Скелет проекта

src/rag_agent/index/embeddings.py

@@ -0,0 +1,29 @@
+from __future__ import annotations
+
+import hashlib
+from dataclasses import dataclass
+from typing import Iterable, Protocol
+
+
+class EmbeddingClient(Protocol):
+    def embed_texts(self, texts: Iterable[str]) -> list[list[float]]:
+        raise NotImplementedError
+
+
+@dataclass
+class StubEmbeddingClient:
+    dim: int
+
+    def embed_texts(self, texts: Iterable[str]) -> list[list[float]]:
+        vectors: list[list[float]] = []
+        for text in texts:
+            digest = hashlib.sha256(text.encode("utf-8")).digest()
+            values = [b / 255.0 for b in digest]
+            if len(values) < self.dim:
+                values = (values * ((self.dim // len(values)) + 1))[: self.dim]
+            vectors.append(values[: self.dim])
+        return vectors
+
+
+def get_embedding_client(dim: int) -> EmbeddingClient:
+    return StubEmbeddingClient(dim=dim)