LogoLogo
Slack CommunityCatalyst Login
  • Welcome
  • RagaAI Catalyst
    • User Quickstart
    • Concepts
      • Configure Your API Keys
      • Supported LLMs
        • OpenAI
        • Gemini
        • Azure
        • AWS Bedrock
        • ANTHROPIC
      • Catalyst Access/Secret Keys
      • Enable Custom Gateway
      • Uploading Data
        • Create new project
        • RAG Datset
        • Chat Dataset
          • Prompt Format
        • Logging traces (LlamaIndex, Langchain, etc.)
        • Trace Masking Functions
        • Trace Level Metadata
        • Correlating Traces with External IDs
        • Add Dataset
      • Running RagaAI Evals
        • Executing Evaluations
        • Compare Datasets
      • Analysis
      • Embeddings
    • RagaAI Metric Library
      • RAG Metrics
        • Hallucination
        • Faithfulness
        • Response Correctness
        • Response Completeness
        • False Refusal
        • Context Relevancy
        • Context Precision
        • Context Recall
        • PII Detection
        • Toxicity
      • Chat Metrics
        • Agent Quality
        • Instruction Adherence
        • User Chat Quality
      • Text-to-SQL
        • SQL Response Correctness
        • SQL Prompt Ambiguity
        • SQL Context Ambiguity
        • SQL Context Sufficiency
        • SQL Prompt Injection
      • Text Summarization
        • Summary Consistency
        • Summary Relevance
        • Summary Fluency
        • Summary Coherence
        • SummaC
        • QAG Score
        • ROUGE
        • BLEU
        • METEOR
        • BERTScore
      • Information Extraction
        • MINEA
        • Subjective Question Correction
        • Precision@K
        • Chunk Relevance
        • Entity Co-occurrence
        • Fact Entropy
      • Code Generation
        • Functional Correctness
        • ChrF
        • Ruby
        • CodeBLEU
        • Robust Pass@k
        • Robust Drop@k
        • Pass-Ratio@n
      • Marketing Content Evaluation
        • Engagement Score
        • Misattribution
        • Readability
        • Topic Coverage
        • Fabrication
      • Learning Management System
        • Topic Coverage
        • Topic Redundancy
        • Question Redundancy
        • Answer Correctness
        • Source Citability
        • Difficulty Level
      • Additional Metrics
        • Guardrails
          • Anonymize
          • Deanonymize
          • Ban Competitors
          • Ban Substrings
          • Ban Topics
          • Code
          • Invisible Text
          • Language
          • Secret
          • Sentiment
          • Factual Consistency
          • Language Same
          • No Refusal
          • Reading Time
          • Sensitive
          • URL Reachability
          • JSON Verify
        • Vulnerability Scanner
          • Bullying
          • Deadnaming
          • SexualContent
          • Sexualisation
          • SlurUsage
          • Profanity
          • QuackMedicine
          • DAN 11
          • DAN 10
          • DAN 9
          • DAN 8
          • DAN 7
          • DAN 6_2
          • DAN 6_0
          • DUDE
          • STAN
          • DAN_JailBreak
          • AntiDAN
          • ChatGPT_Developer_Mode_v2
          • ChatGPT_Developer_Mode_RANTI
          • ChatGPT_Image_Markdown
          • Ablation_Dan_11_0
          • Anthropomorphisation
      • Guardrails
        • Competitor Check
        • Gibberish Check
        • PII
        • Regex Check
        • Response Evaluator
        • Toxicity
        • Unusual Prompt
        • Ban List
        • Detect Drug
        • Detect Redundancy
        • Detect Secrets
        • Financial Tone Check
        • Has Url
        • HTML Sanitisation
        • Live URL
        • Logic Check
        • Politeness Check
        • Profanity Check
        • Quote Price
        • Restrict Topics
        • SQL Predicates Guard
        • Valid CSV
        • Valid JSON
        • Valid Python
        • Valid Range
        • Valid SQL
        • Valid URL
        • Cosine Similarity
        • Honesty Detection
        • Toxicity Hate Speech
    • Prompt Playground
      • Concepts
      • Single-Prompt Playground
      • Multiple Prompt Playground
      • Run Evaluations
      • Using Prompt Slugs with Python SDK
      • Create with AI using Prompt Wizard
      • Prompt Diff View
    • Synthetic Data Generation
    • Gateway
      • Quickstart
    • Guardrails
      • Quickstart
      • Python SDK
    • RagaAI Whitepapers
      • RagaAI RLEF (RAG LLM Evaluation Framework)
    • Agentic Testing
      • Quickstart
      • Concepts
        • Tracing
          • Langgraph (Agentic Tracing)
          • RagaAI Catalyst Tracing Guide for Azure OpenAI Users
        • Dynamic Tracing
        • Application Workflow
      • Create New Dataset
      • Metrics
        • Hallucination
        • Toxicity
        • Honesty
        • Cosine Similarity
      • Compare Traces
      • Compare Experiments
      • Add metrics locally
    • Custom Metric
    • Auto Prompt Optimization
    • Human Feedback & Annotations
      • Thumbs Up/Down
      • Add Metric Corrections
      • Corrections as Few-Shot Examples
      • Tagging
    • On-Premise Deployment
      • Enterprise Deployment Guide for AWS
      • Enterprise Deployment Guide for Azure
      • Evaluation Deployment Guide
        • Evaluation Maintenance Guide
    • Fine Tuning (OpenAI)
    • Integration
    • SDK Release Notes
      • ragaai-catalyst 2.1.7
  • RagaAI Prism
    • Quickstart
    • Sandbox Guide
      • Object Detection
      • LLM Summarization
      • Semantic Segmentation
      • Tabular Data
      • Super Resolution
      • OCR
      • Image Classification
      • Event Detection
    • Test Inventory
      • Object Detection
        • Failure Mode Analysis
        • Model Comparison Test
        • Drift Detection
        • Outlier Detection
        • Data Leakage Test
        • Labelling Quality Test
        • Scenario Imbalance
        • Class Imbalance
        • Active Learning
        • Image Property Drift Detection
      • Large Language Model (LLM)
        • Failure Mode Analysis
      • Semantic Segmentation
        • Failure Mode Analysis
        • Labelling Quality Test
        • Active Learning
        • Drift Detection
        • Class Imbalance
        • Scenario Imbalance
        • Data Leakage Test
        • Outlier Detection
        • Label Drift
        • Semantic Similarity
        • Near Duplicates Detection
        • Cluster Imbalance Test
        • Image Property Drift Detection
        • Spatio-Temporal Drift Detection
        • Spatio-Temporal Failure Mode Analysis
      • Tabular Data
        • Failure Mode Analysis
      • Instance Segmentation
        • Failure Mode Analysis
        • Labelling Quality Test
        • Drift Detection
        • Class Imbalance
        • Scenario Imbalance
        • Label Drift
        • Data Leakage Test
        • Outlier Detection
        • Active Learning
        • Near Duplicates Detection
      • Super Resolution
        • Semantic Similarity
        • Active Learning
        • Near Duplicates Detection
        • Outlier Detection
      • OCR
        • Missing Value Test
        • Outlier Detection
      • Image Classification
        • Failure Mode Analysis
        • Labelling Quality Test
        • Class Imbalance
        • Drift Detection
        • Near Duplicates Test
        • Data Leakage Test
        • Outlier Detection
        • Active Learning
        • Image Property Drift Detection
      • Event Detection
        • Failure Mode Analysis
        • A/B Test
    • Metric Glossary
    • Upload custom model
    • Event Detection
      • Upload Model
      • Generate Inference
      • Run tests
    • On-Premise Deployment
      • Enterprise Deployment Guide for AWS
      • Enterprise Deployment Guide for Azure
  • Support
Powered by GitBook
On this page

Was this helpful?

  1. RagaAI Catalyst
  2. RagaAI Metric Library
  3. Additional Metrics
  4. Guardrails

Reading Time

Calculates the reading time of the model response

Required Parameters: Prompt, Response

Interpretation: score represnts the reading time in minutes for the prompt response. if the score is greater than threshold, the test will fail

Code Example:

prompt = '''Write an article on Artificial Intelligence'''

response = '''In the realm of technological innovation, few fields hold as much promise and excitement as Artificial Intelligence (AI). Often portrayed in science fiction as sentient robots or super-intelligent machines, AI in reality encompasses a diverse range of technologies that enable machines to simulate human intelligence. From self-driving cars to personalized recommendations on streaming platforms, AI is already woven into the fabric of our daily lives, and its impact is only set to grow.
At its core, AI involves the development of algorithms and systems that can perform tasks which typically require human intelligence. These tasks include learning from data, recognizing patterns, making decisions, and even understanding natural language. Machine Learning, a subset of AI, has been particularly transformative. It allows computers to learn from vast amounts of data and improve their performance without being explicitly programmed.
One of the key strengths of AI lies in its ability to process and analyze data at a scale and speed beyond human capability. This has led to groundbreaking applications in various industries. In healthcare, AI is being used to analyze medical images for early detection of diseases such as cancer. It can sift through massive datasets to identify trends and insights that aid researchers and doctors in providing better care.
Financial institutions rely on AI algorithms for fraud detection, risk assessment, and algorithmic trading. Chatbots powered by AI are becoming ubiquitous in customer service, offering quick and efficient responses to queries. Smart home devices use AI to understand and adapt to users' preferences, creating more comfortable and energy-efficient living spaces.
However, the rapid advancement of AI also raises important questions and challenges. Ethical considerations surrounding AI, such as privacy, bias in algorithms, and the potential for job displacement, need careful attention. Ensuring transparency and accountability in AI systems is crucial to building trust among users.
Looking ahead, the future of AI holds immense possibilities. As researchers delve deeper into areas like Artificial General Intelligence (AGI) aiming to create machines with human-like cognitive abilities, the boundaries of what AI can achieve continue to expand.
In conclusion, Artificial Intelligence stands at the forefront of the technological revolution, reshaping industries and the way we interact with machines. While presenting exciting opportunities, it also demands thoughtful and responsible development to harness its full potential for the benefit of society.'''

evaluator.add_test(
    test_names=["reading_time_guardrail"],
    data={'prompt':prompt,
          'response': response,

    },

).run()

evaluator.print_results()
PreviousNo RefusalNextSensitive

Last updated 1 year ago

Was this helpful?