Jump to Content
orq.aiHomepage
ResourcesAPI ReferenceChangelogPython SDKNode.js SDKEvaluatorq
HomepageStatusConsoleorq.ai
Resources
StatusConsole
ResourcesAPI ReferenceChangelogPython SDKNode.js SDKEvaluatorq
All
Pages
Start typing to search…

Documentation

  • Introduction
  • Quick Start

Reference

  • AI Proxy
    • Integrations
      • Agno AI
      • Autogen
      • DSPy
      • Instructor
      • Langchain
      • OpenAI
  • Analytics
    • Contact
      • Creating a Contact
      • Using Contact Metrics
    • Dashboard
    • Deployment Analytics
  • Dataset
    • Creating a Dataset
    • Creating a Curated Dataset
    • Using Datasets via the API
  • Deployment
    • Creating a Deployment
    • Integrating a Deployment
    • Deployment Versioning
    • Deployment Routing
    • Evaluators & Guardrails in Deployments
    • Deployment Cache
    • Deployment Security and Privacy
    • Including Knowledge Base Retrievals in Invoke
    • Attaching files to a Deployment
    • Sending Extra Parameters During Generation
  • Evaluator
    • Creating an Evaluator
    • Creating an Evaluator via the API
    • Evaluator Library
    • Function Evaluator
    • HTTP Evaluator
      • Creating an HTTP Evaluator
    • JSON Evaluator
      • Creating a JSON Evaluator
    • LLM Evaluator
      • Creating an LLM Evaluator
    • Python Evaluator
      • Creating a Python Evaluator
    • Ragas Evaluator
    • Using Evaluators via the API
  • Experiment
    • Creating an Experiment
    • Using Evaluator in Experiment
    • Running an Experiment
    • Exporting an Experiment
    • Use cases for Experiments
  • Feedback
    • Adding Feedback to Generations
    • Making Corrections on a Generation
    • Feedback Types
    • Adding Feedback Programmatically
  • Hub
  • Knowledge Base
    • Creating a Knowledge Base
      • Retrieval Settings
      • Retrieval Observability
      • Agentic RAG
      • Chunking Strategy
    • Creating a Knowledge Base via API
    • Searching a Knowledge Base
    • Using a Knowledge Base in a Prompt
  • Model Garden
    • Integrations
      • Azure OpenAI
      • Amazon Bedrock
      • Google Vertex AI
    • API keys & Endpoints
    • Using the Model Garden
    • Using the Model Garden via the API
  • Observability
    • Logs
    • Threads
    • Traces
  • Playground
    • Creating a Playground
  • Projects
  • Prompt
    • Creating a Prompt
    • Message Roles
    • Model Parameters
    • Prompt Engineering Guide
    • Using Images and Vision in a Prompt
    • Using the Prompt Generator
    • Using Response Format
    • Using Prompts via the API
  • Prompt Snippet
    • Creating a Prompt Snippet
    • Using a Prompt Snippet in a Prompt
  • Tool
    • Creating a Tool
    • Using a Tool in a Prompt
  • Webhook
    • Creating a Webhook
    • Webhook Events
    • Webhook Security & Validation
    • Webhook Best Practices

Administer

  • Workspace Settings
    • Billing & Usage
    • Permissions
      • Using Permissions
  • Data Compliance

Common Architectures

  • Simple Deployment
  • Customer Support Chatbot
  • Simple RAG
  • AI Agent

Tutorials

  • Cookbooks
    • Capturing and Leveraging User Feedback in Orq.ai
    • Chaining Deployments and Running Evaluations
    • Creating SQL Queries from Natural Language
    • Data Extraction from PDF
    • How to connect Orq.ai with your Lovable app
    • Image-Based Receipt Extraction with Orq
    • Intent Classification with Orq.ai
    • Multilingual FAQ Bot Using RAG with Orq.ai
    • Using Third Party Vector Databases with Orq.ai
    • Orq.ai as Prompt Manager
    • How to Maintain and Send Chat History with Orq.ai Deployments
    • How to use Orq.ai nodes in n8n workflows
  • LLM Glossary

MCP Server

  • MCP
Powered by 

Evaluator Library

There are many Evaluators available to include in your Projects.

Browse through all Function Evaluators, Ragas Evaluator and LLM Evaluator in the Hub.

Browse through all available [Evaluators](doc:evaluator) and [Prompts](doc:prompt).

From the Hub, use the Add to project button to make an Evaluator available for use in Experiment or Deployment.

Updated 3 months ago


Creating an Evaluator via the API
Function Evaluator