init

services/ragflow_client.py

@@ -0,0 +1,59 @@
+import json
+from typing import Any, Dict, Optional
+
+import httpx
+
+from config import Config
+
+
+class RagflowClient:
+    """RAGFlow 客户端（仅检索）"""
+
+    def __init__(self):
+        cfg = Config.get_section("ragflow")
+        self._base_url = cfg.get("url", "")
+        self._api_key = cfg.get("api_key", "")
+        self._retrieval_path = cfg.get("retrieval", "/api/v1/retrieval")
+        self._dataset_ids = cfg.get("dataset_ids", "")
+
+    def _build_url(self) -> str:
+        return self._base_url.rstrip("/") + "/" + self._retrieval_path.lstrip("/")
+
+    def retrieve(self, query: str, top_k: int = 3) -> Dict[str, Any]:
+        """检索匹配文档"""
+        if not self._base_url or not self._retrieval_path:
+            raise RuntimeError("未配置 ragflow.url 或 ragflow.retrieval")
+        url = self._build_url()
+        headers = {"Authorization": f"Bearer {self._api_key}"} if self._api_key else {}
+        payload = {
+            "dataset_ids": self._dataset_ids,
+            "query": query,
+            "top_k": top_k,
+        }
+
+        with httpx.Client(timeout=30) as client:
+            response = client.post(url, json=payload, headers=headers)
+        response.raise_for_status()
+        return response.json()
+
+
+def extract_table_name(record: Dict[str, Any]) -> Optional[str]:
+    """从检索结果中提取表名"""
+    if not record:
+        return None
+
+    metadata = record.get("metadata") or {}
+    for key in ("table", "table_name"):
+        if key in metadata:
+            return metadata.get(key)
+
+    for key in ("table", "table_name"):
+        if key in record:
+            return record.get(key)
+
+    content = record.get("content") or record.get("text") or ""
+    for line in str(content).splitlines():
+        if line.lower().startswith("table:"):
+            return line.split(":", 1)[1].strip()
+
+    return None