Product Updates
Product Updates
Orq.ai Product Updates
Discover the latest releases built by Orq to simplify LLMOps workflows.
Discover the latest releases built by Orq to simplify LLMOps workflows.
January - April 2024
Version Control
Deploy
Version Control
Deploy
Version Control
Deploy
Prompt Generator
Prompt
Prompt Generator
Prompt
Prompt Generator
Prompt
Aggregate Metrics
Experiment
Aggregate Metrics
Experiment
Aggregate Metrics
Experiment
Google Gemini Pro 1.5
Model Garden
Google Gemini Pro 1.5
Model Garden
Google Gemini Pro 1.5
Model Garden
Vision Models
Model Garden
Vision Models
Model Garden
Vision Models
Model Garden
Cohere Models
Model Garden
Cohere Models
Model Garden
Cohere Models
Model Garden
Prompt Studio V2
Deploy
Prompt Studio V2
Deploy
Prompt Studio V2
Deploy
Anthropic Integration
Model Garden
Anthropic Integration
Model Garden
Anthropic Integration
Model Garden
AWS Bedrock Integration
Model Garden
AWS Bedrock Integration
Model Garden
AWS Bedrock Integration
Model Garden
Playground V2
Experiment
Playground V2
Experiment
Playground V2
Experiment
Hyperlinking
Platform
Hyperlinking
Platform
Hyperlinking
Platform
Custom LLM Evaluators
Experiment
Custom LLM Evaluators
Experiment
Custom LLM Evaluators
Experiment
Evaluators
Experiment
Evaluators
Experiment
Evaluators
Experiment
Mass Experimentation
Experiment
Mass Experimentation
Experiment
Mass Experimentation
Experiment
Llama 3 on Perplexity
Experiment
Llama 3 on Perplexity
Experiment
Llama 3 on Perplexity
Experiment
Function Calling
Platform
Function Calling
Platform
Function Calling
Platform
May - August 2024
Vertex AI
Model Garden
Vertex AI
Model Garden
Vertex AI
Model Garden
Gemini Models
Model Garden
Gemini Models
Model Garden
Gemini Models
Model Garden
Google AI Provider
Model Garden
Google AI Provider
Model Garden
Google AI Provider
Model Garden
Retrieval Augmented Generation
Knowledge Bases (RAG)
Retrieval Augmented Generation
Knowledge Bases (RAG)
Retrieval Augmented Generation
Knowledge Bases (RAG)
Webhooks
Observe
Webhooks
Observe
Webhooks
Observe
Contact Analytics
Observe
Contact Analytics
Observe
Contact Analytics
Observe
Private Model Support
Model Garden
Private Model Support
Model Garden
Private Model Support
Model Garden
Human Evaluators
Evaluate
Human Evaluators
Evaluate
Human Evaluators
Evaluate
Prompt Library
Prompt
Prompt Library
Prompt
Prompt Library
Prompt
Multi API Key Selector
Model Garden
Multi API Key Selector
Model Garden
Multi API Key Selector
Model Garden
Deployment Tester
Deploy
Deployment Tester
Deploy
Deployment Tester
Deploy
Groq Integration
Model Garden
Groq Integration
Model Garden
Groq Integration
Model Garden
September - December 2024
Evaluator Library
Evaluate
Evaluator Library
Evaluate
Evaluator Library
Evaluate
Guardrails
Deploy
Guardrails
Deploy
Guardrails
Deploy
RAGAS Evaluators
Knowledge Bases (RAG)
RAGAS Evaluators
Knowledge Bases (RAG)
RAGAS Evaluators
Knowledge Bases (RAG)
Role-based Access Control
Platform
Role-based Access Control
Platform
Role-based Access Control
Platform
LLM Call Caching
Platform
LLM Call Caching
Platform
LLM Call Caching
Platform
Usage Metrics
Platform
Usage Metrics
Platform
Usage Metrics
Platform
Output Masking
Deploy
Output Masking
Deploy
Output Masking
Deploy
Prompt Snippets
Prompt
Prompt Snippets
Prompt
Prompt Snippets
Prompt
Log Filters
Platform
Log Filters
Platform
Log Filters
Platform
Claude 3.5 Haiku
Platform
Claude 3.5 Haiku
Platform
Claude 3.5 Haiku
Platform
Claude 3.5 Sonnet
Platform
Claude 3.5 Sonnet
Platform
Claude 3.5 Sonnet
Platform
What's new in Orq.ai?
Release Notes
Orq.a is committed to shipping fast. Learn more about the latest features we've released to improve Generative AI product development workflows for our users.
December 2024
Evaluate features
Evaluator Library: The new Evaluator Library provides over 50 preconfigured templates to streamline quality checks, compliance, and contextual alignment. With customizable evaluators and seamless integration into experiments and deployments, this update ensures consistent quality control throughout the AI product development lifecycle.
Evals & Guardrails (HTTP and JSON): New HTTP and JSON evaluators and guardrails allow you to perform custom checks using external APIs and predefined JSON schemas. These tools help enforce compliance and validate inputs and outputs during experiments and deployments, enhancing control and precision.
RAGAS Evaluators: RAGAS Evaluators offer specialized tools to evaluate retrieval-augmented generation (RAG) workflows. These evaluators ensure the accuracy, relevance, and safety of responses by assessing factors like context precision, response relevancy, and faithfulness in both experiments and deployments.
December 2024
Evaluate features
Evaluator Library: The new Evaluator Library provides over 50 preconfigured templates to streamline quality checks, compliance, and contextual alignment. With customizable evaluators and seamless integration into experiments and deployments, this update ensures consistent quality control throughout the AI product development lifecycle.
Evals & Guardrails (HTTP and JSON): New HTTP and JSON evaluators and guardrails allow you to perform custom checks using external APIs and predefined JSON schemas. These tools help enforce compliance and validate inputs and outputs during experiments and deployments, enhancing control and precision.
RAGAS Evaluators: RAGAS Evaluators offer specialized tools to evaluate retrieval-augmented generation (RAG) workflows. These evaluators ensure the accuracy, relevance, and safety of responses by assessing factors like context precision, response relevancy, and faithfulness in both experiments and deployments.
December 2024
Evaluate features
Evaluator Library: The new Evaluator Library provides over 50 preconfigured templates to streamline quality checks, compliance, and contextual alignment. With customizable evaluators and seamless integration into experiments and deployments, this update ensures consistent quality control throughout the AI product development lifecycle.
Evals & Guardrails (HTTP and JSON): New HTTP and JSON evaluators and guardrails allow you to perform custom checks using external APIs and predefined JSON schemas. These tools help enforce compliance and validate inputs and outputs during experiments and deployments, enhancing control and precision.
RAGAS Evaluators: RAGAS Evaluators offer specialized tools to evaluate retrieval-augmented generation (RAG) workflows. These evaluators ensure the accuracy, relevance, and safety of responses by assessing factors like context precision, response relevancy, and faithfulness in both experiments and deployments.
November 2024
November 2024
November 2024
October 2024
October 2024
October 2024
September 2024
September 2024
September 2024
August 2024
August 2024
August 2024
July 2024
July 2024
July 2024
June 2024
June 2024
June 2024
May 2024
May 2024
May 2024
April 2024
April 2024
April 2024
March 2024
March 2024
March 2024
February 2024
February 2024
February 2024
January 2024
January 2024
January 2024
Start building AI apps with Orq.ai
Take a 14-day free trial. Start building AI products with Orq.ai today.
Start building AI apps with Orq.ai
Take a 14-day free trial. Start building AI products with Orq.ai today.
Start building AI apps with Orq.ai
Take a 14-day free trial. Start building AI products with Orq.ai today.