Knowledge

Community

HoneyHive AI Docs

SDK Reference

API Reference

Log In

Sign Up

Getting started with Evaluators in HoneyHive.

Quickstart

HoneyHive Cloud: The AI Evaluation & Observability Platform

What is HoneyHive?

Getting started on HoneyHive's managed cloud.

HoneyHive Cloud

Getting started with HoneyHive on your cloud.

Private Cloud

Setup and Authentication

Python SDK Reference

TypeScript SDK Reference

Get started with tracing OpenAI calls with HoneyHive

An overview of what you can do with your traces in HoneyHive

Overview

An overview of our data model for logging traces and events

Our Data Model

How to instrument your application for maximum insights.

Instrumentation Best Practices

Get started by tracing your LLM app with HoneyHive.

Tracing in Python

Understand how to use HoneyHive's SessionTracer with your LLM Pipeline to understand its performance and behavior

Tracing in TypeScript

Get started by tracing your custom pipeline with HoneyHive.

Tracing via API

Understand how to use HoneyHive's LlamaIndex Tracer to understand your LlamaIndex pipeline's performance and behavior

Tracing with LlamaIndex

Understand how to use HoneyHive's LangChain Tracer to understand your LangChain pipeline's performance and behavior

Tracing with LangChain

Introduction to evaluating LLM pipelines with HoneyHive

Get started with running evaluations on your Langchain and LlamaIndex pipelines with HoneyHive

Evaluation Quickstart

Logging evaluation runs programmatically with the Python SDK

Running Evaluations via SDK

Collaborate, analyze the evaluation report and share learnings with your team.

Sharing & Collaboration

Connect your application to HoneyHive and start monitoring your application performance in production.

Learn how to create custom queries to slice and dice your data.

Building Queries

Configuring session analytics for your app.

Analyzing Sessions

An introduction to configuring evaluators with HoneyHive

How to create a custom Python evaluator in HoneyHive console

Code Evaluator

How to create a custom LLM evaluator in HoneyHive console

LLM Evaluator

How to create custom human evaluator fields for annotators to manually review outputs

Human Evaluator

How to upload or curate datasets in HoneyHive

Creating Datasets

How to programmatically export datasets in HoneyHive.

Exporting Datasets

Test, version and manage your prompts in the Studio.

Playground

Projects

How to invite teammates to your HoneyHive account.

Inviting Teammates

The key concepts behind the HoneyHive Platform

Key Concepts

Platform Architecture

Retrieve a list of configurations

Create a new configuration

Update an existing configuration

Delete a configuration

Retrieve a list of datapoints

Update a specific datapoint

Create a new datapoint

Retrieve a specific datapoint

Delete a specific datapoint

Get datasets

Update a dataset

Create a dataset

Delete a dataset

Retrieve events based on filters

Update an event

Please refer to our instrumentation guide for detailed information

Introduction

Tracing

Testing & Evaluation

Performance Monitoring

Managing Evaluators

Managing Datasets

Managing Prompts

Managing Workspace

Learn more