feat(rag): 新增 Embedder 抽象与离线 FakeEmbedder

src/genesis/rag/embeddings.py

@@ -0,0 +1,51 @@
+from __future__ import annotations
+
+from typing import List, Protocol
+
+
+class Embedder(Protocol):
+    def embed(self, texts: List[str]) -> List[List[float]]: ...
+
+
+_DIM = 64
+
+
+def _tokenize(text: str) -> List[str]:
+    toks = []
+    cur = ""
+    for ch in text.lower():
+        if ch.isalnum():
+            cur += ch
+        else:
+            if cur:
+                toks.append(cur)
+                cur = ""
+    if cur:
+        toks.append(cur)
+    out = []
+    for t in toks:
+        idx = 0
+        for i, c in enumerate(t):
+            if i > 0 and c.isupper():
+                out.append(t[idx:i])
+                idx = i
+        out.append(t[idx:])
+    return [x for x in out if x]
+
+
+class FakeEmbedder:
+    def embed(self, texts: List[str]) -> List[List[float]]:
+        vecs = []
+        for t in texts:
+            v = [0.0] * _DIM
+            for tok in _tokenize(t):
+                h = __import__("hashlib").md5(tok.encode("utf-8")).digest()
+                idx = h[0] % _DIM
+                v[idx] += 1.0
+            norm = __import__("math").sqrt(sum(x * x for x in v)) or 1.0
+            vecs.append([x / norm for x in v])
+        return vecs
+
+
+def get_embedder(engine) -> Embedder:
+    return FakeEmbedder()