v0.9.9

.env.example

@@ -46,8 +46,14 @@ STORAGE_PATH=./storage
 # ==================== 管理员账号配置 ====================
 # 初始管理员账号信息
 ADMIN_USERNAME=admin
-ADMIN_PASSWORD=admin@123
+ADMIN_PASSWORD=Admin@123456
 ADMIN_EMAIL=admin@unisspace.com
 ADMIN_NICKNAME=系统管理员
-# 开发环境跳过 SSL 证书验证（生产环境请勿开启）
+# 仅当 LLM/Embedding 服务使用自签名证书时开启（生产环境保持 false）
-DISABLE_SSL_VERIFY=true
+DISABLE_SSL_VERIFY=false
+
+# ==================== ZVec 向量化配置 ====================
+# 向量数据目录（留空时使用 STORAGE_PATH 下的 vector_index，一般无需设置）
+ZVEC_DATA_DIR=
+# Embedding 向量维度（需与 llm_model_config 中选择的 embedding 模型一致）
+ZVEC_EMBEDDING_DIM=1536

backend/.dockerignore

@@ -44,3 +44,7 @@ Thumbs.db
 storage/
 temp/
 data/
+
+# Environment（避免把本地数据库/Redis 配置和明文密码打进镜像）
+.env
+.env.*

backend/Dockerfile

@@ -34,7 +34,8 @@ RUN set -eux; \
         shared-mime-info \
         fontconfig \
         fonts-dejavu-core \
-        fonts-wqy-microhei; then \
+        fonts-wqy-microhei \
+        curl; then \
         cp /tmp/debian.sources.bak /etc/apt/sources.list.d/debian.sources; \
         dpkg --configure -a || true; \
         apt-get -f install -y || true; \
@@ -48,7 +49,8 @@ RUN set -eux; \
             shared-mime-info \
             fontconfig \
             fonts-dejavu-core \
-            fonts-wqy-microhei; \
+            fonts-wqy-microhei \
+            curl; \
     fi; \
     rm -rf /var/lib/apt/lists/*
 

backend/app/api/v1/chat.py

@@ -26,7 +26,6 @@ from app.services.project_service import (
 )
 from app.services.rag_service import rag_service
 from app.services.zvec_service import zvec_service
-from app.services.llm_provider_service import LLMProviderService
 from app.services.project_vectorization_task_service import project_vectorization_task_service
 from pydantic import BaseModel
 
@@ -285,43 +284,16 @@ def _compact_cited_refs(answer: str, retrieved_docs):
     return normalized_answer, refs
 
 
-async def _generate_session_title(db, llm_config_id: int, question: str, answer: str) -> Optional[str]:
+MAX_SESSION_TITLE_LENGTH = 60
-    """根据首轮问答，用 LLM 生成简洁的会话标题。失败时返回 None。"""
-    stmt = select(LLMModelConfig).where(LLMModelConfig.config_id == llm_config_id)
-    result = await db.execute(stmt)
-    llm_config = result.scalar_one_or_none()
-    if not llm_config:
-        return None
 
-    system_prompt = (
-        "你是一个会话标题生成器。请根据用户的问题和助手的回答，"
-        "用一句不超过 16 个字的中文短语概括对话主题，作为标题。"
-        "只输出标题本身，不要引号、标点结尾或任何解释。"
-    )
-    user_content = f"用户问题：{question}\n\n助手回答：{(answer or '')[:500]}"
-
-    try:
-        title = await LLMProviderService.generate_text(
-            provider=llm_config.provider,
-            endpoint_url=llm_config.endpoint_url,
-            api_key=llm_config.api_key,
-            llm_model_name=llm_config.llm_model_name,
-            timeout=min(int(llm_config.llm_timeout or 60), 60),
-            temperature=0.3,
-            top_p=float(llm_config.llm_top_p or 0.9),
-            max_tokens=32,
-            system_prompt=system_prompt,
-            messages=[{"role": "user", "content": user_content}],
-        )
-    except Exception as exc:  # noqa: BLE001 - 标题生成失败不应影响主流程
-        logger.warning("生成会话标题失败: %s", exc)
-        return None
 
+def _normalize_session_title(title: Optional[str]) -> str:
+    """会话标题统一处理：取首行、去掉多余引号与空白，超长截断，空值回退。"""
     title = (title or "").strip().strip('"').strip("「」").strip()
     title = title.splitlines()[0].strip() if title else ""
     if not title:
-        return None
+        return "新对话"
-    return title[:60]
+    return title[:MAX_SESSION_TITLE_LENGTH]
 
 
 @router.post("/sessions", response_model=dict)
@@ -347,7 +319,7 @@ async def create_chat_session(
         user_id=current_user.id,
         project_id=req.project_id,
         llm_config_id=req.llm_config_id,
-        title=req.title,
+        title=_normalize_session_title(req.title),
     )
     db.add(session)
     await db.commit()
@@ -672,8 +644,6 @@ async def send_chat_message_stream(
     user_message_id = query_message.id
     assistant_message_id = assistant_message.id
 
-    # 是否首轮对话（生成会话标题用）
-    is_first_exchange = len(conversation_history) == 0
     llm_config_id = session.llm_config_id
     project_id = session.project_id
     # 每累计这么多字符就回写一次占位行，平衡「刷新可见性」与「写库频率」
@@ -682,7 +652,7 @@ async def send_chat_message_stream(
     async def _persist_assistant(parts, *, completed):
         """把已生成内容回写到占位的助手消息行。
 
-        completed=True 时附带引用解析与标题生成；False 表示流式中途的增量回写。
+        completed=True 时附带引用解析；False 表示流式中途的增量回写。
         """
         assistant_response = "".join(parts)
         cited_refs = []
@@ -700,22 +670,8 @@ async def send_chat_message_stream(
                     json.dumps(cited_refs, ensure_ascii=False) if cited_refs else None
                 )
 
-        new_title = None
-        if completed and is_first_exchange:
-            new_title = await _generate_session_title(
-                db, llm_config_id, question, assistant_response
-            )
-            # LLM 生成失败时回退为截断后的问题，确保侧边栏拿到有意义的标题
-            if not new_title:
-                fallback = (question or "").strip().splitlines()[0] if question else ""
-                new_title = (fallback[:24] + "...") if len(fallback) > 24 else fallback
-            if new_title:
-                sess = await db.get(ChatSession, req.session_id)
-                if sess is not None:
-                    sess.title = new_title
-
         await db.commit()
-        return assistant_response, references, new_title
+        return assistant_response, references
 
     async def event_generator():
         assistant_response_parts = []
@@ -746,24 +702,18 @@ async def send_chat_message_stream(
                     chars_since_flush = 0
                     await _persist_assistant(assistant_response_parts, completed=False)
 
-            assistant_response, references, new_title = await _persist_assistant(
+            assistant_response, references = await _persist_assistant(
                 assistant_response_parts, completed=True
             )
             finished = True
 
             yield _stream_event("references", references or [])
-            if new_title:
-                yield _stream_event("title", {
-                    "session_id": req.session_id,
-                    "title": new_title,
-                })
             yield _stream_event("done", {
                 "session_id": req.session_id,
                 "user_message_id": user_message_id,
                 "assistant_message_id": assistant_message_id,
                 "content": assistant_response,
                 "references": references or [],
-                "title": new_title,
             })
         except (asyncio.CancelledError, GeneratorExit):
             # 客户端中途断开（如刷新页面）：尽力把已生成的部分回写到占位行。

docker-compose.yml

@@ -14,7 +14,6 @@ services:
       TZ: Asia/Shanghai
     volumes:
       - ${STORAGE_PATH:-./storage}/mysql:/var/lib/mysql
-      - ./backend/scripts/init.sql:/docker-entrypoint-initdb.d/init.sql:ro
     ports:
       - "${MYSQL_PORT:-3306}:3306"
     command:
@@ -34,12 +33,14 @@ services:
     command: redis-server --requirepass ${REDIS_PASSWORD:-redis_password_change_me} --appendonly yes
     environment:
       TZ: Asia/Shanghai
+      # 供容器内 redis-cli 健康检查使用，避免 NOAUTH 导致检查失效
+      REDISCLI_AUTH: ${REDIS_PASSWORD:-redis_password_change_me}
     volumes:
       - ${STORAGE_PATH:-./storage}/redis:/data
     ports:
       - "${REDIS_PORT:-6379}:6379"
     healthcheck:
-      test: ["CMD", "redis-cli", "--raw", "incr", "ping"]
+      test: ["CMD", "redis-cli", "--no-auth-warning", "ping"]
       interval: 10s
       timeout: 5s
       retries: 5
@@ -63,6 +64,12 @@ services:
       - REDIS_DB=${REDIS_DB:-8}
       - SECRET_KEY=${SECRET_KEY:-your-secret-key-change-me-in-production}
       - DEBUG=${DEBUG:-false}
+      - STORAGE_ROOT=/data/nex_docus_store
+      - CHUNK_SIZE=${CHUNK_SIZE:-800}
+      - CHUNK_OVERLAP=${CHUNK_OVERLAP:-150}
+      - DISABLE_SSL_VERIFY=${DISABLE_SSL_VERIFY:-false}
+      - ZVEC_DATA_DIR=${ZVEC_DATA_DIR:-}
+      - ZVEC_EMBEDDING_DIM=${ZVEC_EMBEDDING_DIM:-1536}
       - ADMIN_USERNAME=${ADMIN_USERNAME:-admin}
       - ADMIN_PASSWORD=${ADMIN_PASSWORD:-Admin@123456}
       - ADMIN_EMAIL=${ADMIN_EMAIL:-admin@example.com}

frontend/nginx.conf

@@ -25,8 +25,8 @@ server {
 
         # 超时设置
         proxy_connect_timeout 60s;
-        proxy_send_timeout 60s;
+        proxy_send_timeout 300s;
-        proxy_read_timeout 60s;
+        proxy_read_timeout 300s;
 
         # 增加上传文件大小限制
         client_max_body_size 100M;
@@ -41,6 +41,27 @@ server {
         add_header Cache-Control "no-cache, no-store, must-revalidate";
     }
 
+    # 聊天流式响应（SSE）：LLM 生成耗时较长，需要更长的读写超时
+    location /api/v1/chat/send/stream {
+        proxy_pass http://backend:8000/api/v1/chat/send/stream;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+
+        proxy_http_version 1.1;
+        proxy_set_header Connection "";
+
+        proxy_buffering off;
+        proxy_request_buffering off;
+
+        proxy_connect_timeout 60s;
+        proxy_send_timeout 600s;
+        proxy_read_timeout 600s;
+
+        add_header Cache-Control "no-cache, no-store, must-revalidate";
+    }
+
     # MCP Streamable HTTP 反向代理
     # 不对 /mcp 做 301/302 重定向，避免部分 MCP client 在跳转后丢失 POST body 或请求方法
     location = /mcp {