chore: import upstream snapshot with attribution

2026-07-13 12:49:10 +08:00
commit 3165c4acf8
382 changed files with 154008 additions and 0 deletions
@@ -0,0 +1,39 @@
+/*
+ * Copyright 2024 CloudWeGo Authors
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ *     http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package embedding
+
+import "context"
+
+// Embedder converts a batch of strings into dense vector representations.
+//
+// EmbedStrings returns one vector per input text, in the same order. The
+// vector length (dimensions) is fixed by the underlying model and identical
+// for every text in the batch.
+//
+// The returned [][]float64 maps as:
+//
+//	embeddings[i]  →  vector for texts[i]
+//	len(embeddings[i])  →  model's embedding dimension (e.g. 1536 for ada-002)
+//
+// Both [Indexer] and [Retriever] use an Embedder to convert documents and
+// queries into vectors. They must share the exact same model — mismatched
+// dimensions or model families break semantic similarity.
+//
+//go:generate  mockgen -destination ../../internal/mock/components/embedding/Embedding_mock.go --package embedding -source interface.go
+type Embedder interface {
+	EmbedStrings(ctx context.Context, texts []string, opts ...Option) ([][]float64, error) // invoke
+}