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)
        • 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. On-Premise Deployment
  3. Evaluation Deployment Guide

Evaluation Maintenance Guide

PreviousEvaluation Deployment GuideNextFine Tuning (OpenAI)

Last updated 4 months ago

Was this helpful?

This document provides a comprehensive guide to maintaining and managing the Raga Catalyst infrastructure, covering key operational tasks and configurations.

IP Address Update

Purpose: Update the VM IP address

Command:

bash $HOME/raga-evaluation-scripts/scripts/update_ip_address.sh
Proxy URL Update

Purpose: Update the proxy server URL

Command:

bash $HOME/raga-evaluation-scripts/scripts/update_proxy_url.sh <proxy_server_endpoint>

Note: Replace <proxy_server_endpoint> with the actual proxy server endpoint

Enable Backups for AWS Instance

### Purpose Enable periodic backups for the Raga Catalyst AWS instance.

Step 1: Create an IAM Policy

  1. Go to the IAM Console in AWS

  2. Navigate to Policies > Create Policy

  3. Choose the JSON tab and enter the following policy:

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Sid": "VisualEditor0",
            "Effect": "Allow",
            "Action": [
                "ec2:DescribeVolumes",
                "ec2:DescribeInstances",
                "ec2:CreateSnapshot",
                "ec2:DescribeSnapshots",
                "ec2:CreateTags",
                "ec2:DeleteSnapshot"
            ],
            "Resource": "*"
        }
    ]
}
  1. Click Next and provide a name: RagaCatalyst-EbsSnapshot-Policy

  2. Review and create the policy

Step 2: Create an IAM Role

  1. Go to the IAM Console and navigate to Roles

  2. Click Create Role

  3. Under Select trusted entity, choose AWS service

  4. Choose EC2 as the use case

  5. Click Next and attach the previously created policy

  6. Give the role a name: RagaCatalyst-EbsSnapshot-Role

  7. Create the role

Step 3: Attach the Role to an EC2 Instance

  1. Go to the EC2 Console

  2. Select the instance you want to modify

  3. Click Actions > Security > Modify IAM role

  4. Select the role RagaCatalyst-EbsSnapshot-Role and save

Step 4: Schedule a Cron Job for Snapshots

SSH into the EC2 instance and execute:

(crontab -l; echo "0 1 * * * bash $HOME/raga-evaluation-scripts/scripts/aws-ebs-backup.sh") | crontab -

Note: This creates an AMI snapshot once a day at 1 AM UTC. Adjust the cron expression as needed.

Enable Backups for GCP Instance

Purpose

Enable periodic backups for the Raga Catalyst GCP instance.

Prerequisites

  • GCP Console access with Owner or Editor role

  • VM instance details (IP address)

  • IAM permissions to modify service accounts and VM configurations

Configuration Steps

1. Project Configuration

  1. Navigate to

  2. Verify active project in top navigation

  3. Document:

    • Project ID

    • Project Number (from Dashboard > Project Info)

2. VM Instance Setup

  1. Access Compute Engine > VM Instances

  2. Locate target VM using Internal/External IP

  3. Document instance details:

    • Instance name

    • Zone

    • IP addresses

3. Service Account Configuration

Initial Setup

  1. Stop the VM instance

  2. Navigate to instance settings

  3. Click "Edit"

Service Account Attachment

  1. Select "Compute Engine default service account"

    • Format: PROJECT_NUMBER-compute@developer.gserviceaccount.com

  2. Configure Access Scopes:

    • Set "Access for each API"

    • Enable:

      • Compute Engine: "Read Write"

      • Storage: "Read Write"

      • Cloud Platform: "Full Access"

  3. Save and restart VM

Note: Public IP may change after restart. Document new IP.

4. IAM Role Setup

  1. Navigate to IAM & Admin > IAM

  2. Locate compute service account

  3. Add "Compute Storage Admin" role

  4. Save changes

5. Snapshot Scheduling

  1. SSH into Azure VM

  2. Execute:

    echo "0 1 * * * $HOME/raga-evaluation-scripts/scripts/GCP-disk-backup.sh" | crontab -

    This creates daily snapshots at 1 AM UTC.

Verification

  1. VM Configuration:

    • Confirm service account attachment

    • Verify configured scopes

  2. IAM Settings:

    • Check storage admin role assignment

    • Verify permissions

Technical Requirements

Service Account

  • Format: PROJECT_NUMBER-compute@developer.gserviceaccount.com

  • Required scopes:

    • compute-rw

    • storage-rw

    • cloud-platform

VM State

  • Must be stopped for service account modifications

  • Must be running for snapshot operations

Important Notes

  • Both service account scopes AND IAM roles are required

  • Allow full VM startup before testing

  • Verify all permissions before snapshot operations

  • Cron schedule can be modified based on requirements

Support

For additional assistance or issues, please contact your system administrator or GCP support team.

Enable Backups for Azure Instance

Purpose

Enable periodic backups for the Raga Catalyst Azure instance.

Enable System-Assigned Managed Identity

Follow these steps in the Azure Portal:

  1. Open the Azure Portal

  2. Navigate to the Virtual Machines service and select your VM

  3. In the left-hand menu, find the Identity section under Settings

  4. Under the System-assigned tab, toggle the Status to On

  5. Click Save

  6. Note down the Object ID of the managed identity once enabled

Grant Permissions to the Managed Identity

The managed identity needs appropriate permissions to execute operations like fetching VM metadata, retrieving disk information, and managing snapshots.

Identify Resource Group

  1. Navigate to the Overview section of the VM in Azure Portal

  2. Note down the Resource Group name

Assign Required Roles

  1. Navigate to the Resource Group of the VM

  2. Click on Access Control (IAM) in the left-hand menu

  3. Click + Add > Add role assignment

  4. Select the Disk Snapshot Contributor role

  5. Under "Assign access to", select Managed identity

  6. Search for your VM's managed identity and click Save

Schedule Snapshot Creation

To set up automatic snapshot creation:

  1. SSH into the Azure VM using terminal

  2. Execute the following command to schedule snapshots:

    echo "0 1 * * * $HOME/raga-evaluation-scripts/scripts/Azure-disk-backup.sh" | crontab -

    This configuration creates an AMI snapshot daily at 1 AM UTC. You can modify the cron expression based on your requirements.

GCP Console