09. Embedded Vector Stores: ChromaDB, DuckDB & In-Memory FAISS (Facebook AI Similarity Search) • Generative AI, Large Language Models (LLMs) & Vector RAG • Rishabh Ki Kaksha

Generative AI, Large Language Models (LLMs) & Vector RAG › 09. Embedded Vector Stores: ChromaDB, DuckDB & In-Memory FAISS (Facebook AI Similarity Search)

40 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

# 09. Embedded Vector Stores: ChromaDB, DuckDB & In-Memory FAISS (Facebook AI Similarity Search)

> Generative AI & Vector RAG Notes by Rishabh - Topic 09

---

### 1. In-Memory & Embedded Vector Engines 💾

Jab bina heavy cloud server deploy kiye local machine ya CI testing me instant vector search chahiye:
1. **FAISS (Meta AI - C++ Core):** Blazing fast GPU/CPU vector similarity library.
2. **ChromaDB:** Python SQLite + Clickhouse embedded vector store.
3. **DuckDB + vss:** Ultra-fast analytical columnar SQL database with vector search.

---

### 2. High-Speed FAISS GPU Index Setup

```python
import faiss
import numpy as np

d = 1536 # Embedding dimension
index = faiss.IndexHNSWFlat(d, 32) # HNSW index with M=32

# Transfer index to NVIDIA GPU:
res = faiss.StandardGpuResources()
gpu_index = faiss.index_cpu_to_gpu(res, 0, index)

# Add 100,000 vectors:
vectors = np.random.randn(100000, d).astype('float32')
faiss.normalize_L2(vectors)
gpu_index.add(vectors)

# Query Top-5 in < 0.2ms!
query = np.random.randn(1, d).astype('float32')
faiss.normalize_L2(query)
distances, indices = gpu_index.search(query, k=5)
```

---

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

1. **FAISS `IndexFlatIP` aur `IndexHNSWFlat` me kya difference hai?** -> `IndexFlatIP` exact brute-force search karta hai ($100\%$ accuracy par slow); `IndexHNSWFlat` graph based approximate search karta hai (Sub-millisecond).
2. **ChromaDB persistence kaise handle karta hai?** -> Local DuckDB/SQLite file aur Parquet data files me disk par save karta hai (`persist_directory`).
3. **FAISS index disk par save aur load kaise hota hai?** -> `faiss.write_index(index, "my.index")` aur `faiss.read_index("my.index")` binary serialization se.

---
**Next Topic:** 10. Document Chunking Strategies: Fixed Size, Recursive Character, Semantic Chunking & Parent Document Retrievers

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