A SMALL SEARCH TOOL. AN INSPECTABLE TRAIL.
Six fictional notes.
Exact passages.
No generated answer.
About 38 MB downloads. Your notes and question stay in this browser.
Your source pack is ready to explore.
0 / 800 charactersAsk a question above. Three exact passages will appear here, each with a path back to its source.
NO GENERATED ANSWER. JUST THE NOTES.cameracamera:1If a borrowed camera is damaged, take photographs of the damage and label the kit before asking the equipment coordinator to inspect it. Do not return it to the available shelf.
camera:2A working camera can be checked back in after its battery, lens cap and carry bag have been counted. Record any missing item in the return note.
A small, reproducible experiment. The model finds related language; the original notes remain the evidence.
On 13 answerable held-out questions, semantic search accepted 7 and abstained on 6. On 3 no-answer questions it returned 0 false positives and 3 abstentions. Text matching accepted all 13 answerable questions and all 3 no-answer questions.
| Method | Recall@3 | MRR |
|---|---|---|
| Semantic | 0.923 | 0.827 |
| Text matching | 0.538 | 0.515 |
Recall@3 is the mean fraction of labelled relevant passages found in the first three; MRR uses the first relevant passage in the full ranking. Both exclude no-answer questions and do not imply a question was accepted. These are Node CPU evaluation results, not browser performance measurements.
The 0.5773 threshold was selected on 8 separate calibration questions, never the held-out set. Six fictional sources and 12 passages are a tiny test, not evidence of general accuracy.
Download raw evaluation ↗ · Frozen test set ↗Notes, questions and vectors live in memory. They are not sent to a service, logged or saved in application storage. Reset clears the workspace; reloading clears your edits. Public model files download from this same site only when requested. Your browser may cache those public files.
Export deliberately creates a file containing your question and retrieved quotations. Keep it wherever you normally keep those notes.
MiniLM-L6-v2, q8 weights, 384 dimensions, mean pooling and normalized vectors. Transformers.js 4.3.0 runs ONNX WASM in a dedicated worker with one thread. Every question and passage is checked against the model’s 512-token limit; nothing is silently shortened.
Archived and current versions stay separate. Retrieval does not resolve contradictions or establish which statement is true. Editing sources invalidates results and unloads the model to clear pending work.
Pinned asset hashes ↗ · Architecture ↗