Fix Windows builds by making fastembed optional

.github/workflows/release.yml

@@ -1,15 +1,51 @@
+# This file was autogenerated by dist: https://axodotdev.github.io/cargo-dist
+#
+# Copyright 2022-2024, axodotdev
+# SPDX-License-Identifier: MIT or Apache-2.0
+#
+# CI that:
+#
+# * checks for a Git Tag that looks like a release
+# * builds artifacts with dist (archives, installers, hashes)
+# * uploads those artifacts to temporary workflow zip
+# * on success, uploads the artifacts to a GitHub Release
+#
+# Note that the GitHub Release will be created with a generated
+# title/body based on your changelogs.
+
 name: Release
 permissions:
-  contents: "write"
+  "contents": "write"
 
+# This task will run whenever you push a git tag that looks like a version
+# like "1.0.0", "v0.1.0-prerelease.1", "my-app/0.1.0", "releases/v1.0.0", etc.
+# Various formats will be parsed into a VERSION and an optional PACKAGE_NAME, where
+# PACKAGE_NAME must be the name of a Cargo package in your workspace, and VERSION
+# must be a Cargo-style SemVer Version (must have at least major.minor.patch).
+#
+# If PACKAGE_NAME is specified, then the announcement will be for that
+# package (erroring out if it doesn't have the given version or isn't dist-able).
+#
+# If PACKAGE_NAME isn't specified, then the announcement will be for all
+# (dist-able) packages in the workspace with that version (this mode is
+# intended for workspaces with only one dist-able package, or with all dist-able
+# packages versioned/released in lockstep).
+#
+# If you push multiple tags at once, separate instances of this workflow will
+# spin up, creating an independent announcement for each one. However, GitHub
+# will hard limit this to 3 tags per commit, as it will assume more tags is a
+# mistake.
+#
+# If there's a prerelease-style suffix to the version, then the release(s)
+# will be marked as a prerelease.
 on:
   pull_request:
   push:
     tags:
       - '**[0-9]+.[0-9]+.[0-9]+*'
 
 jobs:
-  # 1. Plan Job (Linux에서 실행됨 - 버전 v0.30.3 유지)
+  # Run 'dist plan' (or host) to determine what tasks we need to do
   plan:
     runs-on: "ubuntu-22.04"
     outputs:
@@ -25,14 +61,20 @@ jobs:
           persist-credentials: false
           submodules: recursive
       - name: Install dist
+        # we specify bash to get pipefail; it guards against the `curl` command
+        # failing. otherwise `sh` won't catch that `curl` returned non-0
         shell: bash
-        # 🔥 [중요] 사용자님의 원래 버전(v0.30.3)으로 복구하여 에러 127 해결
         run: "curl --proto '=https' --tlsv1.2 -LsSf https://github.com/axodotdev/cargo-dist/releases/download/v0.30.3/cargo-dist-installer.sh | sh"
       - name: Cache dist
         uses: actions/upload-artifact@v4
         with:
           name: cargo-dist-cache
           path: ~/.cargo/bin/dist
+      # sure would be cool if github gave us proper conditionals...
+      # so here's a doubly-nested ternary-via-truthiness to try to provide the best possible
+      # functionality based on whether this is a pull_request, and whether it's from a fork.
+      # (PRs run on the *source* but secrets are usually on the *target* -- that's *good*
+      # but also really annoying to build CI around when it needs secrets to work right.)
       - id: plan
         run: |
           dist ${{ (!github.event.pull_request && format('host --steps=create --tag={0}', github.ref_name)) || 'plan' }} --output-format=json > plan-dist-manifest.json
@@ -45,26 +87,36 @@ jobs:
           name: artifacts-plan-dist-manifest
           path: plan-dist-manifest.json
 
-  # 2. Build Job (윈도우 설정 추가됨)
+  # Build and packages all the platform-specific things
   build-local-artifacts:
     name: build-local-artifacts (${{ join(matrix.targets, ', ') }})
+    # Let the initial task tell us to not run (currently very blunt)
     needs:
       - plan
     if: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix.include != null && (needs.plan.outputs.publishing == 'true' || fromJson(needs.plan.outputs.val).ci.github.pr_run_mode == 'upload') }}
     strategy:
       fail-fast: false
+      # Target platforms/runners are computed by dist in create-release.
+      # Each member of the matrix has the following arguments:
+      #
+      # - runner: the github runner
+      # - dist-args: cli flags to pass to dist
+      # - install-dist: expression to run to install dist on the runner
+      #
+      # Typically there will be:
+      # - 1 "global" task that builds universal installers
+      # - N "local" tasks that build each platform's binaries and platform-specific installers
       matrix: ${{ fromJson(needs.plan.outputs.val).ci.github.artifacts_matrix }}
     runs-on: ${{ matrix.runner }}
     container: ${{ matrix.container && matrix.container.image || null }}
     env:
       GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       BUILD_MANIFEST_NAME: target/distrib/${{ join(matrix.targets, '-') }}-dist-manifest.json
     steps:
-      # 🔥 [수정됨] 윈도우 빌드 실패 방지 (Linux 127 에러 방지를 위해 조건문 강화)
       - name: enable windows longpaths
         if: ${{ runner.os == 'Windows' }}
-        run: git config --system core.longpaths true
-
+        run: |
+          git config --global core.longpaths true
       - uses: actions/checkout@v4
         with:
           persist-credentials: false
@@ -78,6 +130,7 @@ jobs:
           fi
       - name: Install dist
         run: ${{ matrix.install_dist.run }}
+      # Get the dist-manifest
       - name: Fetch local artifacts
         uses: actions/download-artifact@v4
         with:
@@ -88,16 +141,29 @@ jobs:
         run: |
           ${{ matrix.packages_install }}
       - name: Build artifacts
+        shell: bash
         run: |
-          dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} > dist-manifest.json
+          # Actually do builds and make zips and whatnot
+          # For Windows builds, disable embeddings feature due to ONNX Runtime compatibility issues
+          TARGETS="${{ join(matrix.targets, ' ') }}"
+          if [[ "$TARGETS" == *"windows"* ]]; then
+            dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} --no-default-features > dist-manifest.json
+          else
+            dist build ${{ needs.plan.outputs.tag-flag }} --print=linkage --output-format=json ${{ matrix.dist_args }} > dist-manifest.json
+          fi
           echo "dist ran successfully"
       - id: cargo-dist
         name: Post-build
+        # We force bash here just because github makes it really hard to get values up
+        # to "real" actions without writing to env-vars, and writing to env-vars has
+        # inconsistent syntax between shell and powershell.
         shell: bash
         run: |
+          # Parse out what we just built and upload it to scratch storage
           echo "paths<<EOF" >> "$GITHUB_OUTPUT"
           dist print-upload-files-from-manifest --manifest dist-manifest.json >> "$GITHUB_OUTPUT"
           echo "EOF" >> "$GITHUB_OUTPUT"
+
           cp dist-manifest.json "$BUILD_MANIFEST_NAME"
       - name: "Upload artifacts"
         uses: actions/upload-artifact@v4
@@ -107,7 +173,7 @@ jobs:
             ${{ steps.cargo-dist.outputs.paths }}
             ${{ env.BUILD_MANIFEST_NAME }}
 
-  # 3. Global Build Job (그대로 유지)
+  # Build and package all the platform-agnostic(ish) things
   build-global-artifacts:
     needs:
       - plan
@@ -127,6 +193,7 @@ jobs:
           name: cargo-dist-cache
           path: ~/.cargo/bin/
       - run: chmod +x ~/.cargo/bin/dist
+      # Get all the local artifacts for the global tasks to use (for e.g. checksums)
       - name: Fetch local artifacts
         uses: actions/download-artifact@v4
         with:
@@ -138,9 +205,12 @@ jobs:
         run: |
           dist build ${{ needs.plan.outputs.tag-flag }} --output-format=json "--artifacts=global" > dist-manifest.json
           echo "dist ran successfully"
+
+          # Parse out what we just built and upload it to scratch storage
           echo "paths<<EOF" >> "$GITHUB_OUTPUT"
           jq --raw-output ".upload_files[]" dist-manifest.json >> "$GITHUB_OUTPUT"
           echo "EOF" >> "$GITHUB_OUTPUT"
+
           cp dist-manifest.json "$BUILD_MANIFEST_NAME"
       - name: "Upload artifacts"
         uses: actions/upload-artifact@v4
@@ -149,13 +219,13 @@ jobs:
           path: |
             ${{ steps.cargo-dist.outputs.paths }}
             ${{ env.BUILD_MANIFEST_NAME }}
-
-  # 4. Host Job (배포 - 그대로 유지)
+  # Determines if we should publish/announce
   host:
     needs:
       - plan
       - build-local-artifacts
       - build-global-artifacts
+    # Only run if we're "publishing", and only if plan, local and global didn't fail (skipped is fine)
     if: ${{ always() && needs.plan.result == 'success' && needs.plan.outputs.publishing == 'true' && (needs.build-global-artifacts.result == 'skipped' || needs.build-global-artifacts.result == 'success') && (needs.build-local-artifacts.result == 'skipped' || needs.build-local-artifacts.result == 'success') }}
     env:
       GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -173,6 +243,7 @@ jobs:
           name: cargo-dist-cache
           path: ~/.cargo/bin/
       - run: chmod +x ~/.cargo/bin/dist
+      # Fetch artifacts from scratch-storage
       - name: Fetch artifacts
         uses: actions/download-artifact@v4
         with:
@@ -189,8 +260,10 @@ jobs:
       - name: "Upload dist-manifest.json"
         uses: actions/upload-artifact@v4
         with:
+          # Overwrite the previous copy
           name: artifacts-dist-manifest
           path: dist-manifest.json
+      # Create a GitHub Release while uploading all files to it
       - name: "Download GitHub Artifacts"
         uses: actions/download-artifact@v4
         with:
@@ -199,6 +272,7 @@ jobs:
           merge-multiple: true
       - name: Cleanup
         run: |
+          # Remove the granular manifests
           rm -f artifacts/*-dist-manifest.json
       - name: Create GitHub Release
         env:
@@ -207,13 +281,18 @@ jobs:
           ANNOUNCEMENT_BODY: "${{ fromJson(steps.host.outputs.manifest).announcement_github_body }}"
           RELEASE_COMMIT: "${{ github.sha }}"
         run: |
+          # Write and read notes from a file to avoid quoting breaking things
           echo "$ANNOUNCEMENT_BODY" > $RUNNER_TEMP/notes.txt
+
           gh release create "${{ needs.plan.outputs.tag }}" --target "$RELEASE_COMMIT" $PRERELEASE_FLAG --title "$ANNOUNCEMENT_TITLE" --notes-file "$RUNNER_TEMP/notes.txt" artifacts/*
 
   announce:
     needs:
       - plan
       - host
+    # use "always() && ..." to allow us to wait for all publish jobs while
+    # still allowing individual publish jobs to skip themselves (for prereleases).
+    # "host" however must run to completion, no skipping allowed!
     if: ${{ always() && needs.host.result == 'success' }}
     runs-on: "ubuntu-22.04"
     env:

Cargo.toml

@@ -12,6 +12,10 @@ categories = ["command-line-utilities", "development-tools", "text-processing"]
 name = "amdb"
 path = "src/main.rs"
 
+[features]
+default = ["embeddings"]
+embeddings = ["dep:fastembed"]
+
 [dependencies]
 clap = { version = "4.4", features = ["derive"] }
 console = "0.15"
@@ -44,7 +48,7 @@ serde_json = "1.0"
 axum = "0.7"
 regex = "1.10"
 lazy_static = "1.4"
-fastembed = "4"
+fastembed = { version = "4", optional = true }
 ordered-float = "4.0"
 toml = "0.8"
 bincode = "1.3"

README.md

@@ -25,11 +25,17 @@ curl --proto '=https' --tlsv1.2 -LsSf https://github.com/BETAER-08/amdb/releases
 ### Option 2: Manual Download
 Prefer to download the file yourself? Go to the Releases Page and download the version for your OS.
 
+**📌 Windows Users:** Windows binaries are built without the embeddings feature due to ONNX Runtime compatibility issues. The Focus Mode (vector search) feature is not available on Windows, but all other functionality works normally.
+
 ### Option 3: Install via Cargo
 If you have the Rust toolchain installed:
 
 ```bash
+# Default installation (includes embeddings on non-Windows platforms)
 cargo install amdb
+
+# Windows or without embeddings
+cargo install amdb --no-default-features
 ```
 
 ## 🚀 Quick Start
@@ -62,6 +68,8 @@ amdb generate
 
 For large projects, a full context might be too big. Use **Focus Mode** to generate a summary relevant to a specific feature or bug. `amdb` uses vector search to find the most relevant files.
 
+**⚠️ Note:** This feature requires the `embeddings` feature which is not available on Windows builds due to dependency compatibility issues.
+
 ```bash
 # Example: generating context for authentication logic
 amdb generate --focus "login authentication jwt"

dist-workspace.toml

@@ -10,4 +10,6 @@ ci = "github"
 # The installers to generate for each app
 installers = []
 # Target platforms to build apps for (Rust target-triple syntax)
-targets = ["aarch64-apple-darwin", "aarch64-unknown-linux-gnu", "x86_64-apple-darwin", "x86_64-unknown-linux-gnu",]
+targets = ["aarch64-apple-darwin", "aarch64-pc-windows-msvc", "aarch64-unknown-linux-gnu", "x86_64-apple-darwin", "x86_64-pc-windows-msvc", "x86_64-unknown-linux-gnu"]
+# Skip checking whether the specified configuration files are up to date
+allow-dirty = ["ci"]

src/core/embedding.rs

@@ -1,22 +1,41 @@
 use anyhow::Result;
+
+#[cfg(feature = "embeddings")]
 use fastembed::{TextEmbedding, InitOptions, EmbeddingModel};
 
 pub struct EmbeddingEngine {
+    #[cfg(feature = "embeddings")]
     model: TextEmbedding,
 }
 
 impl EmbeddingEngine {
     pub fn new() -> Result<Self> {
-        let mut options = InitOptions::new(EmbeddingModel::BGESmallENV15);
-        options.show_download_progress = true;
+        #[cfg(feature = "embeddings")]
+        {
+            let mut options = InitOptions::new(EmbeddingModel::BGESmallENV15);
+            options.show_download_progress = true;
 
-        let model = TextEmbedding::try_new(options)?;
-        Ok(Self { model })
+            let model = TextEmbedding::try_new(options)?;
+            Ok(Self { model })
+        }
+
+        #[cfg(not(feature = "embeddings"))]
+        {
+            Ok(Self {})
+        }
     }
 
     pub fn embed(&self, text: &str) -> Result<Vec<f32>> {
-        let documents = vec![text.to_string()];
-        let embeddings = self.model.embed(documents, None)?;
-        Ok(embeddings[0].clone())
+        #[cfg(feature = "embeddings")]
+        {
+            let documents = vec![text.to_string()];
+            let embeddings = self.model.embed(documents, None)?;
+            Ok(embeddings[0].clone())
+        }
+
+        #[cfg(not(feature = "embeddings"))]
+        {
+            anyhow::bail!("Embedding feature is not available. On Windows, embeddings are not supported due to ONNX Runtime dependency limitations. On other platforms, rebuild with default features enabled.")
+        }
     }
 }