claude-botandClaude Sonnet 5 2f6f56c4f0 feat(llamacpp): embeddings adapter over llama-server's /v1/embeddings ...

Batches requests (default size 2, matching llama-server's limits for long
notes), sorts responses by index, and normalises vectors to unit length.
CheckAsync prefers GET /health, falling back to a one-word embed call when
the server doesn't expose it. Registers as a keyed IEmbeddingModel so
multiple models can be wired up under different names.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

2026-09-24 11:31:48 +02:00

..

Wiki.Application.Tests

chore: solution scaffold (net10.0, ports-and-adapters layout, MudBlazor host, xunit)

2026-09-24 11:19:40 +02:00

Wiki.Contracts

feat(llamacpp): embeddings adapter over llama-server's /v1/embeddings

2026-09-24 11:31:48 +02:00

Wiki.Core.Tests

core: domain model, ports, vault parsing; contract suites for note store, vector index, catalog, embeddings

2026-09-24 11:24:33 +02:00

Wiki.Host.Tests

chore: solution scaffold (net10.0, ports-and-adapters layout, MudBlazor host, xunit)

2026-09-24 11:19:40 +02:00