import json import os from typing import Dict, List, Optional import httpx from config import Config def _build_document_for_table(table: str, templates: List[str]) -> str: lines = [f"table: {table}"] for t in templates: lines.append(f"- {t}") return "\n".join(lines) def _build_sql_gen_document(table: str, prompt: Dict[str, any]) -> str: system_prompt = prompt.get("system_prompt", "") business_prompt = prompt.get("business_prompt", "") constraints = prompt.get("constraints", []) lines = [f"table: {table}"] if system_prompt: lines.append("[system] " + system_prompt) if business_prompt: lines.append("[business] " + business_prompt) if constraints: lines.append("[constraints]") for c in constraints: lines.append(f"- {c}") return "\n".join(lines) class RagflowSync: """RAGFlow 同步工具""" def __init__(self): cfg = Config.get_section("ragflow") self._base_url = cfg.get("url", "").rstrip("/") self._api_key = cfg.get("api_key", "") self._table_retrieval_dataset_id = (cfg.get("table_retrieval_dataset_id") or "").strip() self._sql_gen_dataset_id = (cfg.get("sql_gen_dataset_id") or "").strip() self._upload_path = (cfg.get("upload") or "").strip() self._upload_mode = (cfg.get("upload_mode") or "overwrite").strip().lower() def _validate_common(self) -> None: if not self._base_url: raise RuntimeError("未配置 ragflow.url") if not self._upload_path: raise RuntimeError("未配置 ragflow.upload 上传接口,请在 config/config.ini 中设置") if self._upload_mode not in ("overwrite", "append"): raise RuntimeError("ragflow.upload_mode 仅支持 overwrite 或 append") def _post(self, documents: List[Dict[str, any]]): self._validate_common() url = self._base_url + "/" + self._upload_path.lstrip("/") headers = {"Authorization": f"Bearer {self._api_key}"} if self._api_key else {} payload: Dict[str, any] = {"documents": documents} if self._upload_mode == "overwrite": payload["mode"] = "overwrite" with httpx.Client(timeout=60) as client: response = client.post(url, json=payload, headers=headers) response.raise_for_status() return response.json() def sync_table_retrieval(self) -> Dict[str, any]: if not self._table_retrieval_dataset_id: raise RuntimeError("未配置 ragflow.table_retrieval_dataset_id,无法同步表名检索模板") root = os.path.dirname(os.path.dirname(__file__)) tables_file = os.path.join(root, "config", "table_retrieval_prompts", "tables.json") with open(tables_file, "r", encoding="utf-8") as f: data = json.load(f) tables = data.get("tables", {}) documents = [] for table, templates in tables.items(): doc = { "dataset_ids": self._table_retrieval_dataset_id, "content": _build_document_for_table(table, templates), "metadata": {"table": table}, } documents.append(doc) return self._post(documents) def sync_sql_gen_prompts(self) -> Dict[str, any]: if not self._sql_gen_dataset_id: raise RuntimeError("未配置 ragflow.sql_gen_dataset_id,无法同步 SQL 生成提示词") root = os.path.dirname(os.path.dirname(__file__)) prompts_dir = os.path.join(root, "config", "sql_gen_prompts") documents = [] for name in os.listdir(prompts_dir): if not name.endswith(".json"): continue path = os.path.join(prompts_dir, name) with open(path, "r", encoding="utf-8") as f: prompt = json.load(f) table = prompt.get("table") or os.path.splitext(name)[0] doc = { "dataset_ids": self._sql_gen_dataset_id, "content": _build_sql_gen_document(table, prompt), "metadata": {"table": table}, } documents.append(doc) return self._post(documents)