pinecone 9.0.1


pip install pinecone

  Latest version

Released: May 19, 2026
Navigation
Meta
Author: Pinecone Systems, Inc.
Requires Python: >=3.10
Classifiers

Development Status
  • 5 - Production/Stable

Intended Audience
  • Developers
  • Information Technology
  • Science/Research
  • System Administrators

Operating System
  • OS Independent

Programming Language
  • Python :: 3.10
  • Python :: 3.11
  • Python :: 3.12
  • Python :: 3.13

Topic
  • Database
  • Software Development
  • Software Development :: Libraries
  • Software Development :: Libraries :: Application Frameworks
  • Software Development :: Libraries :: Python Modules

Pinecone Python SDK

The Pinecone Python SDK provides a client for the Pinecone vector database. Use it to create and manage indexes, upsert and query vectors, and run inference operations from Python.

Requires Python 3.10+.

Installation

pip install pinecone

For development dependencies (testing, type checking, linting):

pip install pinecone[dev]

Quick start

from pinecone import Pinecone, ServerlessSpec

# Initialize the client
pc = Pinecone(api_key="your-api-key")

# Create a serverless index
pc.indexes.create(
    name="movie-recommendations",
    dimension=1536,
    metric="cosine",
    spec=ServerlessSpec(cloud="aws", region="us-east-1"),
)

# Connect to the index
index = pc.index("movie-recommendations")

# Upsert vectors
index.upsert(
    vectors=[
        ("movie-42", [0.012, -0.087, 0.153]),  # 1536-dim embedding
        ("movie-87", [0.045, 0.021, -0.064]),  # 1536-dim embedding
    ],
    namespace="movies-en",
    batch_size=100,  # split larger inputs into parallel batches automatically
)

# Query for similar vectors
results = index.query(
    vector=[0.012, -0.087, 0.153],  # 1536-dim embedding
    top_k=10,
    namespace="movies-en",
)

for match in results.matches:
    print(f"{match.id}: {match.score:.4f}")

Async usage

The SDK provides an async client for use with asyncio:

import asyncio
from pinecone import AsyncPinecone

async def main():
    async with AsyncPinecone(api_key="your-api-key") as pc:
        desc = await pc.indexes.describe("movie-recommendations")
        index = await pc.index(host=desc.host)
        async with index:
            results = await index.query(
                vector=[0.012, -0.087, 0.153],  # 1536-dim vector
                top_k=10,
                namespace="movies-en",
            )
            for match in results.matches:
                print(f"{match.id}: {match.score:.4f}")

asyncio.run(main())

Configuration

API key

Pass the API key directly or set the PINECONE_API_KEY environment variable:

from pinecone import Pinecone

# Explicit API key
pc = Pinecone(api_key="your-api-key")

# From environment variable (PINECONE_API_KEY)
pc = Pinecone()

Custom host

Connect to a specific control plane host:

pc = Pinecone(api_key="your-api-key", host="https://api.pinecone.io")

Timeout

Configure request timeouts in seconds:

pc = Pinecone(api_key="your-api-key", timeout=30)

Debug logging

Enable debug logging by setting the PINECONE_DEBUG environment variable:

export PINECONE_DEBUG=1

Development

Setup

Clone the repository and install dependencies with uv:

uv sync

Tests

uv run pytest tests/unit/ -x -v

Type checking

uv run mypy --strict pinecone/

Linting and formatting

uv run ruff check --fix
uv run ruff format

License

Apache-2.0. See LICENSE for details.

9.0.1 May 19, 2026
9.0.1rc1 May 18, 2026
9.0.0 May 04, 2026
9.0.0rc2 May 04, 2026
9.0.0rc1 May 04, 2026
8.2.0rc2 May 04, 2026
8.2.0rc1 May 04, 2026
8.1.2 Apr 08, 2026
8.1.1 Apr 02, 2026
8.1.0 Feb 19, 2026
8.1.0rc1 Feb 17, 2026
8.0.1 Feb 11, 2026
8.0.0 Nov 18, 2025
7.3.1a1 Oct 03, 2025
7.3.1.dev8 Oct 01, 2025
7.3.1.dev7 Oct 01, 2025
7.3.1.dev6 Oct 01, 2025
7.3.1.dev5 Oct 01, 2025
7.3.1.dev4 Sep 30, 2025
7.3.1.dev3 Sep 25, 2025
7.3.1.dev2 Sep 24, 2025
7.3.1.dev1 Sep 24, 2025
7.3.0 Jun 27, 2025
7.2.0 Jun 18, 2025
7.1.0 Jun 16, 2025
7.1.0rc1 Jun 16, 2025
7.0.2 May 28, 2025
7.0.2.dev1 May 27, 2025
7.0.1 May 21, 2025
7.0.1.dev1 May 21, 2025
7.0.0 May 20, 2025
7.0.0.dev3 May 16, 2025
7.0.0.dev2 May 15, 2025
7.0.0.dev1 May 15, 2025
6.0.3.dev1 May 21, 2025
6.0.2 Mar 13, 2025
6.0.2.dev1 Mar 13, 2025
6.0.1 Feb 10, 2025
6.0.1.dev1 Feb 10, 2025
6.0.0 Feb 07, 2025
6.0.0rc2 Oct 22, 2024
6.0.0rc1 Oct 21, 2024
6.0.0.dev9 Feb 03, 2025
6.0.0.dev8 Jan 31, 2025
6.0.0.dev7 Jan 30, 2025
6.0.0.dev6 Dec 17, 2024
6.0.0.dev5 Dec 17, 2024
6.0.0.dev4 Dec 13, 2024
6.0.0.dev3 Oct 25, 2024
6.0.0.dev2 Oct 25, 2024
6.0.0.dev1 Oct 18, 2024
5.4.2 Dec 09, 2024
5.4.1 Nov 26, 2024
5.4.0 Nov 13, 2024
5.4.0.dev5 Nov 13, 2024
5.4.0.dev4 Oct 25, 2024
5.4.0.dev3 Oct 25, 2024
5.4.0.dev2 Oct 25, 2024
5.4.0.dev1 Oct 22, 2024
5.3.1 Sep 19, 2024
5.3.0 Sep 18, 2024
5.2.0 Sep 17, 2024
5.2.0.dev10 Sep 17, 2024
5.2.0.dev9 Sep 17, 2024
5.2.0.dev8 Sep 17, 2024
5.2.0.dev7 Sep 09, 2024
5.2.0.dev6 Sep 06, 2024
5.2.0.dev5 Sep 05, 2024
5.2.0.dev4 Sep 05, 2024
5.2.0.dev3 Sep 05, 2024
5.2.0.dev2 Aug 30, 2024
5.2.0.dev1 Aug 30, 2024
5.2.0.dev0 Aug 30, 2024
5.1.0 Aug 29, 2024
5.1.0rc1 Aug 28, 2024
5.1.0.dev1 Aug 29, 2024
5.0.1 Aug 12, 2024
5.0.0 Jul 31, 2024
4.1.2 Jul 31, 2024
4.1.1 Jul 31, 2024
4.1.0 Jul 31, 2024
4.0.0 May 03, 2024
3.2.2 Jul 31, 2024
3.2.1 Jul 31, 2024
3.2.0 Jul 31, 2024
3.1.0 Jul 31, 2024
3.0.3 Jul 31, 2024
3.0.2 Jul 31, 2024
3.0.1 Jul 31, 2024
3.0.0 Jul 31, 2024
2.2.4 Jul 31, 2024
2.2.3 Jul 31, 2024
2.2.2 Jul 31, 2024

Wheel compatibility matrix

Platform CPython >=3.10 (abi3)
macosx_10_12_x86_64
macosx_11_0_arm64
manylinux2014_aarch64
manylinux2014_x86_64
manylinux_2_17_aarch64
manylinux_2_17_x86_64
musllinux_1_2_aarch64
musllinux_1_2_x86_64
win_amd64

Files in release

Extras:
Dependencies:
httpx[http2] (<1.0,>=0.27)
msgspec
orjson