Design, Optimization, and Deployment of a Hybrid Agentic Retrieval-Augmented Generation (Agentic-RAG) Architecture

An engineer detailed the design and deployment of a hybrid agentic retrieval-augmented generation (RAG) architecture that combines dense semantic search (FAISS) with exact keyword search (BM25) and uses an autonomous LLM agent. The system overcomes vocabulary mismatches and hallucinations by using a cloud model and dynamic score normalization, achieving improved performance in benchmark tests.

Traditional RAG pipelines usually work deterministically by using only static vector search cite: 1 . Because of this, vocabulary mismatches can occur when searching for exact words or technical keywords, and the agent may be unable to verify context cite: 1 . In this research document, I explain the complete details of the Agentic Hybrid RAG architecture I engineered cite: 1 . It combines dense semantic search FAISS IndexFlatIP with L2-normalized embeddings and exact keyword search BM25Okapi , and operates through an autonomous LLM agent using the smolagents framework cite: 1 . It also describes in detail how I overcame issues encountered when running the model locally on CPU, such as Python sandbox import errors, extreme CPU time latency 213 seconds per step , and model hallucinations, by using a cloud model Qwen2.5-72B-Instruct and dynamic score normalization $\alpha=0.7$ , along with the benchmark results cite: 1 . Keywords: Agentic AI, Retrieval-Augmented Generation RAG , Hybrid Search, FAISS, BM25, Smolagents, Knowledge Grounding, Score Normalization cite: 1 . Across enterprise decision-support systems, the deployment of large language models LLMs has exposed significant architectural weaknesses: static parametric knowledge cutoffs, hallucinated facts, and an inability to access proprietary ground-truth records cite: 1 . While standard retrieval-augmented generation RAG addresses these weaknesses by providing external context before generation, canonical RAG pipelines continue to operate in a rigid, deterministic manner cite: 1 . In standard RAG, every query leads to a vector lookup that is not much different cite: 1 . As a result, pipelines fail when queries involve exact alphanumeric codes or rare technical terms vocabulary mismatch problem , or when multiple stages of logical analysis are needed before retrieval cite: 1 . This study aims to design, build, and evaluate an autonomous "agentic hybrid RAG" system that functions as a rational, reasoning-capable system cite: 1 . Its main objectives are: This system includes three mutually complementary components: Architectural Workflow Summary: User Query -- Agent Reasoning -- Code Tool Call: knowledge base search query -- Dual Index: FAISS Vector cos θ + BM25 Lexical -- Min-Max Score Normalization -- Weighted Fusion α=0.7 -- Top-K Passages -- Grounded Answer Synthesis cite: 1 . We divide the source documents $D={d 1, d 2, \dots, d N}$ using recursive character boundary splitting cite: 1 . To maintain semantic continuity, we use a windowing function: Equation 1 : C = Chunk di, W size = 300, W overlap = 50 Here, a chunk size of 300 characters and an overlap of 50 characters are used; this overlap prevents semantic discontinuity between chunk boundaries and ensures completeness of information cite: 1 . Each part chunk $c j$ in $C$ is embedded into a dense vector $e j \in \mathbb{R}^{384}$ using all-MiniLM-L6-v2 , and then L2-normalized efficiently cite: 1 : Equation 2 : ê j = e j / ||e j|| 2, such that ||ê j|| 2 = 1.0 The vectors are indexed using faiss.IndexFlatIP cite: 1 . For a normalized query vector $\hat{q}$, the inner product exactly computes the directional cosine similarity cite: 1 : Equation 3 : Sim q̂, ê j = q̂ · ê j = Σ q̂ k · ê j,k = cos θ IndexFlatIP , by avoiding lossy quantization or clustering-based approximate calculations, guarantees 100% accuracy in vector space cite: 1 . Concurrently, chunks are tokenized after stop-word sanitation cite: 1 . The lexical relevance score of query tokens $Q={t 1, \dots, t m}$ against chunk $c j$ is computed via the probabilistic BM25 model, with saturation parameter $k 1=1.5$ and length normalization $b=0.75$ cite: 1 . Since the distributions of dense vector inner products and BM25 scores do not match, directly combining them causes a large imbalance or skew cite: 1 . Therefore, we apply feature-level min-max scaling cite: 1 : Equation 5 : Ŝ x = S x - min S / max S - min S + ε The final unified hybrid ranking score is computed as cite: 1 : Equation 6 : S hybrid c j = α · Ŝ vector c j + 1 - α · Ŝ keyword c j where $\alpha=0.7$ prioritizes semantic context while allocating 30% weight to exact keyword preservation cite: 1 . The shift from an interactive notebook to a practical standalone system in VS Code has revealed four critical failure points cite: 1 : | Challenge / Failure Mode | Observed Root Cause | Engineering Countermeasure | |---|---|---| 1. Sandbox Import Violation cite: 1 | Small LLM 1.5B hallucinated external APIs requests , wolframalpha cite: 1 . | Enforced explicit tool prompting; transitioned backbone to Qwen2.5-72B-Instruct cite: 1 . | 2. CPU Compute Latency cite: 1 | Local inference exceeded 213 seconds per reasoning step on consumer CPU cite: 1 . | Offloaded LLM reasoning to Hugging Face hosted GPU endpoints InferenceClientModel cite: 1 . | 3. API Interface Drift cite: 1 | smolagents renamed HfApiModel to InferenceClientModel across package updates cite: 1 . | Implemented multi-version dynamic try-except fallback import wrapper cite: 1 . | 4. Vocabulary Mismatch cite: 1 | BM25 failed on conceptual synonyms; pure vector missed exact alphanumeric IDs cite: 1 . | Engineered dual-engine weighted hybrid fusion $\alpha=0.7$ and Min-Max scaling cite: 1 . | When running a 1.5B model locally, the agent made uncontrolled network calls for example: import requests; request.get 'http://api.wolframalpha.com/...' cite: 1 . Since the CodeAgent is running in a secure sandbox that allows only standard math libraries math , re , collections , an Interpreter Error occurred and execution stopped cite: 1 . Solution: The agent's reasoning backbone was upgraded to Qwen2.5-72B-Instruct , and that resolved this issue cite: 1 . This large model, which follows instructions accurately, strictly adhered to the given system contract and made precise calls to knowledge base search query=... without unnecessary assumptions or hallucinations about external dependencies cite: 1 . When running the first stage of the iterative generation on local CPU hardware, an unacceptable time of 213.85 seconds was required cite: 1 . By shifting model inference to high-capacity cloud endpoints, the latency at each stage dropped from over 210 seconds to under 2.4 seconds; this indicates an approximately 89-fold increase in speed cite: 1 . To measure retrieval precision and the ability to control hallucination, the hybrid agentic pipeline was evaluated across three different search categories cite: 1 : | Retrieval Paradigm | Semantic Recall | Exact Identifier | Composite MRR@3 | |---|---|---|---| Pure Vector IndexFlatIP cite: 1 | 0.94 cite: 1 | 0.62 cite: 1 | 0.81 cite: 1 | Pure Keyword BM25Okapi cite: 1 | 0.48 cite: 1 | 0.96 cite: 1 | 0.74 cite: 1 | Hybrid Fusion $\alpha=0.7$ cite: 1 | 0.95 cite: 1 | 0.93 cite: 1 | 0.96 cite: 1 | In benchmark tests, the agent achieved 100% grounding verification on specific target queries cite: 1 . When answering the question, "What is RAG, and why are embeddings important in a RAG system?" , the agent used a hybrid search tool and analyzed information from the RAG001 and EMB001 chunks, producing a comprehensive response that clearly explained vector conversion, semantic indexing, and grounded context synthesis without factual errors cite: 1 . To scale this architecture into enterprise production, we are implementing four key enhancements cite: 1 : This research demonstrated the full reality of an agentic hybrid RAG architecture cite: 1 . By combining FAISS dense vector retrieval, BM25 sparse lexical indexing, and an autonomous code-executing LLM agent, the system overcomes the limitations of static RAG pipelines cite: 1 . We addressed core engineering challenges related to sandbox execution safety, inference latency, and library version compatibility cite: 1 . The empirical results confirm that integrating hybrid retrieval with autonomous agent decision-making delivers better grounding, stronger keyword precision, and highly fast, factual synthesis, establishing a modular framework for modern enterprise AI architectures cite: 1 .