Import existing codebase.

.env.lib_debug

@@ -0,0 +1,4 @@
+export RUST_LOG=warn,cocoindex_engine=trace,tower_http=trace
+export RUST_BACKTRACE=1
+
+export COCOINDEX_SERVER_CORS_ORIGIN=http://localhost:3000

.github/scripts/update_version.sh

@@ -0,0 +1,22 @@
+#!/bin/bash -e
+
+# Extract version from tag (e.g. refs/tags/v1.2.3 -> 1.2.3)
+if [[ ! "$GITHUB_REF" =~ ^refs/tags/v ]]; then
+    echo "No version tag found"
+    exit 0
+fi
+VERSION="${GITHUB_REF#refs/tags/v}"
+
+echo "Building release version: $VERSION"
+
+# Detect OS and set sed inline flag accordingly.
+if [[ "$(uname)" == "Darwin" ]]; then
+  # macOS/BSD sed requires an empty string as backup extension
+  SED_INLINE=(-i '')
+else
+  # GNU sed on Linux can use -i without a backup extension
+  SED_INLINE=(-i)
+fi
+
+# Update Cargo.toml
+sed "${SED_INLINE[@]}" "s/^version = .*/version = \"$VERSION\"/" Cargo.toml

.github/workflows/CI.yml

@@ -0,0 +1,45 @@
+# This file is autogenerated by maturin v1.8.1
+# To update, run
+#
+#    maturin generate-ci github
+#
+name: CI
+
+on:
+  pull_request:
+    branches: [main]
+    paths:
+      - src/**
+      - python/**
+      - "*.toml"
+  push:
+    branches: [main]
+    paths:
+      - src/**
+      - python/**
+      - "*.toml"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ${{ matrix.platform.runner }}
+    strategy:
+      matrix:
+        platform:
+          - { os: linux, runner: ubuntu-22.04, target: aarch64 }
+          - { os: macos, runner: macos-14, target: aarch64 }
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.platform.target }}
+          args: --release --out dist --find-interpreter
+          sccache: 'true'
+          manylinux: auto

.github/workflows/docs.yml

@@ -0,0 +1,67 @@
+name: docs
+
+on:
+  pull_request:
+    branches: [main]
+    paths:
+      - docs/**
+  push:
+    branches: [main]
+    paths:
+      - docs/**
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+jobs:
+  test-deploy:
+    if: github.event_name != 'push'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          sparse-checkout: docs
+          path: src-staging
+      - name: Move docs
+        run: |
+          shopt -s dotglob
+          mv src-staging/docs/* .
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 18
+          cache: yarn
+      - name: Install dependencies
+        run: yarn install --frozen-lockfile
+      - name: Test build website
+        run: yarn build
+
+  deploy:
+    if: github.event_name != 'pull_request'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          sparse-checkout: docs
+          path: src-staging
+      - name: Move docs
+        run: |
+          shopt -s dotglob
+          mv src-staging/docs/* .
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 18
+          cache: yarn
+      - uses: webfactory/ssh-agent@v0.5.0
+        with:
+          ssh-private-key: ${{ secrets.GH_PAGES_DEPLOY }}
+      - name: Deploy to GitHub Pages
+        env:
+          USE_SSH: true
+        run: |
+          git config --global user.email "cocoindex.io@gmail.com"
+          git config --global user.name "CocoIndex"
+          yarn install --frozen-lockfile
+          yarn deploy

.github/workflows/release.yml

@@ -0,0 +1,112 @@
+# This file is autogenerated by maturin v1.8.1
+# To update, run
+#
+#    maturin generate-ci github
+#
+name: release
+
+on:
+  push:
+    tags:
+      - 'v*'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  create-versioned-toml:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - run: ./.github/scripts/update_version.sh
+      - uses: actions/upload-artifact@v4
+        with:
+          name: Cargo.toml
+          path: Cargo.toml
+
+  build:
+    runs-on: ${{ matrix.platform.runner }}
+    needs: [create-versioned-toml]
+    strategy:
+      matrix:
+        platform:
+          - { os: linux, runner: ubuntu-22.04, target: x86_64 }
+          - { os: linux, runner: ubuntu-22.04, target: aarch64 }
+          - { os: linux, runner: ubuntu-22.04, target: armv7 }
+          - { os: musllinux, runner: ubuntu-22.04, target: x86_64 }
+          - { os: musllinux, runner: ubuntu-22.04, target: aarch64 }
+          - { os: musllinux, runner: ubuntu-22.04, target: armv7 }
+          - { os: windows, runner: windows-latest, target: x64 }
+          - { os: macos, runner: macos-13, target: x86_64 }
+          - { os: macos, runner: macos-14, target: aarch64 }
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/download-artifact@v4
+        with:
+          name: Cargo.toml
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - name: Build wheels
+        uses: PyO3/maturin-action@v1
+        with:
+          target: ${{ matrix.platform.target }}
+          args: --release --out dist --find-interpreter
+          sccache: 'true'
+          manylinux: auto
+      - name: Upload wheels
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-${{ matrix.platform.os }}-${{ matrix.platform.target }}
+          path: dist
+
+  sdist:
+    runs-on: ubuntu-latest
+    needs: [create-versioned-toml]
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/download-artifact@v4
+        with:
+          name: Cargo.toml
+      - name: Build sdist
+        uses: PyO3/maturin-action@v1
+        with:
+          command: sdist
+          args: --out dist
+      - name: Upload sdist
+        uses: actions/upload-artifact@v4
+        with:
+          name: wheels-sdist
+          path: dist
+
+  release:
+    name: Release
+    runs-on: ubuntu-latest
+    needs: [create-versioned-toml, build, sdist]
+    permissions:
+      # Use to sign the release artifacts
+      id-token: write
+      # Used to upload release artifacts
+      contents: write
+      # Used to generate artifact attestation
+      attestations: write
+    environment: release
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/download-artifact@v4
+        with:
+          name: Cargo.toml
+      - uses: actions/download-artifact@v4
+        with:
+          pattern: wheels-*
+      - name: Generate artifact attestation
+        uses: actions/attest-build-provenance@v1
+        with:
+          subject-path: 'wheels-*/*'
+      - name: Publish to PyPI
+        if: ${{ startsWith(github.ref, 'refs/tags/') }}
+        uses: PyO3/maturin-action@v1
+        with:
+          command: upload
+          args: --non-interactive --skip-existing wheels-*/*

.gitignore

@@ -0,0 +1,20 @@
+/target
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+.pytest_cache/
+*.py[cod]
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.venv/
+dist/
+
+.DS_Store
+
+# Lock files for dependencies should be ignored for library
+/Cargo.lock
+
+*.egg-info/

Cargo.toml

@@ -0,0 +1,37 @@
+[package]
+name = "cocoindex"
+version = "0.1.0"
+edition = "2021"
+
+# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
+[lib]
+name = "cocoindex_engine"
+crate-type = ["cdylib"]
+
+[dependencies]
+pyo3 = { version = "0.23.4" }
+anyhow = { version = "1.0.95", features = ["std"] }
+async-trait = "0.1.85"
+axum = "0.7.9"
+axum-extra = { version = "0.9.6", features = ["query"] }
+base64 = "0.22.1"
+chrono = "0.4.39"
+config = "0.14.1"
+const_format = "0.2.34"
+env_logger = "0.11.6"
+futures = "0.3.31"
+log = "0.4.25"
+regex = "1.11.1"
+serde = { version = "1.0.217", features = ["derive"] }
+serde_json = "1.0.137"
+sqlx = { version = "0.8.3", features = ["chrono", "postgres", "runtime-tokio"] }
+tokio = { version = "1.43.0", features = ["macros", "rt-multi-thread"] }
+tower = "0.5.2"
+tower-http = { version = "0.6.2", features = ["cors", "trace"] }
+indexmap = { version = "2.7.1", features = ["serde"] }
+blake2 = "0.10.6"
+pgvector = { version = "0.4.0", features = ["sqlx"] }
+blocking = "1.6.1"
+indenter = "0.3.3"
+itertools = "0.14.0"
+derivative = "2.2.0"