Label Scarcity

I want to evaluate and, if it fits, integrate a technique from recent AI research into my project.

## Technique: Label Scarcity
Label Scarcity: Semi-Supervised Pseudo-Labeling for RAG

Demonstrates how to expand a tiny labeled set into a large pseudo-labeled training corpus using iterative k-NN assignment in TF-IDF embedding space. Start with just 3–9 labeled examples per class — the algorithm propagates labels to unlabeled items by confidence-filtered nearest-neighbor votes, growing the pool over multiple self-training rounds. RAG applicability: Query intent classification, retrieval strategy routing (sparse/dense/hybrid), and embedding fine-tuning data generation — all cases where you have abundant unlabeled queries but only a handful of annotations.

## Reference implementation (Vector Ridge Labs, POC-010)
- Live demo: https://osoman2-gradio-pocs.hf.space/?poc=POC-010
- Source code: https://huggingface.co/spaces/osoman2/Gradio_pocs/tree/main/label_scarcity

## My project
<Describe your stack, the problem you want to solve and where this technique would sit. Example: "Python FastAPI RAG service over 50k PDFs, Postgres + pgvector, OpenAI embeddings, p95 latency budget 800 ms.">

## What I need from you
1. Read the reference source code and explain in at most 5 bullets how the technique works and what it would change compared to my current approach.
2. Decide whether it fits my case. If it does not, say why and stop there.
3. Propose the smallest viable integration: files or modules to touch, new dependencies, configuration.
4. Implement it behind a flag or as a separate function so it can be compared side by side with what I have today.
5. Add an evaluation script that measures agreement of the new metric with human judgement on a sample of my outputs, before and after, on my own data.
6. List the risks (latency, cost, failure modes) and what to monitor once it is in production.

Constraints: keep my existing stack and conventions, avoid heavy dependencies unless the gain is clear, and reference the file in the demo source whenever you reuse its logic.