30d roadmap · 5 milestones
30-Day Retrieval Basics
Four weeks that take you from tokenization to a working hybrid retriever evaluated against a frozen query set.
Outcome: Build a solid foundation in both lexical and vector retrieval, ending with hybrid search.
How to work this roadmap
Treat each milestone as a claim that must be supported by evidence. Before reading, write what you think the mechanism does and where it will fail. After studying the linked concepts, run the drills without copying an answer, preserve the output, and revise the explanation. Move forward when you can connect the milestone goal to a working implementation, benchmark, architecture decision, or reviewable design artifact.
The 30d horizon is a sequencing aid, not a completion badge. Spend more time where your prediction and the observed behavior disagree. Keep a short decision log containing the mechanism selected, alternatives rejected, expected failure mode, measurement used, and remaining uncertainty. Review that log with FSRS prompts so the roadmap produces durable system judgment rather than a temporary tour of terminology.
At the end, explain Build a solid foundation in both lexical and vector retrieval, ending with hybrid search. from first principles to a reader outside the domain. A strong explanation should survive follow-up questions about correctness, cost, latency, resource use, security, recovery, and operational visibility. If it cannot, return to the milestone that contains the missing mechanism and build a smaller falsifiable example.
Milestones
Milestone 1
Prerequisites — unlock the rest of this path
Concepts the later milestones depend on. Without these the planner cannot serve the rest of this roadmap.
Concepts
Milestone 2
Week 1 — Lexical retrieval
Tokenization, inverted index, BM25.
Concepts
Build evidence
- Implement BM25 search in HighSignal — Index a corpus of articles and serve ranked keyword search using BM25.
Milestone 3
Week 2 — Evaluation
Make retrieval quality measurable.
Concepts
Build evidence
- Search eval harness — A reusable harness that scores any retriever against a labelled query set.
Milestone 4
Week 3 — Vector retrieval
Embeddings, similarity, exact nearest-neighbour search.
Concepts
Build evidence
- Brute-force vector index — An exact nearest-neighbour index — the recall=1.0 baseline.
Milestone 5
Week 4 — Hybrid search
Fuse lexical and vector retrieval and prove it wins.
Concepts
Build evidence
- Hybrid search v0 in HighSignal — Combine BM25 and vector retrieval with reciprocal rank fusion.