v2: Initial clean branch with unit tests + CI/CD pipeline

- Started from ac75faa (initial E4B-MarkBase integration) - Kept Sources/ (all engine code) + Package.swift + .gitignore - Removed all ad-hoc tests, documentation, scripts, Python files - Added Tests/00_Unit/ (MathTest, TokenizerTest, SamplerTest) - Added .gitea/workflows/ci.yaml (build + unit tests + lint) - Added Scripts/check_resources.sh (memory-aware test runner) - Added Tests/Manifest.json (resource requirements for all tests) - Focus: 4-bit quantized models only
2026-07-05 13:29:25 +08:00
commit 8a66b9086a
90 changed files with 22252 additions and 0 deletions
@@ -0,0 +1,112 @@
+import Foundation
+
+// ─────────────────────────────────────────────────────────────
+// Embeddings API Models
+// OpenAI Compatible Format
+// ─────────────────────────────────────────────────────────────
+
+/// Embeddings request
+public struct EmbeddingsRequest: Codable {
+    public let model: String
+    public let input: InputType
+    public let encoding_format: String?
+    
+    public enum InputType: Codable, Sendable {
+        case string(String)
+        case strings([String])
+        case tokens([Int])
+        case tokensList([[Int]])
+        
+        public init(from decoder: Decoder) throws {
+            let container = try decoder.singleValueContainer()
+            
+            if let string = try? container.decode(String.self) {
+                self = .string(string)
+            } else if let strings = try? container.decode([String].self) {
+                self = .strings(strings)
+            } else if let tokens = try? container.decode([Int].self) {
+                self = .tokens(tokens)
+            } else if let tokensList = try? container.decode([[Int]].self) {
+                self = .tokensList(tokensList)
+            } else {
+                throw DecodingError.dataCorruptedError(
+                    in: container,
+                    debugDescription: "Invalid input type"
+                )
+            }
+        }
+        
+        public func encode(to encoder: Encoder) throws {
+            var container = encoder.singleValueContainer()
+            
+            switch self {
+            case .string(let string):
+                try container.encode(string)
+            case .strings(let strings):
+                try container.encode(strings)
+            case .tokens(let tokens):
+                try container.encode(tokens)
+            case .tokensList(let tokensList):
+                try container.encode(tokensList)
+            }
+        }
+    }
+    
+    public init(
+        model: String,
+        input: InputType,
+        encoding_format: String? = nil
+    ) {
+        self.model = model
+        self.input = input
+        self.encoding_format = encoding_format
+    }
+}
+
+/// Embeddings response
+public struct EmbeddingsResponse: Codable, Sendable {
+    public let object: String
+    public let data: [EmbeddingData]
+    public let model: String
+    public let usage: EmbeddingUsage
+    
+    public init(
+        object: String = "list",
+        data: [EmbeddingData],
+        model: String,
+        usage: EmbeddingUsage
+    ) {
+        self.object = object
+        self.data = data
+        self.model = model
+        self.usage = usage
+    }
+}
+
+/// Single embedding data
+public struct EmbeddingData: Codable, Sendable {
+    public let object: String
+    public let index: Int
+    public let embedding: [Float]
+    
+    public init(
+        object: String = "embedding",
+        index: Int,
+        embedding: [Float]
+    ) {
+        self.object = object
+        self.index = index
+        self.embedding = embedding
+    }
+}
+
+/// Embedding usage
+public struct EmbeddingUsage: Codable, Sendable {
+    public let prompt_tokens: Int
+    public let total_tokens: Int
+    
+    public init(prompt_tokens: Int, total_tokens: Int) {
+        self.prompt_tokens = prompt_tokens
+        self.total_tokens = total_tokens
+    }
+}