17. Guardrails & Safety: NeMo Guardrails, Llama Guard & Prompt Injection Defense Mechanisms • Generative AI, Large Language Models (LLMs) & Vector RAG • Rishabh Ki Kaksha

Generative AI, Large Language Models (LLMs) & Vector RAG › 17. Guardrails & Safety: NeMo Guardrails, Llama Guard & Prompt Injection Defense Mechanisms

45 mins

← Prev Next →

Course Syllabus

Module 1: Large Language Model (LLM) Fundamentals & Transformer Architecture

01. Transformer Architecture Deep Dive: Self-Attention Mechanism, Multi-Head Attention & Positional Encoding 02. Autoregressive Generation: Tokenization (BPE, WordPiece, SentencePiece), Sampling (Temperature, Top-K, Top-P) 03. Prompt Engineering Architecture: Few-Shot Prompting, Chain-of-Thought (CoT), ReAct & System Prompt Hardening

Part 1: LLM Internals & Vector RAG Pipelines

Module 2: Embeddings, Vector Spaces & Similarity Mathematics

04. Vector Embeddings: Dense vs Sparse Vectors (OpenAI text-embedding-3, BGE-Large, BM25) 05. Similarity Metrics: Cosine Similarity, Dot Product, Euclidean Distance & Manifold Geometry 06. Approximate Nearest Neighbor (ANN) Algorithms: HNSW (Hierarchical Navigable Small World) & IVF-PQ Indexes

Module 3: Vector Databases: Pinecone, Qdrant, Milvus, Chroma & pgvector

07. Vector Database Architecture: Comparing Pinecone, Qdrant, Weaviate, Milvus & PostgreSQL with pgvector 08. Metadata Filtering & Payload Indexing for High-Performance Multitenant Vector Search 09. Embedded Vector Stores: ChromaDB, DuckDB & In-Memory FAISS (Facebook AI Similarity Search)

Module 4: Advanced RAG Architecture: Chunking, Reranking & Hybrid Search

10. Document Chunking Strategies: Fixed Size, Recursive Character, Semantic Chunking & Parent Document Retrievers 11. Hybrid Search Architecture: Combining Keyword Search (BM25) + Dense Vector Search with Reciprocal Rank Fusion (RRF) 12. Cross-Encoder Reranking: Integrating Cohere Rerank / BGE-Reranker for Pinpoint Context Relevance

Module 5: Context Window Optimization, Multi-Query & Graph RAG

13. Multi-Query Generation, Sub-Question Decomposition & Step-Back Prompting for Complex Questions 14. Context Compression & Lost-in-the-Middle Mitigation Strategies 15. Graph RAG Architecture: Combining Knowledge Graphs (Neo4j / NetworkX) with Vector Search for Relational Insights

Module 6: RAG Evaluation (RAGAS), Guardrails & Production Deployment

16. RAG Evaluation Framework (RAGAS): Faithfulness, Answer Relevance, Context Precision & Context Recall 17. Guardrails & Safety: NeMo Guardrails, Llama Guard & Prompt Injection Defense Mechanisms 18. Streaming Output Architecture with Server-Sent Events (SSE) & WebSocket RAG Responses 19. Caching in GenAI: Semantic Caching with GPTCache & Redis to Slash API Costs by 70% 20. Production GenAI Deployment: Building an Enterprise PDF/Docs AI Assistant with LangChain & LlamaIndex

Interactive Lesson Studio

# 17. Guardrails & Safety: NeMo Guardrails, Llama Guard & Prompt Injection Defense Mechanisms

> Generative AI & Vector RAG Notes by Rishabh - Topic 17

---

### 1. The Multi-Layered AI Firewall 🛡️

```
[ User Input ] ➔ [ 1. Input Guardrail (Prompt Injection / Toxicity / PII Filter) ]
                         ⬇
                 [ LLM Core Engine + Vector RAG ]
                         ⬇
[ Safe Output ] ◄── [ 2. Output Guardrail (Hallucination / PII Mask / Topic Compliance) ]
```

---

### 2. Llama Guard 3 & NeMo Guardrails Architecture

*   **Llama Guard:** Meta's fine-tuned safety classifier (Detects hate speech, self-harm, sexual content, cyberattacks).
*   **PII Masking (Microsoft Presidio):** Aadhaar numbers, Credit Cards, Emails ko automatically redact karna (`[REDACTED_PHONE]`).

---

### 3. Interview Ke 3 Sawal Is Topic Se

1. **Indirect Prompt Injection kya hoti hai?** -> Jab user prompt safe ho, lekin retrieve kiya gaya third-party PDF document ya webpage malicious instruction contain karta ho jo LLM ko hijack kar leti hai.
2. **Self-Harm / Toxic outputs intercept hone par latency kitni add hoti hai?** -> Small safety classifier model (e.g. 1B) use karne par ~20ms overhead.
3. **Canary Tokens prompt leakage detection me kaise use hote hain?** -> System prompt me ek secret random string chupana; agar output me canary token dikhe toh response instantly drop karna.

---
**Next Topic:** 18. Streaming Output Architecture with Server-Sent Events (SSE) & WebSocket RAG Responses

Loading lesson content...

Python 3.12

Full IDE

Live Execution Terminal

Click "Execute Live" to run code.
                

Lesson Mastery AI Quiz

AI Doubt Solver

CERTIFICATE OF COMPLETION

Rishabh Gehlot

PHP 8+ & Laravel 11 Master Track