Update artifacts/api-server/src/routes/model.ts

Update artifacts/api-server/src/routes/model.ts

Update artifacts/api-server/src/routes/model.ts

Update artifacts/api-server/src/routes/model.ts

Update artifacts/api-server/src/routes/model.ts

Update artifacts/api-server/src/routes/search.ts

feat: model answers from own knowledge first, web results expand after (parallel execution)

perf+fix: drop runPythonScore call (saves 5-12s), keep source-weight+relevance scoring, penalise news language for general answers

feat: Jaccard semantic deduplication — filters near-duplicate facts across Wikipedia/DuckDuckGo/Wikidata

fix: strong sentence quality filter (citation artifacts, fragments, meta-language) + combined perplexity+relevance ranking

fix: modelDriveAnswer uses distilgpt2 only for scoring, returns real web sentences — no hallucination

fix: QA prompt format (Context/Q/A) so distilgpt2 answers instead of hallucinating

fix: modelDriveAnswer no longer times out — nSamples 1, maxTokens 50/40, pool 20, coherence 0.05

feat: migrate HST Crystalline v8 search engine to io (200+ sources, distilgpt2 refinement)

fix: match Colab Cell 10 params + extend CPU timeouts to 8 min

cleanup: strip dead code (web-scraping, fine-tuning, scoring)

perf: greedy decoding (temp=0.1), 60 tokens — fit within CPU budget, no more timeouts

feat: AI-only mode — remove all web search, model answers every query directly

feat: replace logo with new io_logo.png

perf: greedy decoding + inference_mode for coherent fast answers on CIF path

fix: ThreadingHTTPServer so health checks never block during inference + all CPU threads for generation

fix: increase inference timeout 30s->180s, reduce nSamples 3->1 and maxTokens 400->100 for CPU feasibility

fix: complete model server HTTP handler, remove duplicate daemon, extend health timeout to 900s

Update artifacts/api-server/src/index.ts

Update artifacts/api-server/src/index.ts

fix: extend daemon health-probe timeout 90s→300s for 515MB model download+load

fix: remove circular isCheckpointReady() guard from startModelDaemon — daemon now self-starts

fix: aiScore ReferenceError — declare variables before if/else block

feat: AI/Search % badge, search-conditioned model, daemon self-fetches checkpoint via hf_hub_download

search-guided model: fetch first, condition model on results, maxTokens=400, usedModel flag

model-first: generate tokens directly, web search for grounding only

Revert "Io HST Search Engine — initial HuggingFace Space"

Fix: remove broken getCodeIntro ref, restore working code template flow

Io HST Search Engine — initial HuggingFace Space

Io HST Search Engine — initial HuggingFace Space

Io HST Search Engine — initial HuggingFace Space