5 Commits

Author SHA1 Message Date
KS Jannette
362a47f88a Upgraded embedding model to voyage-3.5, updated README.md 2026-08-01 05:35:06 -04:00
KS Jannette
c6b07ccb56 fix minor css issue on stickies 2026-08-01 04:50:40 -04:00
KS Jannette
8e79e78006 hotfix 2026-08-01 04:41:31 -04:00
19d4a82c90 Merge pull request 'Re-aligned heuristic, updated readme, added code comment' (#3) from BUG-cohesion-scoreUI-display into master
Reviewed-on: #3
2026-08-01 08:13:29 +00:00
KS Jannette
6f09b6ecdc Re-aligned heuristic, updated readme, added code comment 2026-08-01 04:06:39 -04:00
6 changed files with 193 additions and 174 deletions

View File

@@ -8,11 +8,15 @@ In kongruity, the artifacts become "sticky notes." A board full of them looks ch
With a click, they are semantically evaluated, grouped into thematic clusters with descriptive headers, rankable and exportable to project planning and execution tools.
## Voyage AI voyage-3.5
![Embedding model benchmarking.](Voyage.jpg)
## Clustering and evaluation: methodology
Two models run in parallel, and neither sees the other's work. Anthropic's `claude-sonnet-5` (`backend/services/clustering.service.js`) reads the raw text of every note and groups them into labeled thematic clusters.
At the same time, Voyage AI's voyage-3 model (`backend/services/embedding.service.js`) converts each note's text into a numeric representation of its semantic meaning aka vector.
At the same time, Voyage AI's voyage-3.5 model (`backend/services/embedding.service.js`) converts each note's text into a numeric representation of its semantic meaning aka vector.
Once the LLM returns, kongruity scores that grouping (`backend/services/validation.service.js`) using an established silhouette coefficient, with cosine distance rather than Euclidean as the proximity metric.
@@ -30,14 +34,18 @@ Average silhouette width is a widely-used measure of clustering quality. Higher
2. How well-separated each cluster is from its nearest neighboring cluster.
Although the coefficient is mathematically bounded by [−1, 1], cosine distance between high-dimensional text embeddings is compressed: unrelated notes sit close to orthogonal, so both the within-cluster and nearest-cluster distances land near 0.8. Because silhouette divides the gap between them by the larger of the two, the practical range on embedding data is roughly [−0.05, 0.10] rather than the full interval.
The bands below are therefore calibrated against that observed range. On the seed board, the five ideal thematic clusters score 0.09; swapping a few notes between clusters drops it to 0.06; a scrambled assignment falls below zero.
The score appears above the results with a plain-language band:
- **0.70 and above** — Strong
- **0.40 to 0.69** — Moderate
- **0.10 to 0.39** — Weak
- **Below 0.10** — Poor
- **0.07 and above** — Strong
- **0.04 to 0.06** — Moderate
- **0.01 to 0.03** — Weak
- **Below 0.01** — Poor
Silhouette values are archetypically bounded below 1.0 for real-world data, so the number is best read as a relative measure. See Hugo Sträng, Tai Dinh. An upper bound on the silhouette evaluation metric for clustering. Pattern Recognition, Volume 178, 2026, 113402, ISSN 0031-3203.
A score near 0.00 means the grouping is no better than chance. Bands are specific to `voyage-3` cosine distance and would need recalibration behind a different embedding model. See Hugo Sträng, Tai Dinh. An upper bound on the silhouette evaluation metric for clustering. Pattern Recognition, Volume 178, 2026, 113402, ISSN 0031-3203.
## Organizing clusters, exporting to workflow software

BIN
Voyage.jpg Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 114 KiB

View File

@@ -27,7 +27,7 @@ export const embedNotes = async (notes) => {
for await (const chunk of batches) {
const response = await client.embed({
input: chunk.map((n) => n.text),
model: "voyage-3",
model: "voyage-3.5",
});
response.data.forEach((item, i) => {

View File

@@ -6,132 +6,136 @@ import Sticky from './sticky';
import Button from './button';
import '../styles/stickies.css';
// In practice, silhouette on cosine distance between text embeddings occupies roughly
// [-0.05, 0.10], not strict theoretical [-1, 1]: near-orthogonal vectors put both the within- and
// nearest-cluster distances close to 0.8, and the coefficient divides their gap
// by the larger. These bands are calibrated to that range for voyage-3. see README, Reading the cohesion score
const scoreLabel = (score: number): string => {
if (score >= 0.7) return 'Strong';
if (score >= 0.4) return 'Moderate';
if (score >= 0.1) return 'Weak';
return 'Poor';
if (score >= 0.07) return 'Strong';
if (score >= 0.04) return 'Moderate';
if (score >= 0.01) return 'Weak';
return 'Poor';
};
const Stickies = () => {
const { data: stickies, isLoading, error } = useGetStickies();
const { mutate: cluster, data: clusterResponse, isPending } = useClusterStickies();
const { data: stickies, isLoading, error } = useGetStickies();
const { mutate: cluster, data: clusterResponse, isPending } = useClusterStickies();
const [rankedClusters, setRankedClusters] = useState<RankedCluster[]>([]);
const dragIndex = useRef<number | null>(null);
const [dragOverIndex, setDragOverIndex] = useState<number | null>(null);
const [rankedClusters, setRankedClusters] = useState<RankedCluster[]>([]);
const dragIndex = useRef<number | null>(null);
const [dragOverIndex, setDragOverIndex] = useState<number | null>(null);
useEffect(() => {
if (clusterResponse?.clusters) {
setRankedClusters(
clusterResponse.clusters.map((c, i) => ({ ...c, rank: i + 1 }))
);
}
}, [clusterResponse]);
useEffect(() => {
if (clusterResponse?.clusters) {
setRankedClusters(
clusterResponse.clusters.map((c, i) => ({ ...c, rank: i + 1 }))
);
}
}, [clusterResponse]);
if (isLoading) return <div>Loading...</div>;
if (error) return <div>Error: {error.message}</div>;
if (isLoading) return <div>Loading...</div>;
if (error) return <div>Error: {error.message}</div>;
const score = clusterResponse?.score;
const score = clusterResponse?.score;
const handleCluster = () => {
cluster();
};
const handleCluster = () => {
cluster();
};
const buildStickyMap = (): Map<string, StickyType> => {
const map = new Map<string, StickyType>();
stickies?.forEach((s) => map.set(s.id, s));
return map;
};
const buildStickyMap = (): Map<string, StickyType> => {
const map = new Map<string, StickyType>();
stickies?.forEach((s) => map.set(s.id, s));
return map;
};
const stickyMap = buildStickyMap();
const stickyMap = buildStickyMap();
const renderStickies = (items: StickyType[]) =>
items?.map((sticky) => <Sticky key={sticky.id} sticky={sticky} />);
const renderStickies = (items: StickyType[]) =>
items?.map((sticky) => <Sticky key={sticky.id} sticky={sticky} />);
const handleDragStart = (index: number) => {
dragIndex.current = index;
};
const handleDragStart = (index: number) => {
dragIndex.current = index;
};
const handleDragOver = (e: DragEvent, index: number) => {
e.preventDefault();
setDragOverIndex(index);
};
const handleDragOver = (e: DragEvent, index: number) => {
e.preventDefault();
setDragOverIndex(index);
};
const handleDragLeave = () => {
setDragOverIndex(null);
};
const handleDragLeave = () => {
setDragOverIndex(null);
};
const handleDrop = (targetIndex: number) => {
const sourceIndex = dragIndex.current;
if (sourceIndex === null || sourceIndex === targetIndex) {
dragIndex.current = null;
setDragOverIndex(null);
return;
}
const handleDrop = (targetIndex: number) => {
const sourceIndex = dragIndex.current;
if (sourceIndex === null || sourceIndex === targetIndex) {
dragIndex.current = null;
setDragOverIndex(null);
return;
}
const reordered = [...rankedClusters];
const [moved] = reordered.splice(sourceIndex, 1);
reordered.splice(targetIndex, 0, moved);
const reordered = [...rankedClusters];
const [moved] = reordered.splice(sourceIndex, 1);
reordered.splice(targetIndex, 0, moved);
setRankedClusters(reordered.map((c, i) => ({ ...c, rank: i + 1 })));
dragIndex.current = null;
setDragOverIndex(null);
};
setRankedClusters(reordered.map((c, i) => ({ ...c, rank: i + 1 })));
dragIndex.current = null;
setDragOverIndex(null);
};
const handleDragEnd = () => {
dragIndex.current = null;
setDragOverIndex(null);
};
return (
<div className="stickies-container">
<Button onClick={handleCluster} isLoading={isPending} label="Group Stickies By Topic" />
{rankedClusters.length > 0 ? (
<div className="clusters-container">
{score != null && (
<div className="cohesion-score">
Cluster cohesion: <strong>{score.toFixed(2)}</strong> — {scoreLabel(score)}
</div>
)}
{rankedClusters.map((group, index) => (
<div
key={group.label}
className={`cluster-group cluster-draggable${dragOverIndex === index ? ' cluster-drag-over' : ''}`}
draggable
onDragStart={() => handleDragStart(index)}
onDragOver={(e) => handleDragOver(e, index)}
onDragLeave={handleDragLeave}
onDrop={() => handleDrop(index)}
onDragEnd={handleDragEnd}
>
<div className="cluster-header">
<span className="cluster-rank" aria-label={`Priority ${group.rank}`}>
{group.rank}
</span>
{group.rank === 1 && (
<span className="cluster-reorder-hint">Drag and drop to reorganize cluster priority</span>
)}
<h3 className="cluster-label">{group.label}</h3>
<span className="cluster-drag-handle" aria-hidden="true">⠿</span>
</div>
<div className="stickies-grid">
{renderStickies(
group?.noteIds
.map((id) => stickyMap?.get(id))
.filter((s): s is StickyType => !!s)
)}
</div>
</div>
))}
const handleDragEnd = () => {
dragIndex.current = null;
setDragOverIndex(null);
};
console.log(score?.toFixed(2))
return (
<div className="stickies-container">
<Button onClick={handleCluster} isLoading={isPending} label="Group Stickies By Topic" />
{rankedClusters.length > 0 ? (
<div className="clusters-container">
{score != null && (
<div className="cohesion-score">
Cluster cohesion: <strong>{scoreLabel(score)}</strong>
</div>
)}
{rankedClusters.map((group, index) => (
<div
key={group.label}
className={`cluster-group cluster-draggable${dragOverIndex === index ? ' cluster-drag-over' : ''}`}
draggable
onDragStart={() => handleDragStart(index)}
onDragOver={(e) => handleDragOver(e, index)}
onDragLeave={handleDragLeave}
onDrop={() => handleDrop(index)}
onDragEnd={handleDragEnd}
>
<div className="cluster-header">
<span className="cluster-rank" aria-label={`Priority ${group.rank}`}>
{group.rank}
</span>
{group.rank === 1 && (
<span className="cluster-reorder-hint">Drag and drop to reorganize cluster priority</span>
)}
<h3 className="cluster-label">{group.label}</h3>
<span className="cluster-drag-handle" aria-hidden="true">⠿</span>
</div>
<div className="stickies-grid">
{renderStickies(
group?.noteIds
.map((id) => stickyMap?.get(id))
.filter((s): s is StickyType => !!s)
)}
</div>
</div>
))}
</div>
) : (
<div className="stickies-grid">
{renderStickies(stickies ?? [])}
</div>
)}
</div>
) : (
<div className="stickies-grid">
{renderStickies(stickies ?? [])}
</div>
)}
</div>
);
);
};
export default Stickies;

View File

@@ -1,100 +1,107 @@
.stickies-grid {
display: flex;
flex-wrap: wrap;
gap: 16px;
justify-content: center;
margin-top: 18px;
padding: 24px;
display: flex;
flex-wrap: wrap;
gap: 16px;
justify-content: center;
margin-top: 18px;
padding: 24px;
}
.stickies-container {
margin: 36px 0px 36px 0px;
margin: 36px 0px 36px 0px;
}
.clusters-container {
display: flex;
flex-direction: column;
gap: 32px;
padding: 24px 0;
display: flex;
flex-direction: column;
gap: 32px;
padding: 24px 0;
}
.cluster-group {
border: 1px solid #6dd6f4;
border-radius: 8px;
padding: 16px;
border: 1px solid #6dd6f4;
border-radius: 8px;
padding: 16px;
}
.cluster-draggable {
cursor: grab;
transition: box-shadow 0.2s ease, border-color 0.2s ease, transform 0.15s ease;
cursor: grab;
transition: box-shadow 0.2s ease, border-color 0.2s ease, transform 0.15s ease;
}
.cluster-draggable:active {
cursor: grabbing;
cursor: grabbing;
}
.cluster-drag-over {
border-color: #ffb7ce;
box-shadow: 0 0 12px rgba(255, 183, 206, 0.4);
transform: scale(1.01);
border-color: #ffb7ce;
box-shadow: 0 0 12px rgba(255, 183, 206, 0.4);
transform: scale(1.01);
}
.cluster-header {
display: flex;
align-items: center;
gap: 12px;
margin-bottom: 16px;
position: relative;
display: flex;
align-items: center;
gap: 12px;
margin-bottom: 16px;
min-height: 32px;
}
.cluster-rank {
display: flex;
align-items: center;
justify-content: center;
width: 32px;
height: 32px;
border-radius: 50%;
background: #6dd6f4;
color: #1a1a2e;
font-weight: 700;
font-size: 0.95em;
flex-shrink: 0;
display: flex;
align-items: center;
justify-content: center;
width: 32px;
height: 32px;
border-radius: 50%;
background: #6dd6f4;
color: #1a1a2e;
font-weight: 700;
font-size: 0.95em;
flex-shrink: 0;
}
.cluster-reorder-hint {
font-size: 0.8em;
color: #9ca3af;
font-style: italic;
white-space: nowrap;
flex-shrink: 0;
font-size: 0.8em;
color: #9ca3af;
font-style: italic;
white-space: nowrap;
flex-shrink: 0;
}
.cluster-label {
margin: 0;
font-size: 1.2em;
font-weight: 600;
flex: 1;
position: absolute;
left: 50%;
transform: translateX(-50%);
max-width: 50%;
margin: 0;
font-size: 1.2em;
font-weight: 600;
pointer-events: none;
}
.cluster-drag-handle {
font-size: 1.4em;
color: #6dd6f4;
opacity: 0.4;
user-select: none;
transition: opacity 0.2s ease;
flex-shrink: 0;
margin-left: auto;
font-size: 1.4em;
color: #6dd6f4;
opacity: 0.4;
user-select: none;
transition: opacity 0.2s ease;
flex-shrink: 0;
}
.cluster-draggable:hover .cluster-drag-handle {
opacity: 0.8;
opacity: 0.8;
}
.cohesion-score {
text-align: center;
font-size: 0.95em;
color: #e0e0e0;
padding: 8px 16px;
background: rgba(109, 214, 244, 0.1);
border-radius: 6px;
width: fit-content;
margin: 0 auto;
}
text-align: center;
font-size: 0.95em;
color: #e0e0e0;
padding: 8px 16px;
background: rgba(109, 214, 244, 0.1);
border-radius: 6px;
width: fit-content;
margin: 0 auto;
}

View File

@@ -14,7 +14,7 @@ const MOCK_CLUSTER_RESPONSE = {
{ label: 'Auth Issues', noteIds: ['note_001'] },
{ label: 'Export Issues', noteIds: ['note_002'] },
],
score: 0.74,
score: 0.09,
};
let fetchMock: ReturnType<typeof vi.fn>;