RelevanceAI-dev 1.1.2.2022.2.15.5.51.22.902259

No project description provided

Join our slack channel!

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

🔥 Features

• Fast vector search with free dashboard to preview and visualise results
• Vector clustering with support for libraries like scikit-learn and easy built-in customisation
• Store nested documents with support for multiple vectors and metadata in one object
• Multi-vector search with filtering, facets, weighting
• Hybrid search with support for weighting keyword matching and vector search ... and more!

🧠 Documentation

API type	Link
Guides	Documentation
Python Reference	Documentation

You can easily access our documentation while using the SDK using:

from relevanceai import Client
client = Client()

# Easy one line of code to access our docs
client.docs

🛠️ Installation

Using pip:

pip install -U relevanceai

Using conda:

conda install -c relevance relevanceai

⏩ Quickstart

Login into your project space

from relevanceai import Client

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

Prepare your documents for insertion by following the below format:

• Each document should be a dictionary
• Include a field _id as a primary key, otherwise it's automatically generated
• Suffix vector fields with _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"},
]

Insert data into a dataset

Create a dataset object with the name of the dataset you'd like to use. If it doesn't exist, it'll be created for you.

Quick tip! Our Dataset object is compatible with common dataframes methods like .head(), .shape() and .info().

ds = client.Dataset("quickstart")
ds.insert_documents(docs)

Perform vector search

results = ds.vector_search(
    multivector_query=[{"vector": [0.2, 0.2, 0.2], "fields": ["example_vector_"]}],
    page_size=3,
    query="sample search" # optional, name to display in dashboard
)

Cluster dataset with Auto Cluster

Generate 12 clusters using kmeans

clusterop = ds.auto_cluster("kmeans-12", vector_fields=["example_vector_"])
clusterop.list_closest_to_center()

Quick tip! After each of these steps, the output will provide a URL to the Relevance AI dashboard where you can see a visualisation of your results

🚧 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:

Don't forget 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 object 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