3 Commits

Include renames

Author	SHA1	Message	Date
jpmschweitzerandClaude Fable 5	8348b4bf92	perf: batch page embeddings via /api/embed and upsert before pruning stale points ... - embed_batch now issues one batched /api/embed request (the old loop made one /api/embeddings round-trip per chunk) with a per-text fallback that preserves None-for-failed semantics - update_from_page embeds all chunks in that single call and stores them in one Qdrant batch upsert (upsert_points) - reindex order reversed: upsert new points first, then prune stale ids (deterministic uuid5 ids make overwrite safe) so a mid-way failure no longer leaves the page with zero vectors - VectorUpdateSummary gains status (success/partial/failed) and chunks_skipped; all-embeddings-failed keeps old vectors and reports failure instead of success=True Measured on a 7-chunk page ingest (local server, llm_tester): ~375ms -> ~181ms median over 3 runs. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01QbFZyDvYksazX6nYQYZ67L	2026-07-14 13:09:37 +02:00
jpmschweitzerandClaude Opus 4.5	dfd1f19bf9	feat: add temperature parameter to Ollama generate_text ... Add temperature control for LLM text generation: - temperature=0.0 for deterministic outputs (JSON, rankings) - temperature=0.3-0.5 for controlled creative content - None uses model default (~0.7 for mistral-nemo) Based on llm-findings.md recommendations for improving mistral-nemo output consistency. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>	2025-12-23 17:21:18 +01:00
jpmschweitzer	95852190ba	Initial commit: library-desk service extraction from portainer-core	2025-12-11 17:28:23 +01:00