11. Hybrid Search Architecture: Combining Keyword Search (BM25) + Dense Vector Search with Reciprocal Rank Fusion (RRF) • Generative AI, Large Language Models (LLMs) & Vector RAG • Rishabh Ki Kaksha

Generative AI, Large Language Models (LLMs) & Vector RAG › 11. Hybrid Search Architecture: Combining Keyword Search (BM25) + Dense Vector Search with Reciprocal Rank Fusion (RRF)

50 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

# 11. Hybrid Search Architecture: Combining Keyword Search (BM25) + Dense Vector Search with Reciprocal Rank Fusion (RRF)

> Generative AI & Vector RAG Notes by Rishabh - Topic 11

---

### 1. Why Pure Vector Search Fails in Enterprise RAG ⚠️

*   User query: *"Show error log for CVE-2024-3094 on node prod-db-02"*.
*   Pure Vector Search generic "vulnerabilities and databases" articles retrieve karega!
*   **Hybrid Search:** **BM25 Keyword Search** (Exact error strings) + **Dense Vector Search** (Conceptual meaning) dono parallel run karta hai!

---

### 2. Reciprocal Rank Fusion (RRF) Algorithm 🧮

Score scale differences ko ignore karke purely Rank Positions se aggregate karta hai:
$$\text{RRF\_Score}(d) = \sum_{m \in \{\text{Dense}, \text{Sparse}\}} \frac{1}{k + \text{Rank}_m(d)} \quad (\text{Standard } k = 60)$$

```python
def reciprocal_rank_fusion(dense_ranks: dict, sparse_ranks: dict, k: int = 60) -> list:
    rrf_scores = {}
    for doc_id, rank in dense_ranks.items():
        rrf_scores[doc_id] = rrf_scores.get(doc_id, 0.0) + (1.0 / (k + rank))
    for doc_id, rank in sparse_ranks.items():
        rrf_scores[doc_id] = rrf_scores.get(doc_id, 0.0) + (1.0 / (k + rank))

# Sort descending:
    return sorted(rrf_scores.items(), key=lambda x: x[1], reverse=True)
```

---

### 3. Master Comparison Matrix

---

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

1. **RRF me constant $k=60$ ka kya role hota hai?** -> Higher rank items ko overly dominant hone se mitigate karta hai aur outliers ko smooth karta hai.
2. **Dense aur Sparse scores ko direct multiply/add kyu nahi karte?** -> Kyunki BM25 scores unbounded $(0, +\infty)$ hote hain jabki Cosine similarity bounded $[-1, 1]$ hoti hai (Scale mismatch!).
3. **Qdrant aur Elasticsearch hybrid search kaise execute karte hain?** -> Single query API call me dense vector aur sparse vector pass karke internal RRF / Relative Score Fusion execute karna.

---
**Next Topic:** 12. Cross-Encoder Reranking: Integrating Cohere Rerank / BGE-Reranker for Pinpoint Context Relevance

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