about the tech company known as Apple."}
    ],
    include_fields=["chunk_text"],
)

for match in response.matches:
    print(match._id, match._score, match.chunk_text)

​

Parameters

Set these in the field’s write_parameters and read_parameters. Set dimension and processing_location on the embed object itself, as embed.dimension and embed.processing_location. Putting either one in write_parameters or read_parameters returns a 400.

Parameter	Type	Required/Optional	Description	Default
truncate	string	Optional	How to handle inputs longer than those supported by the model. Accepted values: END or NONE. END truncates the input sequence at the input token limit. NONE returns an error when the input exceeds the input token limit.	END

​

Good to know

• Dimension: 3,072 by default, or any integer from 1 to 3,072. The dimension is fixed when you create the index. Very low dimensions keep little of the text’s meaning. At dimension 1, every cosine score is 1 or -1, so results fall into two tied groups regardless of the query. OpenAI’s benchmarks of shortened text-embedding-3 embeddings go down to 256 dimensions, so treat a few hundred as a practical minimum.
• Metric: cosine by default, or dotproduct or euclidean.
• Processing location: global (default) or us. The Starter and Builder plans can use only global. See Processing locations.
• Availability: Integrated embedding on document indexes only, on every plan.