強化 Ollama host health runtime 探針

services/ollama_health_probe.py

@@ -0,0 +1,46 @@
+"""Lightweight Ollama runtime health probes shared by scheduler and UI."""
+
+import os
+
+
+def _env_flag(name: str, default: bool = False) -> bool:
+    raw = os.getenv(name)
+    if raw is None:
+        return default
+    return str(raw).strip().lower() in {"1", "true", "yes", "on"}
+
+
+def host_health_model_probe_enabled(label: str) -> bool:
+    """Return whether host health should verify a tiny real model operation."""
+    if not _env_flag("OLLAMA_HOST_HEALTH_MODEL_PROBE_ENABLED", True):
+        return False
+    if "Fallback" in label:
+        return _env_flag("OLLAMA_HOST_HEALTH_MODEL_PROBE_INCLUDE_111", False)
+    return True
+
+
+def probe_ollama_embedding_runtime(requests_module, host: str) -> tuple[bool, str | None]:
+    """Verify Ollama can serve a tiny embedding, not just answer /api/tags."""
+    model = os.getenv("OLLAMA_HOST_HEALTH_EMBED_MODEL", "bge-m3:latest")
+    timeout = float(os.getenv("OLLAMA_HOST_HEALTH_EMBED_TIMEOUT", "8"))
+    keep_alive = os.getenv("OLLAMA_HOST_HEALTH_EMBED_KEEP_ALIVE", "1m")
+    try:
+        resp = requests_module.post(
+            f"{host.rstrip('/')}/api/embed",
+            json={"model": model, "input": "health", "keep_alive": keep_alive},
+            timeout=timeout,
+        )
+        if resp.status_code != 200:
+            return False, f"EmbedProbe HTTP {resp.status_code}"
+        payload = resp.json()
+        embeddings = payload.get("embeddings")
+        if isinstance(embeddings, list) and embeddings:
+            first = embeddings[0]
+            if isinstance(first, list) and first:
+                return True, None
+        embedding = payload.get("embedding")
+        if isinstance(embedding, list) and embedding:
+            return True, None
+        return False, "EmbedProbe empty embedding"
+    except Exception as exc:
+        return False, f"EmbedProbe {type(exc).__name__}: {str(exc)[:160]}"