Retrieval Augmented Generation in Production with Haystack

Table of contents

1. Brief Table of Contents (Not Yet Final)
2. 1. Using Generative AI with Haystack
   1. LLMs
      1. What Are LLMs?
      2. LLM Use-Cases
   2. Incorporating LLMs i n Industry Applications
      1. Retrieval Augmented Generation (RAG)
      2. Document Retrieval
      3. Vector Embeddings
      4. Storing Data
   3. Building Industry LLM Applications
      1. LLM Application Development Lifecycle
      2. RAG Use-Cases
   4. Build Your First RAG App Using Haystack
      1. Build A Basic RAG Pipeline
      2. Custom Components
      3. Evaluation and quick iteration
      4. Deploying Your App
   5. Summary
3. 2. Optimizing AI
   1. RAG Evaluation
      1. Evaluation With Ground Truth
      2. Evaluation Without Ground Truth
   2. Pipeline Optimizations
      1. Optimizing Chunking
      2. Optimizing Embeddings And Storage
      3. Basic Pipeline For Document Q&A
      4. Optimizing Retrieval
      5. Optimizing Generation
   3. Summary
4. 3. Observable AI
   1. Data and Concept Drifts
   2. GenAI Monitoring
      1. Quality
      2. Security
      3. Latency and Costs
   3. Logging and Tracing
      1. Logging
      2. Tracing
   4. Observability with Haystack
      1. Logging with Haystack
      2. Tracing With Haystack
      3. Visualizing Traces with Jaeger
      4. Security with Haystack
      5. GenAI Monitoring with Haystack
   5. Summary
5. 4. Advanced RAG and Keeping Pace with AI Developments
   1. AI Agents
      1. Conditional Routing With Haystack
      2. Tool Calling With Haystack
      3. Self-Reflection
   2. Multimodal RAG
   3. Knowledge Graphs For RAG
   4. SQL RAG
   5. Conclusion
6. About the Author