fix(avatar): batch knowledge embedding requests

digital-avatar-app/backend/embeddings.py

@@ -51,22 +51,32 @@ def embed(texts):
     if api_url:
         api_key = os.getenv("EMBEDDING_API_KEY", "")
         model = os.getenv("EMBEDDING_MODEL", "text-embedding-3-small")
-        payload = json.dumps({"input": texts, "model": model}).encode("utf-8")
-        req = urllib.request.Request(
-            api_url,
-            data=payload,
-            headers={
-                "Content-Type": "application/json",
-                "Authorization": f"Bearer {api_key}" if api_key else "",
-            },
-            method="POST",
-        )
-        with urllib.request.urlopen(req, timeout=30) as resp:
-            data = json.loads(resp.read().decode("utf-8"))
-        items = data["data"]
-        if items and "index" in items[0]:
-            items = sorted(items, key=lambda x: x["index"])
-        return [item["embedding"] for item in items]
+        try:
+            batch_size = max(1, int(os.getenv("EMBEDDING_BATCH_SIZE", "10")))
+        except ValueError:
+            batch_size = 10
+        embeddings = []
+        for start in range(0, len(texts), batch_size):
+            batch = texts[start:start + batch_size]
+            payload = json.dumps({"input": batch, "model": model}).encode("utf-8")
+            req = urllib.request.Request(
+                api_url,
+                data=payload,
+                headers={
+                    "Content-Type": "application/json",
+                    "Authorization": f"Bearer {api_key}" if api_key else "",
+                },
+                method="POST",
+            )
+            with urllib.request.urlopen(req, timeout=30) as resp:
+                data = json.loads(resp.read().decode("utf-8"))
+            items = data["data"]
+            if items and "index" in items[0]:
+                items = sorted(items, key=lambda x: x["index"])
+            if len(items) != len(batch):
+                raise ValueError("embedding response count does not match request")
+            embeddings.extend(item["embedding"] for item in items)
+        return embeddings
     return _hash_embedding(texts)