Build RAG That
Stays Good
Experiment with strategies, version your corpus, and catch quality regressions before your users do. Start free with 15 documents in under a minute.
Upload docs · run strategies · compare results in minutes
Initial corpus
1,204 docs
Mar 1
Added Q1 content
1,891 docs
Mar 14
Pruned stale pages
1,743 docs
Mar 22
Latest sync
1,910 docs
Mar 30
currentSDK
client.datasets.upload( name="prod-docs", files=["./docs/**/*.md"] ) # → version created automatically
Connect your corpus.
Versions are automatic.
Every sync or upload creates a new version automatically. No setup, no opt-in. Your full corpus history goes back to the first upload, so you always have a baseline to compare against.
Catch corpus drift
before your users do
Every new version automatically triggers centroid shift, norm shift, and distribution checks. You get a clear pass or fail before anything reaches production. No instrumentation to write.
Centroid Shift
Semantic center is stable
0.08
threshold 0.10
Norm Shift
Vector magnitudes unchanged
0.06
threshold 0.15
Vector Validity
No NaN or zero vectors
100%
threshold 100%
Duplicate Rate
Near-zero redundancy
1.2%
threshold 5%
What a failure looks like
Centroid Shift exceeded threshold
Large semantic shift detected — review new batch
0.31
threshold 0.10
ada-002 · 256t chunks
Mar 1
Recall 0.71
rolled back
3-small · semantic chunks
Mar 14
Recall 0.84
superseded
3-large · hybrid search
Mar 22
Recall 0.91
superseded
3-large · late chunks · hybrid
Mar 30
Recall 0.94
live
Any version can be promoted back to live. Re-embedding not required.
Promote, rollback,
or branch. Your history is always there.
Every retrieval config that has ever shipped is stored. Compare recall across versions, promote the winner, or rollback to any prior state in seconds. No re-embedding required.
Your pipeline is one setup away
from being observable
Start with the free RAG Lab. No signup needed. Upload 15 documents, generate a gold set, and compare strategies in minutes.