Quick start

📘

Relevance AI is an end-to-end collaborative platform for analyzing unstructured data for actionable insights. It makes it easy to connect to data, analyze it using machine learning and share it as interactive apps, dashboards or APIs.

Relevance AI's core elements:

App Builder - Insights for Everyone
A no-code builder to quickly build and share visualizations, interactive apps and reports.

• Interactive visualizations designed for machine learning and unstructured data.
• Built for insights and usability to be actionable for anyone.
• Share and collaborate easily with comments and access controls.

Python Library - Deep Experimentation & Flexibility for Data Teams
A python library for experimenting more deeply with vectors and unstructured data.

• Easily extract vectors from unstructured data. Integrates with HuggingFace, SentenceTransformers, etc.
• Apply algorithms on vectors and data for actionable insights, such as clustering, nearest neighbours, etc. Integrates well with Pandas, Sklearn and more.
• Create and update apps from code in a few lines.
• Also serves as an SDK to the API.

API & Platform - Managed Infrastructure
Highly scalable and flexible infrastructure to store, query and analyze unstructured data through an API.

• Managed end-to-end from data to value, hiding all the complexities such as data transformation to vectors, management of data warehouses + vector database and more.
• Integrates flexibly with existing data warehouses (e.g. Snowflake, Bigquery, ..) and vector databases (e.g. FAISS, HNSWLib, Elasticsearch, ..).

General flow

Or code-free platform makes the process smooth and quick.
1- Sign up with Relevance AI for free at https://relevance.ai/
2- Upload your dataset data using the platform
3- Vectorize your data using the platform
4- Use any of the on-platform analysers: search, cluster, ...
5- Use the platform to present and share insights]: Explorer, report, ...

You can always use our python library for more in-depth analysis and functionalities that have not yet been embedded into the platform.

A quick tour on available features is provided on the next page.