From a7cba078dd487fb6c4c6c0bea688a6d589537e0d Mon Sep 17 00:00:00 2001
From: Andy Lee <andylizf@outlook.com>
Date: Sun, 27 Jul 2025 01:24:13 -0700
Subject: [PATCH] chore: consolidate essential fixes and add pre-commit hooks

- Add pre-commit configuration with ruff and black
- Fix lint CI job to use uv tool install instead of sync
- Add essential LlamaIndex dependencies to leann-core

Co-Authored-By: Yichuan Wang <73766326+yichuan-w@users.noreply.github.com>
---
 .github/workflows/build-reusable.yml |  8 ++++----
 .pre-commit-config.yaml              | 23 +++++++++++++++++++++++
 packages/leann-core/pyproject.toml   |  2 ++
 uv.lock                              |  4 ++++
 4 files changed, 33 insertions(+), 4 deletions(-)
 create mode 100644 .pre-commit-config.yaml

diff --git a/.github/workflows/build-reusable.yml b/.github/workflows/build-reusable.yml
index 9109383..1d762c2 100644
--- a/.github/workflows/build-reusable.yml
+++ b/.github/workflows/build-reusable.yml
@@ -26,17 +26,17 @@ jobs:
       - name: Install uv
         uses: astral-sh/setup-uv@v4
       
-      - name: Install dependencies
+      - name: Install ruff
         run: |
-          uv sync --dev
+          uv tool install ruff
       
       - name: Run ruff check
         run: |
-          uv run ruff check .
+          ruff check .
       
       - name: Run ruff format check
         run: |
-          uv run ruff format --check .
+          ruff format --check .
 
   build:
     needs: lint
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
new file mode 100644
index 0000000..ee7c901
--- /dev/null
+++ b/.pre-commit-config.yaml
@@ -0,0 +1,23 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+      - id: check-merge-conflict
+      - id: debug-statements
+
+  - repo: https://github.com/psf/black
+    rev: 24.1.1
+    hooks:
+      - id: black
+        language_version: python3
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.2.1
+    hooks:
+      - id: ruff
+        args: [--fix]
+      - id: ruff-format
diff --git a/packages/leann-core/pyproject.toml b/packages/leann-core/pyproject.toml
index 16f94c0..5071c3a 100644
--- a/packages/leann-core/pyproject.toml
+++ b/packages/leann-core/pyproject.toml
@@ -20,6 +20,8 @@ dependencies = [
     "torch>=2.0.0",
     "sentence-transformers>=2.2.0",
     "llama-index-core>=0.12.0",
+    "llama-index-readers-file>=0.4.0",  # Essential for document reading
+    "llama-index-embeddings-huggingface>=0.5.5",  # For embeddings
     "python-dotenv>=1.0.0",
     "openai>=1.0.0",
     "huggingface-hub>=0.20.0",
diff --git a/uv.lock b/uv.lock
index 80e6794..a46abc5 100644
--- a/uv.lock
+++ b/uv.lock
@@ -1891,6 +1891,8 @@ dependencies = [
     { name = "accelerate" },
     { name = "huggingface-hub" },
     { name = "llama-index-core" },
+    { name = "llama-index-embeddings-huggingface" },
+    { name = "llama-index-readers-file" },
     { name = "mlx", marker = "sys_platform == 'darwin'" },
     { name = "mlx-lm", marker = "sys_platform == 'darwin'" },
     { name = "msgpack" },
@@ -1916,6 +1918,8 @@ requires-dist = [
     { name = "accelerate", marker = "extra == 'colab'", specifier = ">=0.20.0,<1.0.0" },
     { name = "huggingface-hub", specifier = ">=0.20.0" },
     { name = "llama-index-core", specifier = ">=0.12.0" },
+    { name = "llama-index-embeddings-huggingface", specifier = ">=0.5.5" },
+    { name = "llama-index-readers-file", specifier = ">=0.4.0" },
     { name = "mlx", marker = "sys_platform == 'darwin'", specifier = ">=0.26.3" },
     { name = "mlx-lm", marker = "sys_platform == 'darwin'", specifier = ">=0.26.0" },
     { name = "msgpack", specifier = ">=1.0.0" },