Introduction

Steps to Create a Run

Select how you want to upload a model/ dataset

Use the Collinear AI Platform to create a new run and evaluate your dataset.

Creating a new run

Collinear AI

Collinear AI offers a one-stop platform for post-training, enabling enterprises to customize large language models (LLMs) to their bespoke criteria.
The API provides access to Collinear's proprietary post-training technologies:
1. AI Judges for evaluating LLMs for Safety, Reliability, and Bespoke Quality criteria
2. Synthetic data generation and curation capabilities
3. Auto-Align for fine-tuning models

Developers can leverage these tools to create custom AI models that comply with application specific safety requirements, ensure factual accuracy, and maintain brand alignment. The API supports various integration options and includes comprehensive documentation to facilitate seamless implementation. With Collinear's API, businesses can unlock the full potential of AI technologies while addressing current limitations in off-the-shelf models.

What is Collinear AI

Creating Your Organization

Creating Your Space

Use the Collinear AI Platform to access your API Key.

Getting your API Key

Use the Collinear AI Platform to access your Space Id.

Getting your Space ID

Use the Collinear AI Platform to get Model Id.

Getting your Model ID

Use the Collinear AI Platform to get Judge Id.

Getting your Judge ID

Use the Collinear AI Platform to get Dataset ID.

Getting your Dataset ID

Use the Collinear AI Platform to export your dataset rows in a JSON file

Exporting your dataset

This documentation provides an overview of the custom query language designed to parse and evaluate complex queries on structured data. The language supports a variety of conditions, logical operators, and special features that enable users to filter data effectively.

Query Language

Use the Collinear AI Platform to compare model and judge performance.

Compare Model and Judge Performance

Use the Collinear AI Platform to create a new custom evaluation

Creating a Custom Evaluation

Use the Collinear AI Platform to create a new reliability evaluation

Creating a Reliability Evaluation

Use the Collinear AI Platform to create a new safety evaluation

Creating a Safety Evaluation

A comprehensive overview of models categorized by judge type, including reliability and safety judges.

Types of Judges

You can use the Veritas model to evaluate the factual correctness of model outputs, ensuring that the responses are accurate and free from hallucinated content.

Veritas - Reliability Judge

Use the Collinear AI Platform to create Collinear Flex judges.

Creating a Collinear Flex Judge

Use the Collinear AI Platform to create a judge for your space.

Add A Judge

Use the Collinear AI Platform to create a safety judge for your space.

Add A Safety Judge

Use the Collinear AI Platform to create reliability judges.

Add A Reliability Judge

Use the Collinear AI Platform to create custom judges.

Add A Custom Judge

Use the Collinear AI Platform to run judge on your CSV / JSON.

Upload File And Run Judge

Use the Collinear AI API to upload a dataset to your space.

Upload Dataset

Use the Collinear AI API to run judge on your dataset.

Run Judge on Dataset

Use the Collinear AI API to run conversation model on your dataset.

Run Conversation Model On Dataset

Use the Collinear AI Reliability Monitoring to view a dashboard that tracks key metrics to monitor your AI’s consistency, accuracy, and performance.

Reliability Monitoring

Collinear  empowers your business with dashboard that tracks key metrics to ensure your AI performs safely, accurately, and reliably

Safety Monitoring Dahhboard

The Curated Data Dashboard is a sophisticated tool designed for managing and evaluating conversational models within an organizational framework. This dashboard serves as a centralized platform where various parameters and metrics related to the performance of models can be assessed, curated, and monitored In this documentation, we will explore the core functionalities and components of the Curated Data Dashboard, detailing their usage and significance in maintaining and enhancing conversational AI systems.

Introduction

Get Started

Evaluation

Judge

Datasets

Monitor

Curated Data

Creating a new run

Introduction

Steps to Create a Run

Select how you want to upload a model/ dataset

Introduction

Get Started

Evaluation

Judge

Datasets

Monitor

Curated Data

​Introduction

​Steps to Create a Run

​Select how you want to upload a model/ dataset

Introduction

Steps to Create a Run

Select how you want to upload a model/ dataset