RelevanceAI-dev

Github Banner

For guides, tutorials on how to use this package, visit https://docs.relevance.ai/docs.

🔥 Features

Features of the library include:

Quick vector search with free dashboard to preview results
Vector clustering with support with built-in easy customisation
Multi-vector search with filtering, facets, weighting
Hybrid search (weighting exact text matching and vector search together) ... and more!

🧠 Documentation

There are two main ways of documentations to take a look at:

API type	Link
Guides	Documentation
Python Reference	Documentation

🛠️ Installation

pip install -U relevanceai

Or you can install it via conda to:

conda install pip
pip install -c relevanceai

You can also install on conda (only available on Linux environments at the moment): conda install -c relevance relevanceai.

⏩ Quickstart

Login into your project space

from relevanceai import Client

client = Client(<project_name>, <api_key>)

This is a data example in the right format to be uploaded to relevanceai. Every document you upload should:

Be a list of dictionaries
Every dictionary has a field called _id
Vector fields end in vector

docs = [
    {"_id": "1", "example_vector_": [0.1, 0.1, 0.1], "data": "Documentation"},
    {"_id": "2", "example_vector_": [0.2, 0.2, 0.2], "data": "Best document!"},
    {"_id": "3", "example_vector_": [0.3, 0.3, 0.3], "data": "document example"},
    {"_id": "4", "example_vector_": [0.4, 0.4, 0.4], "data": "this is another doc"},
    {"_id": "5", "example_vector_": [0.5, 0.5, 0.5], "data": "this is a doc"},
]

Upload data into a new dataset

The documents will be uploaded into a new dataset that you can name in whichever way you want. If the dataset name does not exist yet, it will be created automatically. If the dataset already exist, the uploaded _id will be replacing the old data.

client.insert_documents(dataset_id="quickstart", docs=docs)

Perform a vector search

client.services.search.vector(
    dataset_id="quickstart",
    multivector_query=[
        {"vector": [0.2, 0.2, 0.2], "fields": ["example_vector_"]},
    ],
    page_size=3,
    query="sample search" # Stored on the dashboard but not required

🚧 Development

Getting Started

To get started with development, ensure you have pytest and mypy installed. These will help ensure typechecking and testing.

python -m pip install pytest mypy

Then run testing using:

Make sure to set your test credentials!

export TEST_PROJECT = xxx
export TEST_API_KEY = xxx

python -m pytest
mypy relevanceai

Set up precommit

pip install precommit
pre-commit install

🧰 Config

The config contains the adjustable global settings for the SDK. For a description of all the settings, see here.

To view setting options, run the following:

client.config.options

The syntax for selecting an option is section.key. For example, to disable logging, run the following to modify logging.enable_logging:

client.config.set_option('logging.enable_logging', False)

To restore all options to their default, run the following:

Changing the base URL

You can change the base URL as such:

client.base_url = "https://.../latest"

You can also update the ingest base URL:

client.ingest_base_url = "https://.../latest

Metadata

Release files for RelevanceAI-dev 0.31.0.2022.1.31.1.22.50.582642

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for RelevanceAI-dev 0.31.0.2022.1.31.1.22.50.582642
File	Size	Uploaded
RelevanceAI-dev-0.31.0.2022.1.31.1.22.50.582642.tar.gz	117.4 kB	Jan 31, 2022	Details

Built distribution (wheel)

Table of built distributions (wheels) for RelevanceAI-dev 0.31.0.2022.1.31.1.22.50.582642
File	Interpreter	ABI	Platform	Reset
RelevanceAI_dev-0.31.0.2022.1.31.1.22.50.582642-py3-none-any.whl 161.0 kB Jan 31, 2022	Python 3	none	any	Details

Total release size: 278.5 kB

Release files / RelevanceAI-dev-0.31.0.2022.1.31.1.22.50.582642.tar.gz

Download URL	RelevanceAI-dev-0.31.0.2022.1.31.1.22.50.582642.tar.gz
Size	117.4 kB
Tags	Source
SHA-256 checksum How to use checksums	`3fed85d79adf26d3b188059c37c8296c7320276f0ab8abc396efa71b45684d00`
BLAKE2b-256 checksum How to use checksums	`e39407d255752496e8c3a6700c72bbf01d89813a08edc83e57824326cd0fdb44`
Upload date	Jan 31, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.7.1 importlib_metadata/4.10.1 pkginfo/1.8.2 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.10.2`

Release files / RelevanceAI_dev-0.31.0.2022.1.31.1.22.50.582642-py3-none-any.whl

Download URL	RelevanceAI_dev-0.31.0.2022.1.31.1.22.50.582642-py3-none-any.whl
Size	161.0 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`d99803bb8d154073c84b8fd4dc453795eedaf8f3f90edb5d921345e93f4d3fdc`
BLAKE2b-256 checksum How to use checksums	`280bcef2ec7c0d2ff0907387a6b59a9cfae8608dff6790336a277f730805e463`
Upload date	Jan 31, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.7.1 importlib_metadata/4.10.1 pkginfo/1.8.2 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.10.2`