Pine
064b06ecf0
迁入 app/park：llm(对话)、rag(双路向量知识库)、tools/ai_tools(智能体工具)、 asr(语音识别)、s2s_bridge(实时语音桥)、vision_yolo/vision_llm(人脸/多模态)、 knowledge/*.md、vendor/s2s-cloud(s2s 云化栈)；routers 补 /api/ai|kb|asr|vision| s2s|tools 端点。智能体提示词/企业名录改读 park_config 主数据源。pyproject 加重依赖 (dashscope/numpy/openai/torch/transformers/ultralytics/websockets/soundfile/scipy/ nltk/jinja2)。TestClient 冒烟：ai/chat(无 Key 走本地规则)、kb、s2s、tools、display 均 200。
270 lines
11 KiB
Python
270 lines
11 KiB
Python
# -*- coding: utf-8 -*-
|
||
"""AI 对话引擎 —— 阿里云 DashScope（通义千问）+ 函数调用
|
||
工具调用执行后通过 MQTT 广播，所有大屏同步响应
|
||
DashScope 不可用时自动回退本地规则引擎（离线兜底）
|
||
"""
|
||
|
||
import json
|
||
import logging
|
||
import ssl
|
||
import urllib.error
|
||
import urllib.request
|
||
|
||
import certifi
|
||
|
||
from .config import settings
|
||
|
||
log = logging.getLogger("dpm.llm")
|
||
|
||
|
||
def _trunc(s, n=400):
|
||
"""日志用截断：超长内容只留前 n 字并标注总长。"""
|
||
s = str(s)
|
||
return s if len(s) <= n else s[:n] + f"...（共{len(s)}字）"
|
||
|
||
|
||
# macOS 系统 Python 无系统 CA，使用 certifi 提供的根证书
|
||
_SSL_CTX = ssl.create_default_context(cafile=certifi.where())
|
||
|
||
SYSTEM_PROMPT = (
|
||
"你是「昆明市大学生创业园 · OPC 智能园区」的 AI 智能助手，运行在大屏展播系统上。"
|
||
"园区提供空间、孵化、融资、政策、资源、AI 赋能、综合服务七位一体服务。"
|
||
"回答园区相关问题时，必须严格依据【园区知识库】中的标准资料口径回答，"
|
||
"不得使用资料外的数字；涉及运营数据时请区分口径（官方统计/省级绩效累计/AI平台指标），"
|
||
"并在需要时调用 get_park_overview 工具获取实时准确数据。"
|
||
"当可能需要「切换页面 / 控制播放 / 展示卡片 / 弹出通知」时，必须调用对应工具；"
|
||
"其余园区相关问题用简洁、专业的中文回答，可适当使用列表。"
|
||
"你必须基于知识库或者工具调用结果回答问题，不能编造数据或内容。"
|
||
"如果有不确定的内容，请明确告知用户「我不确定，请咨询园区工作人员」。"
|
||
"如果用户询问园区的企业，没有指定的情况下，必须介绍派音人工智能"
|
||
"企业信息（企业名称、负责人、入驻分区、简介）一律以【园区知识库·检索命中】中企业名录原文为准；"
|
||
"严禁自行编造或补充企业备案号、成立时间、注册资本、投资方、获奖、政府项目等知识库未记载的细节；"
|
||
"若用户问到的企业细节在知识库中没有记载，请如实说明「该信息在园区资料中未记载」，不要编造。"
|
||
)
|
||
|
||
# 暴露给大模型的工具定义（执行时经 MQTT 广播到前端）
|
||
TOOLS = [
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "navigate_page",
|
||
"description": "切换大屏展示页面（数据大屏 / 数字孪生 / AI 助手 / 媒体轮播）",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"page": {"type": "string", "enum": ["/", "/twin", "/ai", "/screen"],
|
||
"description": "目标页面路径"},
|
||
},
|
||
"required": ["page"],
|
||
},
|
||
},
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "media_control",
|
||
"description": "控制媒体播放（播放/暂停/下一项/上一项）",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"action": {"type": "string", "enum": ["play", "pause", "next", "prev"]},
|
||
},
|
||
"required": ["action"],
|
||
},
|
||
},
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "show_card",
|
||
"description": "在大屏上展示信息卡片（企业分布 / 分区介绍 / 园区总览 / 自定义内容）",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"card": {"type": "string", "enum": ["companies", "zones", "overview", "custom"]},
|
||
"title": {"type": "string"},
|
||
"content": {"type": "string"},
|
||
},
|
||
"required": ["card"],
|
||
},
|
||
},
|
||
},
|
||
{
|
||
"type": "function",
|
||
"function": {
|
||
"name": "send_alert",
|
||
"description": "在大屏上弹出通知提示",
|
||
"parameters": {
|
||
"type": "object",
|
||
"properties": {
|
||
"title": {"type": "string"},
|
||
"content": {"type": "string"},
|
||
},
|
||
"required": ["title", "content"],
|
||
},
|
||
},
|
||
},
|
||
]
|
||
|
||
_TOOL_MAP = {
|
||
"navigate_page": "navigate",
|
||
"media_control": "control",
|
||
"show_card": "show_card",
|
||
"send_alert": "alert",
|
||
}
|
||
|
||
|
||
def _chat_once(messages, with_tools=True):
|
||
log.info("llm: 调用模型 %s（%d 条消息, 带工具=%s）", settings.LLM_MODEL, len(messages), with_tools)
|
||
payload = {
|
||
"model": settings.LLM_MODEL,
|
||
"messages": messages,
|
||
"temperature": 0.6,
|
||
}
|
||
if with_tools:
|
||
payload["tools"] = TOOLS
|
||
req = urllib.request.Request(
|
||
f"{settings.LLM_BASE_URL}/chat/completions",
|
||
data=json.dumps(payload, ensure_ascii=False).encode("utf-8"),
|
||
headers={
|
||
"Content-Type": "application/json",
|
||
"Authorization": f"Bearer {settings.DASHSCOPE_API_KEY}",
|
||
},
|
||
)
|
||
with urllib.request.urlopen(req, timeout=60, context=_SSL_CTX) as resp:
|
||
return json.loads(resp.read().decode("utf-8"))
|
||
|
||
|
||
def _fallback(messages, screen_id=""):
|
||
"""DashScope 不可用时回退本地规则引擎"""
|
||
from .ai_tools import run_chat as rule_run
|
||
|
||
result = rule_run(messages)
|
||
# 规则引擎产出的工具同样执行（MQTT 广播，带发起屏幕），并汇总发布结果
|
||
_, all_ok = _exec_all(result.get("tools", []), screen_id)
|
||
result["model"] = "rule-engine"
|
||
result["mqtt_published"] = all_ok
|
||
return result
|
||
|
||
|
||
def _exec_all(tools, screen_id=""):
|
||
"""执行工具列表（带发起屏幕 screen_id，工具结果只发到该屏），返回 (results, all_ok)"""
|
||
from .ai_tools import run_tools
|
||
|
||
results, all_ok = run_tools(tools, screen_id)
|
||
return results, all_ok
|
||
|
||
|
||
def run_chat(messages, screen_id=""):
|
||
"""入口：{reply, tools, model}
|
||
tools 已在后端执行（MQTT 广播，带发起屏幕 screen_id），返回值供请求端本地同步执行"""
|
||
if not settings.DASHSCOPE_API_KEY:
|
||
log.warning("未配置 DASHSCOPE_API_KEY，使用本地规则引擎")
|
||
return _fallback(messages, screen_id)
|
||
|
||
# 注入园区知识库（标准资料口径）：按用户 query 检索命中段落动态注入，
|
||
# 替代原 1200 字截断全量注入（避免尾部知识丢失）。无命中时回退 brief()。
|
||
system = SYSTEM_PROMPT
|
||
# 园区端配置的智能体提示词优先（park_config.get_agent()）
|
||
try:
|
||
from .park_config import get_agent
|
||
_agent = get_agent()
|
||
if _agent.get("system_prompt"):
|
||
system = _agent["system_prompt"]
|
||
except Exception: # noqa: BLE001
|
||
pass
|
||
kb = ""
|
||
retrieved_count = 0
|
||
try:
|
||
from .rag import brief, retrieve
|
||
query = ""
|
||
for m in reversed(messages or []):
|
||
if m.get("role") in ("user", "me"):
|
||
query = (m.get("content") or "").strip()
|
||
break
|
||
hits = retrieve(query, top_k=4) if query else []
|
||
if hits:
|
||
retrieved_count = len(hits)
|
||
kb = "\n\n".join(f"[{i + 1}] {c}" for i, c in enumerate(hits))
|
||
log.info("llm: 知识库检索命中 %d 段（query=%s）", len(hits), _trunc(query, 120))
|
||
else:
|
||
kb = brief()
|
||
if kb:
|
||
system += f"\n\n【园区知识库 · 检索命中】\n{kb}"
|
||
except Exception as e: # noqa: BLE001
|
||
log.warning("llm: 知识库注入失败（仅用基础提示词）: %s", e)
|
||
|
||
log.info("llm: ── 对话开始（%d 条输入消息）──", len(messages or []))
|
||
log.info("llm: 系统提示词=%s", _trunc(system, 700))
|
||
if kb:
|
||
log.info("llm: 注入知识库内容=%s", _trunc(kb, 500))
|
||
for m in (messages or [])[-5:]:
|
||
log.info("llm: 输入[%s] %s", m.get("role"), _trunc(m.get("content", ""), 300))
|
||
|
||
msgs = [{"role": "system", "content": system}] + [
|
||
{"role": m.get("role") == "me" and "user" or m.get("role", "user"), "content": m.get("content", "")}
|
||
for m in (messages or [])
|
||
]
|
||
|
||
try:
|
||
data = _chat_once(msgs)
|
||
choice = data["choices"][0]["message"]
|
||
reply = choice.get("content") or ""
|
||
tool_calls = choice.get("tool_calls") or []
|
||
executed = []
|
||
|
||
if tool_calls:
|
||
log.info("llm: 模型请求调用 %d 个工具：", len(tool_calls))
|
||
for tc in tool_calls:
|
||
fn = tc.get("function", {})
|
||
log.info("llm: 工具 %s args=%s", fn.get("name", ""), _trunc(fn.get("arguments", ""), 300))
|
||
for tc in tool_calls:
|
||
fn = tc.get("function", {})
|
||
name = fn.get("name", "")
|
||
try:
|
||
args = json.loads(fn.get("arguments") or "{}")
|
||
except json.JSONDecodeError:
|
||
args = {}
|
||
tool = {"type": _TOOL_MAP.get(name, name), "params": args}
|
||
executed.append(tool)
|
||
msgs.append({"role": "assistant", "content": None, "tool_calls": tool_calls})
|
||
msgs.append({
|
||
"role": "tool",
|
||
"tool_call_id": tc.get("id", ""),
|
||
"content": json.dumps({"ok": True}, ensure_ascii=False),
|
||
})
|
||
# 工具执行（MQTT 广播），并汇总发布结果
|
||
results, all_ok = _exec_all(executed, screen_id)
|
||
log.info("llm: 工具执行结果 %s", results)
|
||
for t in executed:
|
||
log.info("llm: 执行 %s %s", t["type"], json.dumps(t["params"], ensure_ascii=False))
|
||
# 二次调用：携带工具结果生成最终回复
|
||
try:
|
||
data2 = _chat_once(msgs, with_tools=False)
|
||
reply = data2["choices"][0]["message"].get("content") or reply
|
||
except Exception as e: # noqa: BLE001
|
||
log.warning("LLM 二次调用失败（保留工具回复）: %s", e)
|
||
else:
|
||
all_ok = True
|
||
|
||
if not reply:
|
||
reply = "已完成操作。您还可以让我切换页面、控制播放或展示园区卡片。"
|
||
|
||
log.info("llm: 最终回复=%s", _trunc(reply, 600))
|
||
log.info("llm: ── 对话结束 ──")
|
||
return {
|
||
"reply": reply,
|
||
"tools": executed,
|
||
"model": settings.LLM_MODEL,
|
||
"mqtt_published": all_ok,
|
||
"retrieved": retrieved_count > 0,
|
||
"retrieved_count": retrieved_count,
|
||
"tool_names": [t.get("type") for t in executed if t.get("type")],
|
||
}
|
||
except urllib.error.HTTPError as e:
|
||
log.warning("DashScope HTTP %s: %s", e.code, e.read()[:300])
|
||
except Exception as e: # noqa: BLE001
|
||
log.warning("DashScope 调用失败，回退规则引擎: %s", e)
|
||
|
||
return _fallback(messages)
|