Spaces:
Running
Running
Commit History
Yesterday
-
Search defaults, LLM search count and grading, links panel clicks and card under the graph; asset version label9
Verified signatureSearch Model starts on BGE large v1.5 tuned; Number of Results 100 for embedding, LLM search 50 phenotypes / 1000 codes, and POST /api/label-search takes k; LLM search rows can be graded (annotations keep judge and label). Links panel: curved links, aligned labels, cumulative line weight, faint waiting branches, card under the graph, one click one result.243e328
3 days ago
-
LLM search as a choice in the Search Model list; asset version label5
Verified signatureb596b2f -
Links wheel from the Netlify site (rings5); asset version label3
Verified signature415e5a1 -
Label search; built-in model from ENCODE_LLM_* settings; links wheel update
Verified signatureGroup by relevance: phenotype and code results in relevant, related and not relevant groups by the built-in model (GPT 6 Luna). The model endpoint, id and name now come from Space variables; the key stays the OPENAI_API_KEY secret. Links wheel update from GitHub ff8d3d1.86f07a9
8 days ago
-
Links panel sets no inline styles so it runs under a strict CSP; asset version rings3
Verified signature998d874 -
Links panel replaces the code graphs: one ring graph per code, linked concept and phenotype, Source or Derived on every link (MED-RT statements on drug links), concept cards labelled AI generated; also carries the 2026-10-20 dead-code trim and PARSE source name
Verified signature68fc933
-
Narrow-window layout: sidebar stacks above the content, detail page and drawers span the full width, graph aside stacks under the graph
Below 720px the fixed 270px sidebar left no room for the content, the detail page kept a 270px offset, and the graph drawer overflowed the window. Verified in headless Chromium at 500 and 640 wide with the detail page and graph drawer open. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>bd85d88
-
Sticky top bar so detail pages open under it at any scroll offset; title never wraps the 56px bar; Search button no longer clipped on narrow windows; stable scrollbar gutter
Testers reported the About/Collection bar vanishing on individual pages. The detail page is a fixed overlay at top:56px while the bar was in normal flow, so any search long enough to scroll before clicking a row left the bar off screen. Verified in headless Chromium at scroll 0/20/56/300 and widths 500-1400. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>cf2fd3d
-
Serve one planner model (GPT 5.6 Luna on OpenAI); remove the Agent model picker and bring-your-own-model dialog
Verified signature81c7b7b
-
Upload folder using huggingface_hub
Verified signature13f7fd6
-
Upload folder using huggingface_hub
Verified signature21711e7
-
Upload folder using huggingface_hub
Verified signature65dff80
-
Upload folder using huggingface_hub
Verified signature0734562
-
Upload folder using huggingface_hub
Verified signature2351481 -
Upload folder using huggingface_hub
Verified signature16ff626
-
Upload folder using huggingface_hub (part 2)
Verified signature950fe73
-
Use one vertical scrollbar in drawers
Verified signature16d1451 -
Show full graph node details
Verified signatured82df63 -
Remove About control from header
Verified signature6d9c94f -
Deploy reviewed LOINC graph and updated UI/backend (part 2)
Verified signature78248ef
-
Remove model description text from the picker
Verified signatureDrop the blurb/tags fields from the registry and the copy they fed: the sidebar note under the dropdown and the About panel's embedding-model section. The picker shows model names only.a08364d -
Model picker lists only selectable models
Verified signatureDrop the greyed-out '— not deployed' entry from the dropdown; a model you cannot choose is noise there. Undeployed models are still disclosed, in the About panel.01f8ac8 -
Add embedding-model picker backed by a server-side model registry
Verified signatureNew /api/models registry publishes which models exist, what each can search, and whether this deployment serves them. Search endpoints accept &model=<id> and stamp responses with model_id/model_label; annotations record the model. Scopes the ENCODE_PARTA_MODEL query-encoder override to the default vector set so an alternate model cannot silently encode queries with mismatched weights.bc7e936 -
Deploy ENCODE with private artifact bucket
Verified signature9a3640a