union-app-chat-stream 1.0.3

package/app/authenticated_user.py

@@ -0,0 +1,77 @@
+from flask import Flask, request, jsonify, g, has_request_context
+from werkzeug.exceptions import HTTPException
+from loguru import logger
+from app.utils import common_utils
+from app.config.logger_config import setup_logger
+from contextvars import ContextVar
+
+_current_ip: ContextVar[str] = ContextVar("current_ip", default="unknown_ip")
+
+logger = setup_logger()
+
+
+class FlaskSessionClient:
+    def __init__(self, app):
+        self.auth_user_server = app.config['GET_USE_INFO_URL']
+        self.permissions = app.config['PERMISSIONS']
+        self.init_app(app)
+
+    def init_app(self, app: Flask):
+        def patcher(record):
+            record["extra"]["ip"] = _current_ip.get()
+
+        logger.configure(patcher=patcher)
+
+        @app.before_request
+        def require_auth():
+            try:
+                if has_request_context():
+                    ip = common_utils.get_client_ip()
+            except LookupError:
+                ip = "unknown_context-lost"
+            _current_ip.set(ip)
+
+            if request.method == 'OPTIONS':
+                return
+
+            public_paths = [
+                '/healthcheck.html',
+                '/favicon.ico'
+            ]
+            if any(request.path == path or request.path.startswith(path) for path in public_paths):
+                return
+
+            g.current_user = {'jsessionid': 'test-jsessionid'}
+            return
+
+            jsessionid = request.headers.get('Cookie')
+
+            if not jsessionid:
+                logger.error("未登录")
+                return jsonify({"error": "auth error"}), 401
+
+            try:
+                response = common_utils.call_https_api(url=self.auth_user_server,
+                                                       headers={'Cookie': 'CASSESSIONID=' + jsessionid},
+                                                       method='GET', verify_ssl=False)
+                if response.get('status_code') != 200 or not response.get('data'):
+                    logger.error("验证失败")
+                    return jsonify({"error": "auth error"}), 401
+                user = response.get('data')
+                if user['loginName'] and self.permissions and self.permissions not in user['permissions']:
+                    return jsonify({"error": "auth error"}), 401
+                g.current_user = response.get('data')
+                g.current_user['jsessionid'] = jsessionid
+
+                return
+            except Exception as e:
+                logger.error(f"auth 验证失败: {str(e)}，路径: {request.path}")
+                return jsonify({"error": "auth error"}), 401
+
+        @app.errorhandler(Exception)
+        def handle_exception(e):
+            if isinstance(e, HTTPException):
+                return e
+
+            logger.error(f"未处理的异常: {str(e)}")
+            return jsonify({"error": "Internal Server Error"}), 500

package/app/config/env_config.py

@@ -0,0 +1,96 @@
+import os
+
+
+def _env_bool(name, default=False):
+    value = os.getenv(name)
+    if value is None:
+        return default
+    return value.lower() in {"1", "true", "yes", "on"}
+
+
+def _env_int(name, default):
+    value = os.getenv(name)
+    if value is None:
+        return default
+    try:
+        return int(value)
+    except ValueError:
+        return default
+
+
+def _env_float(name, default):
+    value = os.getenv(name)
+    if value is None:
+        return default
+    try:
+        return float(value)
+    except ValueError:
+        return default
+
+
+def _env_list(name, default=None):
+    value = os.getenv(name)
+    if value is None:
+        return default or []
+    return [item.strip() for item in value.split(",") if item.strip()]
+
+
+class Config:
+    SECRET_KEY = os.getenv('SECRET_KEY')
+    GET_USE_INFO_URL = os.getenv('GET_USE_INFO_URL')
+    GET_ORG_INFO_URL = os.getenv('GET_ORG_INFO_URL')
+    GET_JIRA_INFO_URL = os.getenv('GET_JIRA_INFO_URL')
+    GET_BIGDATA_URL = os.getenv('GET_BIGDATA_URL')
+    GET_UNION_BASE_URL = os.getenv('GET_UNION_BASE_URL')
+    GET_ORG_INFO_URL_TOKEN = os.getenv('GET_ORG_INFO_URL_TOKEN')
+    GET_JIRA_INFO_URL_TOKEN = os.getenv('GET_JIRA_INFO_URL_TOKEN')
+    PERMISSIONS = os.getenv('PERMISSIONS')
+    LOG_LEVEL = os.getenv("LOG_LEVEL", "INFO")
+    CONSOLE_STDOUT = os.getenv("CONSOLE_STDOUT", "FALSE")
+    LOG_DIR = os.getenv("LOG_DIR", "/data/appLogs")
+    FLASK_ENV = os.getenv("FLASK_ENV", "prod")
+    JWT_SECRET_KEY = os.getenv("JWT_SECRET_KEY", f"union-fall-back-secret-for-{FLASK_ENV}")
+    JWT_EXPIRATION_SECOND = os.getenv("JWT_EXPIRATION_SECOND", 900)
+    JWT_RENEW_SECOND = os.getenv("JWT_RENEW_SECOND", 120)
+
+    # 大模型地址
+    LLM_URL = os.getenv('LLM_URL')
+    LLM_KEY = os.getenv('LLM_KEY')
+    LLM_MODEL = os.getenv('LLM_MODEL')  # 默认模型名称
+    LLM_MAX_TOKENS = _env_int("LLM_MAX_TOKENS", 4096)
+    LLM_TEMPERATURE = _env_float("LLM_TEMPERATURE", 0.7)
+    LLM_TOP_P = _env_float("LLM_TOP_P", 0.9)
+
+    SYSTEM_PROMPT = os.getenv("SYSTEM_PROMPT", "")
+
+    FILTER_ENABLED = _env_bool("FILTER_ENABLED", False)
+    FILTER_ALLOWED_KEYWORDS = _env_list("FILTER_ALLOWED_KEYWORDS")
+    FILTER_REJECTION_MESSAGE = os.getenv(
+        "FILTER_REJECTION_MESSAGE",
+        "抱歉，我是联合运维智能客服，只能回答与联合运维相关的问题。",
+    )
+
+    TOOLS_MAX_ROUNDS = _env_int("TOOLS_MAX_ROUNDS", 5)
+
+    CONVERSATION_MAX_HISTORY = _env_int("CONVERSATION_MAX_HISTORY", 20)
+    CONVERSATION_TTL = _env_int("CONVERSATION_TTL", 3600)
+
+    RAG_ENABLED = _env_bool("RAG_ENABLED", True)
+    RAG_KNOWLEDGE_DIR = os.getenv("RAG_KNOWLEDGE_DIR", "knowledge")
+    RAG_PERSIST_DIR = os.getenv("RAG_PERSIST_DIR", ".chroma")
+    RAG_COLLECTION = os.getenv("RAG_COLLECTION", "ops_knowledge")
+    RAG_EMBEDDING_MODEL = os.getenv("RAG_EMBEDDING_MODEL", "embedding-3")
+    RAG_EMBEDDING_MAX_CHARS = _env_int("RAG_EMBEDDING_MAX_CHARS", 6000)
+    RAG_EMBEDDING_BATCH_SIZE = _env_int("RAG_EMBEDDING_BATCH_SIZE", 8)
+    RAG_TOP_K = _env_int("RAG_TOP_K", 5)
+    RAG_SEMANTIC_CANDIDATE_K = _env_int("RAG_SEMANTIC_CANDIDATE_K", 40)
+    RAG_CONTEXT_K = _env_int("RAG_CONTEXT_K", 8)
+    RAG_EXACT_CONTEXT_K = _env_int("RAG_EXACT_CONTEXT_K", 6)
+    RAG_EXACT_PER_FILE_CONTEXT_K = _env_int("RAG_EXACT_PER_FILE_CONTEXT_K", 1)
+    RAG_PER_FILE_CONTEXT_K = _env_int("RAG_PER_FILE_CONTEXT_K", 2)
+    RAG_CHUNK_SIZE = _env_int("RAG_CHUNK_SIZE", 1200)
+    RAG_REBUILD_ON_STARTUP = _env_bool("RAG_REBUILD_ON_STARTUP", False)
+
+    @classmethod
+    def init_app(cls, app):
+        pass

package/app/config/logger_config.py

@@ -0,0 +1,46 @@
+from loguru import logger
+import os
+
+
+def setup_logger():
+
+
+    env = os.getenv("FLASK_ENV", "prod")
+    log_level = os.getenv("LOG_LEVEL", "INFO")
+    console_stdout = os.getenv("CONSOLE_STDOUT", "FALSE")
+    log_dir = os.getenv("LOG_DIR", "/data/appLogs")
+    os.makedirs(log_dir, exist_ok=True)
+    app_log_path = os.path.join(log_dir, "union-py-app.log")
+    error_log_path = os.path.join(log_dir, "union-py-error.log")
+    logger.remove()
+
+    logger.configure(extra={"ip": "unknown_ip"})
+    log_format = "{time:YYYY-MM-DD HH:mm:ss}|{level:8}|{extra[ip]}|{name}:{function}:{line}|{message}"
+
+    logger.add(
+        app_log_path,
+        rotation="500 MB",
+        retention="30 days",
+        compression="gz",
+        level=log_level,
+        format=log_format,
+        enqueue=True,
+        encoding="utf=8"
+    )
+    logger.add(
+        error_log_path,
+        rotation="500 MB",
+        retention="30 days",
+        compression="gz",
+        level="ERROR",
+        encoding="utf=8"
+    )
+    if console_stdout:
+        logger.add(
+            sink=lambda msg: print(msg, end=""),
+            level=log_level,
+            format=log_format,
+            enqueue=True
+        )
+
+    return logger

package/app/manager/__init__.py

@@ -0,0 +1,4 @@
+from .chatstream_manager import ChatstreamManager
+from .runtime_manager import RuntimeManager
+
+__all__ = ["ChatstreamManager", "RuntimeManager"]

package/app/manager/chatstream_manager.py

@@ -0,0 +1,90 @@
+import threading
+import time
+from typing import Dict, Generator, List, Optional
+from uuid import uuid4
+
+from app.models.schemas import ChatResponse
+from app.service.chat_service import ChatService
+from app.service.rag_service import RagService
+from app.utils.function_utils import tools
+
+
+class ChatstreamManager:
+    def __init__(self, config, chat_service: ChatService, rag_service: RagService):
+        self._chat_service = chat_service
+        self._rag_service = rag_service
+        self._conversations: Dict[str, Dict] = {}
+        self._max_history = config["CONVERSATION_MAX_HISTORY"]
+        self._ttl = config["CONVERSATION_TTL"]
+        self._lock = threading.Lock()
+
+    @staticmethod
+    def normalize_conversation_id(conversation_id: Optional[str]) -> str:
+        normalized = (conversation_id or "").strip()
+        return normalized or f"conv-{uuid4().hex}"
+
+    def check_rag(self) -> Dict:
+        return self._rag_service.check()
+
+    def force_rebuild_rag(self) -> Dict:
+        return self._rag_service.force_rebuild()
+
+    def _cleanup_expired(self):
+        now = time.time()
+        expired = [cid for cid, c in self._conversations.items() if now - c["last_active"] > self._ttl]
+        for cid in expired:
+            del self._conversations[cid]
+
+    def _ensure_conversation(self, conversation_id: str):
+        if conversation_id not in self._conversations:
+            self._conversations[conversation_id] = {
+                "messages": [],
+                "created_at": time.time(),
+                "last_active": time.time(),
+            }
+
+    def _get_history(self, conversation_id: str) -> List[Dict[str, str]]:
+        with self._lock:
+            self._cleanup_expired()
+            self._ensure_conversation(conversation_id)
+            return list(self._conversations[conversation_id]["messages"])
+
+    def _append_exchange(self, conversation_id: str, user_question: str, assistant_answer: str):
+        with self._lock:
+            self._ensure_conversation(conversation_id)
+            conversation = self._conversations[conversation_id]
+            conversation["messages"].extend([
+                {"role": "user", "content": user_question},
+                {"role": "assistant", "content": assistant_answer},
+            ])
+            conversation["last_active"] = time.time()
+            max_messages = self._max_history * 2
+            if len(conversation["messages"]) > max_messages:
+                conversation["messages"] = conversation["messages"][-max_messages:]
+
+    def chat_stream(
+        self,
+        conversation_id: Optional[str],
+        question: str,
+        jsessionid: str,
+    ) -> Generator[ChatResponse, None, None]:
+        normalized_conversation_id = self.normalize_conversation_id(conversation_id)
+        history = self._get_history(normalized_conversation_id)
+        answer_parts: List[str] = []
+        stopped = False
+
+        for chunk in self._chat_service.tool_call_stream(
+            normalized_conversation_id,
+            question,
+            tools,
+            history,
+            jsessionid,
+        ):
+            if chunk.content:
+                answer_parts.append(chunk.content)
+            if chunk.finish_reason == "stop":
+                stopped = True
+            yield chunk
+
+        if stopped:
+            self._append_exchange(normalized_conversation_id, question, "".join(answer_parts))

package/app/manager/prompts.py

@@ -0,0 +1,62 @@
+"""LLM提示词模板定义"""
+
+
+# 提取时间范围的提示词
+PROMPT_EXTRACT_TIME_RANGE_SYSTEM = """You are a helpful assistant tasked with extracting structured information based on specific criteria provided. Follow the guidelines below to ensure consistency and accuracy.
+### Task
+Always call the `extract_parameters` function with the correct parameters. Ensure that the information extraction is contextual and aligns with the provided criteria.
+### Memory
+Here is the chat history between the human and assistant, provided within <histories> tags:
+<histories>
+
+</histories>
+### Instructions:
+Some additional information is provided below. Always adhere to these instructions as closely as possible:
+<instruction>
+当前时间是{current_time}
+</instruction>
+Steps:
+1. Review the chat history provided within the <histories> tags.
+2. Extract the relevant information based on the criteria given, output multiple values if there is multiple relevant information that match the criteria in the given text.
+3. Generate a well-formatted output using the defined functions and arguments.
+4. Use the `extract_parameter` function to create structured outputs with appropriate parameters.
+5. Do not include any XML tags in your output.
+### Example
+To illustrate, if the task involves extracting a user's name and their request, your function call might look like this: Ensure your output follows a similar structure to examples.
+### Final Output
+Produce well-formatted function calls in json without XML tags, as shown in the example."""
+
+PROMPT_EXTRACT_TIME_RANGE_USER = """### Structure
+Here is the structure of the JSON object, you should always follow the structure.
+<structure>
+{"queryTimeBegin": {"description": "查询的开始时间，格式为yyyy-MM-dd，如果结果没有明确查询年份，则根据当前时间获取年份", "type": "string"}, "queryTimeEnd": {"description": "查询的结束时间，如果结果没有明确结束时间，则默认为当前时间，格式为yyyy-MM-dd", "type": "string"}, "queryContext": {"description": "用户原文", "type": "string"}}
+</structure>
+
+### Text to be converted to JSON
+Inside <text></text> XML tags, there is a text that you should convert to a JSON object.
+<text>
+{query_text}
+</text>"""
+
+# 质量下降月份分析的提示词
+PROMPT_QUALITY_DECLINE_MONTHS = """根据输入的机构的运行质量情况，{data_json}，回答问题{{answer}}。并提取出对比上一个月成功率下降的月份集合{{declineMonth}}，注意，比较的精度是小数点后6位，月份的格式为yyyy-MM：。
+例子：{{\\"answer\\":\\"xxxx年xx月份以来，全链路系统成功率整体趋于下降，具体数据如下：- xxxx年x月：99.9989- xxxx年x月：99.9986- xxxx年x月：99.9985(有几个显示几个)。其中，xxxx年x月系统成功率最高，达到99.9990，最低为xxxx年x月的99.9985。\\",\\"declineMonth\\":\\"yyyy-mm,yyyy-mm(用逗号分隔，没有空格)\\"}}"""
+
+# 机构维度故障详情的提示词
+PROMPT_FAULT_DETAILS_BY_ORG = """根据输入的机构的运行质量情况，{data_json}。按以下为主要内容回答，可以使用markdown格式丰富展示：注意：faultCause属性里为固定名词，不要改变；影响笔数为整数，没有小数点。
+
+<b>以成员机构为维度统计：</b>
+xxx年x月：
+成员机构层面主要因为xx银行\\xx信用社\\xx公司(取前三)的系统失败导致。具体情况(取所有)如下：
+1）xx银行,影响笔数xxx,主要原因：faultCause"""
+
+# 失败模式分析的提示词
+PROMPT_FAILURE_PATTERNS_BY_ORG = """根据输入的机构的运行质量情况，{data_json}。按以下为主要内容回答。可以使用markdown格式丰富展示。注意：1.查出来的机构都是成功率低于全链路系统成功率的。2.分析内容不要输出属性值
+
+按以下进行分析：
+
+xxx年x月
+1.找到交易量较大( scale值等于\"large\")，并且sysSuccessRate大于0.999955的银行单位。做出以下结论:
+1）成员单位xxx,xxx，xxx虽然造成系统失败交易量较大，但系统成功率已达到99.9955%，提升空间有限。
+2.排除提升有限的机构，统计下造成influence高的前3个机构，统计他们的totalCntFail之和。做出以下结论（不要把属性展示出来）:
+2）成员机构xxx,xxx,xxx等合计造成系统失败量xxx(totalCntFail之和)，同时其系统弄成功率相对较低，建议从xxx机构入手推动推动。"""