Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

Checkpoint: File edits

rUv1e85414fcefd
diff --git a/v3/@claude-flow/embeddings/src/types.ts b/v3/@claude-flow/embeddings/src/types.ts
index eece889a8a..f4d39b4faf 100644
--- a/v3/@claude-flow/embeddings/src/types.ts
+++ b/v3/@claude-flow/embeddings/src/types.ts
@@ -92,13 +92,41 @@ export interface MockEmbeddingConfig extends EmbeddingBaseConfig {
simulatedLatency?: number;
}
+/**
+ * Agentic-flow provider configuration
+ * Uses optimized ONNX embeddings with:
+ * - Float32Array with flattened matrices
+ * - 256-entry LRU cache with FNV-1a hash
+ * - SIMD-friendly loop unrolling (4x)
+ * - Pre-allocated buffers (no GC pressure)
+ */
+export interface AgenticFlowEmbeddingConfig extends EmbeddingBaseConfig {
+ provider: 'agentic-flow';
+
+ /** Model ID (default: all-MiniLM-L6-v2) */
+ modelId?: string;
+
+ /** Embedding dimensions (default: 384) */
+ dimensions?: number;
+
+ /** Internal cache size for embedder (default: 256) */
+ embedderCacheSize?: number;
+
+ /** Model directory path */
+ modelDir?: string;
+
+ /** Auto-download model if not present */
+ autoDownload?: boolean;
+}
+
/**
* Union of all provider configs
*/
export type EmbeddingConfig =
| OpenAIEmbeddingConfig
| TransformersEmbeddingConfig
- | MockEmbeddingConfig;
+ | MockEmbeddingConfig
+ | AgenticFlowEmbeddingConfig;
// ============================================================================
// Result Types