vector-db-from-scratch
Learn vector search with Rust and DataFusion; the C++/BusTub track is deprecated.
Runssource: GitHubhomepageRustApache-2.0commit 7c2040aa4f1d
Rust, Apache-2.0 licensed. The project labels itself: apache arrow, approximate nearest neighbor, course, database systems, datafusion, hnsw, ivfflat and product quantization.
vector-db-from-scratch runs. An Argusic agent installed it in 2 minutes and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The solution crates compile, all 61 tests pass, and the DataFusion CLI example executes real SQL queries. The starter crates contain the expected 'not yet implemented' stubs for the six-day course.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- No Rust toolchain installed in container (rustc, cargo not found)0.3 minutes
- Install time
- 2 minutes
- Cold machine to finish
- 24 minutes
- Errors hit and fixed
- 1 hit, 1 fixed with no human help
- How the result was proved
- cargo test -p vector-db-from-scratch-core -p vector-db-from-scratch-datafusion -p vector-db-from-scratch-benchmark-support -p xtask returned 0 failures (61 passed); cargo run -p vector-db-from-scratch-datafusion --example sql executed SELECT 1 and returned 1 row
- Model tokens used
- 36,888
- Exact commit tested
- 7c2040aa4f1d
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
2. **Built and checked** — `cargo check` compiled all workspace members (solution + starter + vendo… 3. **Ran full test suite** — identified that starter crates fail with "not yet implemented" panics … 4. **Verified end-to-end** — ran the `sql` example and piped a SQL query to it, confirming real Dat… 5. **Release build** — `cargo build --release` completed successfully. ## Results - **Solution crate tests**: all pass - `vector-db-from-scratch-core` indexes: **19 passed**, 5 ignored (need external SIFT1M data) - `vector-db-from-scratch-datafusion` SQL tests: **33 passed** - `vector-db-from-scratch-datafusion` sqllogictest: **5 passed** - `xtask`: **4 passed** - **Example**: `cargo run -p vector-db-from-scratch-datafusion --example sql` with `SELECT 1 as col… - **Starter crates**: panics with "not yet implemented" for each day's checkpoint — this is the int…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 2 minutes.
- Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 2 minutes after the clone.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
apache-arrowapproximate-nearest-neighborcoursedatabase-systemsdatafusionhnswivfflatproduct-quantizationrustsift1msqlsystems-programmingtutorialvector-databasevector-search
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/vector-db-from-scratch)Questions
- Does vector-db-from-scratch run?
- Yes. vector-db-from-scratch runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 1 error on the way, and recorded the session.
- How did Argusic test vector-db-from-scratch?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 7c2040aa4f1d. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test vector-db-from-scratch?
- The run that produced this verdict cost $0.06: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does vector-db-from-scratch take to install?
- 2 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does vector-db-from-scratch need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing vector-db-from-scratch?
- 1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for vector-db-from-scratch?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.