Menü
Vector export/import, embedding caching, provider migration
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Auto-registration via KoanAutoRegistrar, minimal Program.cs, "Reference = Intent" pattern
Chat endpoints, embeddings, RAG workflows, vector search
Aggregate boundaries, relationships, lifecycle hooks, value objects
Entity<T> patterns, GUID v7 auto-generation, static methods vs manual repositories
Transparent L1/L2 caching for Entity<T>, [Cacheable] attribute, cross-node coherence, per-request opt-out
Run a mandatory pre-implementation exploration workflow before writing production code in Koan (.NET/C#). Use when a task requires code changes and Codex must first map concerns/layers, read relevant files and docs, check existing constants and types, identify the closest existing pattern, plan exact code placement, and confirm architectural guardrails.
| name | koan-vector-migration |
| description | Vector export/import, embedding caching, provider migration |
Export vectors without regenerating via AI. Cache embeddings to enable zero-cost vector database migration.
var vectorRepo = serviceProvider.GetRequiredService<IVectorSearchRepository<Media, string>>();
await foreach (var batch in vectorRepo.ExportAllAsync(batchSize: 100, ct))
{
// batch.Id: Entity identifier
// batch.Embedding: float[] vector
// batch.Metadata: Optional metadata
// Cache the embedding
var contentHash = EmbeddingCache.ComputeContentHash(embeddingText);
await cache.SetAsync(contentHash, modelId, batch.Embedding, ct);
}
1. Export vectors from Provider A → Cache
2. Switch configuration to Provider B
3. Import vectors from Cache → Provider B
Result: Zero AI API calls for migration
// Step 1: Export from Weaviate
using (EntityContext.Adapter("weaviate"))
{
var vectorRepo = sp.GetRequiredService<IVectorSearchRepository<Media, string>>();
await foreach (var batch in vectorRepo.ExportAllAsync(batchSize: 100, ct))
{
await cache.SetAsync(batch.Id, "ada-002", batch.Embedding, ct);
}
}
// Step 2: Switch to ElasticSearch in appsettings.json
{
"Koan": {
"Data": {
"Sources": {
"Vectors": {
"Adapter": "elasticsearch",
"ConnectionString": "http://localhost:9200"
}
}
}
}
}
// Step 3: Import to ElasticSearch
foreach (var mediaId in allMediaIds)
{
var embedding = await cache.GetAsync(mediaId, "ada-002", ct);
if (embedding != null)
{
var media = new Media { Id = mediaId, Embedding = embedding };
await media.Save();
}
}
docs/guides/ai-vector-howto.md