refactor: 死代码清理 + UX 增强 + 查询清洗模块化

.dockerignore

@@ -0,0 +1,38 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+.venv/
+dist/
+build/
+
+# Git
+.git/
+.gitignore
+
+# IDE
+.vscode/
+.idea/
+
+# Environment
+.env
+
+# Logs
+*.log
+
+# Test
+.pytest_cache/
+htmlcov/
+.coverage
+
+# Docker
+Dockerfile
+.dockerignore
+docker-compose.yml
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Project specific
+data/chroma_db/*.sqlite3

.env.example

@@ -26,6 +26,32 @@ EMBEDDING_MODEL=BAAI/bge-m3
 # Cross-Encoder for relevance scoring
 RERANKER_MODEL=BAAI/bge-reranker-v2-m3
 
+# ===== PostgreSQL（Docker Compose 内自动配置）=====
+# 本地开发（非 Docker）：用自己的 PG 实例
+# DATABASE_URL=postgresql+asyncpg://postgres:postgres@localhost:5432/rednote_insight
+#
+# Docker Compose 部署：自动通过 docker-compose.yml 注入
+# DATABASE_URL=postgresql+asyncpg://postgres:postgres@db:5432/rednote_insight
+
+# ===== Redis（Docker Compose 内自动配置）=====
+# 本地开发（非 Docker）：
+# REDIS_URL=redis://localhost:6379/0
+#
+# Docker Compose 部署：自动通过 docker-compose.yml 注入
+# REDIS_URL=redis://redis:6379/0
+
+# ===== LangFuse 可观测性（可选）=====
+# 注册 https://cloud.langfuse.com 获取
+# LANGFUSE_PUBLIC_KEY=pk-...
+# LANGFUSE_SECRET_KEY=sk-...
+# LANGFUSE_HOST=https://cloud.langfuse.com
+
+# ===== 限流配置（可选）=====
+# RATE_LIMIT_ENABLED=true
+# RATE_LIMIT_INSIGHT=10/minute
+# RATE_LIMIT_QA=20/minute
+# RATE_LIMIT_CRAWL=5/minute
+
 # ===== 小红书 Cookie（Streamlit Cloud 部署用）=====
 # 在本地运行: uv run python scripts/export_cookies.py
 # 复制输出的 JSON 粘贴到 Streamlit Cloud Secrets → XHS_COOKIES

.github/workflows/ci.yml

@@ -0,0 +1,133 @@
+# =============================================================================
+# RedNote Insight — CI Pipeline
+# =============================================================================
+# 触发条件：push 到 main 或 PR 到 main
+# 自动运行：lint → test → build
+# =============================================================================
+
+name: CI
+
+on:
+  push:
+    branches: [main, master, refactor/production]
+  pull_request:
+    branches: [main, master]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  PYTHON_VERSION: "3.11"
+  UV_VERSION: "0.6.x"
+
+jobs:
+  # ===== 1. Lint（代码风格检查）=====
+  lint:
+    name: Lint (ruff)
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: ${{ env.UV_VERSION }}
+
+      - name: Set up Python
+        run: uv python install ${{ env.PYTHON_VERSION }}
+
+      - name: Install dependencies
+        run: uv sync --frozen --no-dev
+
+      - name: Install dev dependencies
+        run: uv sync --frozen
+
+      - name: Run ruff check
+        run: uv run ruff check src/ tests/
+
+      - name: Run ruff format check
+        run: uv run ruff format --check src/ tests/
+
+  # ===== 2. Test（单元测试 + 集成测试）=====
+  test:
+    name: Test (pytest)
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    needs: lint
+    services:
+      # PostgreSQL + pgvector（用于向量检索测试）
+      postgres:
+        image: pgvector/pgvector:pg16
+        env:
+          POSTGRES_USER: postgres
+          POSTGRES_PASSWORD: postgres
+          POSTGRES_DB: rednote_insight_test
+        ports:
+          - 5432:5432
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: ${{ env.UV_VERSION }}
+
+      - name: Set up Python
+        run: uv python install ${{ env.PYTHON_VERSION }}
+
+      - name: Install dependencies
+        run: uv sync --frozen
+
+      - name: Generate demo data
+        run: |
+          # 创建 .env 用于 generate_data.py
+          echo "OPENAI_API_KEY=ci-test-key" > .env
+          echo "OPENAI_BASE_URL=https://api.siliconflow.cn/v1" >> .env
+          uv run python generate_data.py
+        continue-on-error: true
+
+      - name: Run tests
+        run: |
+          uv run pytest tests/ \
+            -v \
+            --tb=short \
+            --timeout=60 \
+            -p no:warnings
+        env:
+          OPENAI_API_KEY: ci-test-key
+          OPENAI_BASE_URL: https://api.siliconflow.cn/v1
+
+  # ===== 3. Build（Docker 镜像构建验证）=====
+  build:
+    name: Build (Docker)
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+    needs: lint
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Build Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          push: false
+          load: true
+          tags: rednote-insight:ci-test
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Verify image
+        run: |
+          docker images rednote-insight:ci-test
+          echo "✅ Docker 镜像构建成功"

.gitignore

@@ -4,6 +4,7 @@ __pycache__/
 *.egg-info/
 dist/
 build/
+.pytest_cache/
 
 # 环境变量
 .env
@@ -14,6 +15,10 @@ sample_data.csv
 
 # 运行时日志
 app.log
+server.log
+
+# 缓存文件
+data/trending_cache.json
 
 # Vector DB index files are small — we COMMIT them so Streamlit Cloud
 # doesn't have to rebuild from scratch (saves 30-60s cold start).
@@ -29,8 +34,6 @@ Thumbs.db
 
 # Streamlit
 # .streamlit/secrets.toml — 提交此文件以在免费版 Streamlit Cloud 使用
-*.pyc
-__pycache__/
 
 # 小红书登录 Cookie（敏感信息，不要提交）
 data/cookies.json

Dockerfile

@@ -0,0 +1,61 @@
+# =============================================================================
+# RedNote Insight — 多阶段 Docker 构建
+# =============================================================================
+# 用法:
+#   docker build -t rednote-insight .
+#   docker run -p 8000:8000 --env-file .env rednote-insight
+# =============================================================================
+
+# ===== Stage 1: Builder — 装依赖 =====
+FROM python:3.11-slim AS builder
+
+WORKDIR /build
+
+# 系统依赖（ChromaDB 需要 sqlite3, jieba 等）
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    build-essential \
+    curl \
+    && rm -rf /var/lib/apt/lists/*
+
+# 安装 uv
+RUN pip install --no-cache-dir uv
+
+# 先复制依赖文件（利用 Docker 缓存层）
+COPY pyproject.toml uv.lock ./
+
+# 安装生产依赖到虚拟环境
+RUN uv sync --frozen --no-dev --no-editable
+
+# ===== Stage 2: Runtime — 最小镜像 =====
+FROM python:3.11-slim AS runtime
+
+WORKDIR /app
+
+# 运行时系统依赖
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libsqlite3-0 \
+    && rm -rf /var/lib/apt/lists/*
+
+# 从 builder 复制虚拟环境
+COPY --from=builder /build/.venv /app/.venv
+
+# 复制项目源码和配置
+COPY pyproject.toml ./
+COPY src/ ./src/
+COPY static/ ./static/
+COPY data/ ./data/
+COPY .env.example ./
+
+# 创建数据目录（如果不存在）
+RUN mkdir -p /app/data/raw /app/data/chroma_db
+
+# 暴露端口
+EXPOSE 8000
+
+# 健康检查
+HEALTHCHECK --interval=30s --timeout=5s --start-period=30s --retries=3 \
+    CMD curl -f http://localhost:8000/api/health || exit 1
+
+# 启动命令
+CMD [".venv/bin/uv", "run", "uvicorn", "src.api.main:app", \
+     "--host", "0.0.0.0", "--port", "8000", "--log-level", "info"]