Embeddings, a vector database, and RAG v1 (Project 2).

1.Try #10 Two Sum II – Input Array Is Sorted – untimed, AI-free

Two Pointers · Medium. Aim for 15–20 minutes. No assistants, no autocomplete.

2.Stuck at 25 minutes? Use the NeetCode method

Read or watch the explanation, close it, then re-code the solution from memory.

3.Write the Big-O

Add a comment with the time and space complexity, and why.

4.Log it

Mark it Solved or Revisit, with minutes and whether you solved it unaided.

5.10 min revision

One item from reviews/relearn.md.

1.Try #11 3Sum – untimed, AI-free

Two Pointers · Medium. Aim for 15–20 minutes. No assistants, no autocomplete.

2.Stuck at 25 minutes? Use the NeetCode method

Read or watch the explanation, close it, then re-code the solution from memory.

3.Write the Big-O

Add a comment with the time and space complexity, and why.

4.Log it

Mark it Solved or Revisit, with minutes and whether you solved it unaided.

5.10 min revision

One item from reviews/relearn.md.

1.Try #12 Container With Most Water – untimed, AI-free

Two Pointers · Medium. Aim for 15–20 minutes. No assistants, no autocomplete.

2.Stuck at 25 minutes? Use the NeetCode method

Read or watch the explanation, close it, then re-code the solution from memory.

3.Write the Big-O

Add a comment with the time and space complexity, and why.

4.Log it

Mark it Solved or Revisit, with minutes and whether you solved it unaided.

5.10 min revision

One item from reviews/relearn.md.

1.Work through: Hugging Face LLM Course – Chapter 1

≈30 min

2.Work through: Sentence Transformers – Quickstart

≈20 min

3.Do

Fetch ~50 GOV.UK pages on one topic; embed paragraphs locally on mps; cosine search in NumPy for 10 questions.

4.Check you’re done

Done when: ≥7/10 questions return relevant top-3 results.

1.Work through: Chroma – Getting Started

≈20 min

2.Do

Persistent Chroma collection with metadata; query with a filter.

3.Check you’re done

Done when: Data survives a restart.

1.Catch up first

Finish anything unticked from Mon–Fri this week before stretch work.

2.Then stretch work

Compare chunk sizes (200 / 500 / 1,000 tokens) on your 10 questions.

1.Start with 20 min revision

Re-solve Group Anagrams from memory.

2.Work through: Anthropic Academy – RAG and Agentic Search section

≈1h

3.Work through: Streamlit Community Cloud

≈10 min

4.Do

Ingest (Content API → heading-aware chunks → Chroma); answer() returns numbered citations + ‘last updated’ dates and refuses when unsupported; Streamlit UI.

5.Check you’re done

Done when: 15 in-scope questions answered with citations; 3 out-of-scope refused.

6.Commit

projects/p2-ask-govuk-rag/

1.Do

Deploy P2 to Streamlit Community Cloud; record a GIF; weekly review.

2.Check you’re done

Done when: Public URL works.

3.Commit

P2 README

4.Weekly review (last 30 min)

3 wins, 3 confusions, 1 thing to re-learn – written at the bottom of this page and saved with your progress.