🛠️ How-to Guides

The how-to guides offer a more comprehensive overview of all the tools Ragas offers and how to use them. This will help you tackle messier real-world usecases when you’re using the framework to help build your own RAG pipelines.

The guides assume you are familiar and confortable with the Ragas basics. If your not feel free to checkout the Get Started sections first.

These guides are organized into 3 sections

• Customisations: How to customise Ragas to use with your system. Things like changing the LLMs used underneath are covered here.

• Applications: Shows how to leverage Ragas framework to solve various real-world problems that you might be facing too.

• Integrations: Integrations with other tools like langchain and llamaindex, making it super easy to add ragas into your setup.

You can check the entire list bellow 👇

Index

• Customizations
  • Bring Your Own LLMs and Embeddings
    • Evaluations
    • Test set Generation
      • LLMs
      • DocumentStore
  • Using Ragas Critic Model instead of GPT-4
  • Importing required modules
    • Setting up generator Model (gpt-3.5)
    • Setting up Model
    • Set up custom Critic Model instead of GPT-4
  • Loading data
  • Generating
  • Using Azure OpenAI
    • Load sample dataset
    • Configuring them for Azure OpenAI endpoints
    • Evaluation
    • Test set generation
  • Using Amazon Bedrock
    • Metrics
      • Load sample dataset
      • Evaluation
    • Test Data Generation
  • Using Vertex AI
    • Load Sample Dataset
    • Evaluation
• Applications
  • Prepare data for evaluation
    • Example dataset
  • Compare Embeddings for retriever
    • Create synthetic test data
    • Build your RAG
    • Import metrics from ragas
    • Evaluate OpenAI embeddings
    • Evaluate Bge embeddings
    • Compare Scores
  • Compare LLMs using Ragas Evaluations
    • Create synthetic test data
    • Build your RAG
    • Import metrics from ragas
    • Evaluate Zephyr 7B Alpha LLM
    • Evaluate Falcon-7B-Instruct LLM
    • Compare Scores
      • Score distribution analysis
  • Write custom prompts with ragas
  • Automatic language adaptation
    • Language Adaptation for Metrics
      • Dataset
      • Adapt metrics to target language
      • Evaluate
    • Language Adaptation for Testset Generation
      • Documents
      • Import and adapt evolutions
      • Generate dataset
  • Explainability through Logging and tracing
• Integrations
  • Evaluating LlamaIndex
    • Building the VectorStoreIndex and QueryEngine
    • Evaluating with Ragas
  • Evaluating Langchain QA Chains
    • Introducing RagasEvaluatorChain
    • Evaluate with langsmith
  • Langsmith Integrations
    • Tracing ragas metrics
  • Arize-Phoenix
    • 1. Introduction
    • 2. Install Dependencies and Import Libraries
    • 3. Configure Your OpenAI API Key
    • 4. Generate Your Synthetic Test Dataset
    • 5. Build Your RAG Application With LlamaIndex
    • 6. Evaluate Your LLM Application
    • 7. Visualize and Analyze Your Embeddings
    • 8. Recap
  • Online Evaluation of RAG with Langfuse
    • The Environment
    • The Data
    • The Metrics
    • The Setup
    • Score with Trace
    • Scoring as batch
  • Athina: Ragas Metrics on your Production Logs
    • ▷ Running Athina Programmatically
    • ▷ Configure Ragas to run automatically on your production logs
      • Learn more about Athina
  • Visualizing Ragas Results with Zeno
  • Tonic Validate: Visualize Ragas Scores
    • Getting Started
    • Reaching out 👋
  • Evaluating Haystack
    • Installation
      • Setting your OPENAI_API_KEY environment variable
    • Use the RagasEvaluator in a Haystack pipeline