Skip to main content

Records plugin for Pinecone SDK

Project description

Records API plugin for Pinecone python SDK

Installation

The plugin is distributed separately from the core python SDK.

# Install the base python SDK, version 5.4.0 or higher
pip install pinecone

# And also the plugin functionality
pip install pinecone-plugin-records

Usage

This plugin extends the functionality of the pinecone SDK to allow creating indexes for specific embedding models, and upserting and searching records in these indexes. These operations are added to the existing Pinecone and Index classes.

Models currently supported:

Create an index for an embedding model, upsert records, and search

The following example highlights how to use the Pinecone class to create a new index for an embedding model, and then uses Index to upsert and search some records.

from pinecone import Pinecone

pc = Pinecone(api_key="<<PINECONE_API_KEY>>")

# Create an index for your embedding model
index_model = pc.create_index_for_model(
    name="my-model-index",
    cloud="aws",
    region="us-east-1",
    embed={
        "model":"multilingual-e5-large",
        "field_map": {"text": "my_text_field"}
    }
)

# establish an index connection
index = pc.Index(host=index_model.host)

# upsert records
index.upsert_records(
    "my-namespace",
    [
        {
            "_id": "test1",
            "my_text_field": "Apple is a popular fruit known for its sweetness and crisp texture.",
        },
        {
            "_id": "test2",
            "my_text_field": "The tech company Apple is known for its innovative products like the iPhone.",
        },
        {
            "_id": "test3",
            "my_text_field": "Many people enjoy eating apples as a healthy snack.",
        },
        {
            "_id": "test4",
            "my_text_field": "Apple Inc. has revolutionized the tech industry with its sleek designs and user-friendly interfaces.",
        },
        {
            "_id": "test5",
            "my_text_field": "An apple a day keeps the doctor away, as the saying goes.",
        },
        {
            "_id": "test6",
            "my_text_field": "Apple Computer Company was founded on April 1, 1976, by Steve Jobs, Steve Wozniak, and Ronald Wayne as a partnership.",
        },
    ],
)

# search for similar records
response = index.search_records(
    namespace="test-namespace",
    query={
        "inputs":{
            "text": "Apple corporation",
        },
        "top_k":3,
    },
    rerank={
        "model": "bge-reranker-v2-m3",
        "rank_fields": ["my_text_field"],
        "top_n": 3,
    },
)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

pinecone_plugin_records-1.0.0.tar.gz (108.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

pinecone_plugin_records-1.0.0-py3-none-any.whl (266.6 kB view details)

Uploaded Python 3

File details

Details for the file pinecone_plugin_records-1.0.0.tar.gz.

File metadata

  • Download URL: pinecone_plugin_records-1.0.0.tar.gz
  • Upload date:
  • Size: 108.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.5 CPython/3.12.7 Linux/6.8.0-1017-azure

File hashes

Hashes for pinecone_plugin_records-1.0.0.tar.gz
Algorithm Hash digest
SHA256 af5b549712bfcd92247624b9b368a03b5ee41114291d2dfb306149ebd21fa6ef
MD5 cb103f712f3f160e8fb2dc19507d72e4
BLAKE2b-256 c3fac397dd3fc215edd958040d71a99942e34a721478c0be68fde95eb045d9e1

See more details on using hashes here.

File details

Details for the file pinecone_plugin_records-1.0.0-py3-none-any.whl.

File metadata

File hashes

Hashes for pinecone_plugin_records-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 96219f3a3c79e37b92bd903eb8807dd5e56f3c9291b0037b0764c8abb165de15
MD5 69fa6eccafa60c8d878ac3386c74ccaf
BLAKE2b-256 be619a5d6d6c4b290cfff967e5ea133a90f8f629de21196e545fff4f0e4a1647

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page