-
Notifications
You must be signed in to change notification settings - Fork 0
Home
Julia Kurrr edited this page Jul 13, 2026
·
3 revisions
End-to-end documentation for the experiments that were done during the architectural development, optimization, and empirical validation of the localized retrieval-augmented generation system.
This wiki documents the work on a retrieval-augmented generation (RAG) pipeline built over 500K Wikipedia documents, structured across 5 interconnected pipeline modules. Each section below links to the detailed analysis of an individual subsystem.
[Embeddings] ---> [Vector Storage] ---> [Vector Index] ---> [Search Engine] ---> [UI Layer & LLM]
(18-Layer Gemma) (Custom Scalar) (Inverted File) (Hybrid ANN + (Streamlit UI +
(256d Embedding) (Quantization ) (512 Centroids) BM25 Fallback) Local Gemma 4)
- Core Model:
google/embeddinggemma-300m - Operational Baseline: Native bfloat16 inference with Hugging Face transformers execution architecture.
- Structural Optimization: 18-layer token-pruned framework paired with Matryoshka Representation Learning (768d to 256d truncation).
- Validation Protocol: Empirical grid-search benchmarking balancing hardware latency against semantic quality indices.
-
Output Artifacts:
wikipedia_embeddings_256d.npy(Storage & Indexing inputs) +wikipedia_metadata_manifest.json(UI & Validation maps).
- Scalar Quantization (SQ8): Custom mathematical conversion transforming raw float32 matrices into 1-byte int8 spaces (4× reduction).
- Low-Overhead Infrastructure: Implementation of a contiguous in-memory storage array bypassing heavy external database dependencies.
- Output Artifacts: Compressed int8 matrix optimized for sub-linear memory addressing.
- Spatial Partitioning: Scikit-learn K-Means clustering isolating 512 discrete centroids directly across the 256-dimensional Matryoshka space.
- Structural Engineering: Construction of a production-grade Inverted File Index (IVF) mapping document tokens to localized posting lists.
- Output Artifacts: Centroid coordinate arrays and mapped cell registers for accelerated subset querying.
- Baseline Framework: High-performance exact Brute-force KNN execution using PyTorch CUDA batch matrix multiplication.
- Optimized Framework: Sub-millisecond Approximate Nearest Neighbor (ANN) search localized within top-performing IVF cluster cells.
- Validation Protocol: Rigorous profiling over 50 test strings capturing systemic Recall@K coefficients, latency variants, and VRAM maps.
- Routing Architecture: Mathematical determination of a cosine similarity cutoff triggering a deterministic failover to classic BM25 keyword matching.
- Integration Core: Central control script (
main.py) executing cross-module function pipelines via a fast UI layer. - Fallback Interface: Live telemetry alerting users upon low-confidence semantic triggers and displaying immediate backup keyword search outputs.
- Generation Framework: Structured API linkage to local Gemma 4 runtime parsing source data constraints and enforcing specific citation schemas.
- Visual Verification: Production of responsive accordion display elements exposing raw article snippets, titles, and underlying confidence ratings.
| Metric | Value |
|---|---|
| Embedding model |
google/embeddinggemma-300m (34 layers, bfloat16) |
| Embedding dimension | 256 (Matryoshka-truncated from native 768) |
| Corpus size | 500,000 Wikipedia documents |
| Full corpus encoding | ~3 hours (Kaggle T4 ×2, BF16, batch=128) |
| Embedding latency per doc | ~21 ms (batch=128 throughput) |
| Vector storage (SQ8 quantized) | 122 MB |
| Vector storage (fp32 baseline) | 488 MB |
| Model VRAM footprint | ~890 MB |
| Mean pairwise cosine (random pairs) | 0.085 (healthy, threshold < 0.5) |
| Query embedding latency | 3–5 ms |
| ANN search latency (IVF-Flat, nprobe=64) | 1–3 ms |
| BM25 fallback latency | ~1 ms |
| Recall@10 (IVF-Flat) | 0.962 |
| LLM generation latency | 0.5–3 s (gemma3:4b, 512 max tokens) |
| End-to-end query latency | 1–4 s |
Last updated: 2026-07-13