Initial commit: QMDSearch 分层信息检索服务

- FastAPI + Qdrant + Redis + Ollama 技术栈
- L1→L2→L3→chunk 四层分层检索（dense + sparse RRF 融合）
- 文档三级总结与 2.5 级回退
- query 解析路由与分类
- /admin 管理页面

app/services/ollama.py

@@ -0,0 +1,62 @@
+"""Ollama 客户端
+
+通过 Ollama HTTP API 调用本地模型进行文本生成。
+"""
+
+import httpx
+import structlog
+
+from app.config import settings
+
+logger = structlog.get_logger()
+
+
+class OllamaClient:
+    """Ollama HTTP API 客户端"""
+
+    def __init__(
+        self,
+        base_url: str | None = None,
+        model: str | None = None,
+        timeout: float = 120.0,
+    ) -> None:
+        self.base_url = (base_url or settings.ollama_base_url).rstrip("/")
+        self.model = model or settings.ollama_model
+        self.timeout = timeout
+
+    async def generate(self, prompt: str, json_mode: bool = False) -> str:
+        """调用 Ollama 生成文本
+
+        Args:
+            prompt: 输入提示词
+            json_mode: 为 True 时启用 Ollama 原生 JSON 约束输出（payload 加 format: json）
+
+        Returns:
+            生成的文本内容
+        """
+        url = f"{self.base_url}/api/generate"
+        payload = {
+            "model": self.model,
+            "prompt": prompt,
+            "stream": False,
+        }
+        if json_mode:
+            payload["format"] = "json"
+
+        async with httpx.AsyncClient(timeout=self.timeout) as client:
+            resp = await client.post(url, json=payload)
+            resp.raise_for_status()
+            data = resp.json()
+
+        result = data.get("response", "")
+        logger.debug("Ollama 生成完成", model=self.model, output_length=len(result))
+        return result
+
+    async def is_available(self) -> bool:
+        """检查 Ollama 服务是否可用"""
+        try:
+            async with httpx.AsyncClient(timeout=5.0) as client:
+                resp = await client.get(f"{self.base_url}/api/tags")
+                return resp.status_code == 200
+        except httpx.HTTPError:
+            return False