Experiments (#68)

* feat: finance bench

* docs: results

* chore: ignroe data README

* feat: fix financebench

* feat: laion, also required idmaps support

* style: format

* style: format

* fix: resolve ruff linting errors

- Remove unused variables in benchmark scripts
- Rename unused loop variables to follow convention

* feat: enron email bench

* experiments for running DiskANN & BM25 on Arch 4090

* style: format

* chore(ci): remove paru-bin submodule and config to fix checkout --recurse-submodules

* docs: data

* docs: data updated

* fix: as package

* fix(ci): only run pre-commit

* chore: use http url of astchunk; use group for some dev deps

* fix(ci): should checkout modules as well since `uv sync` checks

* fix(ci): run with lint only

* fix: find links to install wheels available

* CI: force local wheels in uv install step

* CI: install local wheels via file paths

* CI: pick wheels matching current Python tag

* CI: handle python tag mismatches for local wheels

* CI: use matrix python venv and set macOS deployment target

* CI: revert install step to match main

* CI: use uv group install with local wheel selection

* CI: rely on setup-uv for Python and tighten group install

* CI: install build deps with uv python interpreter

* CI: use temporary uv venv for build deps

* CI: add build venv scripts path for wheel repair

pyproject.toml

@@ -53,27 +53,10 @@ dependencies = [
     "tree-sitter-java>=0.20.0",
     "tree-sitter-c-sharp>=0.20.0",
     "tree-sitter-typescript>=0.20.0",
+    "torchvision>=0.23.0",
 ]
 
 [project.optional-dependencies]
-dev = [
-    "pytest>=7.0",
-    "pytest-cov>=4.0",
-    "pytest-xdist>=3.0",  # For parallel test execution
-    "black>=23.0",
-    "ruff==0.12.7",  # Fixed version to ensure consistent formatting across all environments
-    "matplotlib",
-    "huggingface-hub>=0.20.0",
-    "pre-commit>=3.5.0",
-]
-
-test = [
-    "pytest>=7.0",
-    "pytest-timeout>=2.0",
-    "llama-index-core>=0.12.0",
-    "python-dotenv>=1.0.0",
-]
-
 diskann = [
     "leann-backend-diskann",
 ]
@@ -101,6 +84,28 @@ leann-backend-diskann = { path = "packages/leann-backend-diskann", editable = tr
 leann-backend-hnsw = { path = "packages/leann-backend-hnsw", editable = true }
 astchunk = { path = "packages/astchunk-leann", editable = true }
 
+[dependency-groups]
+# Minimal lint toolchain for CI and local hooks
+lint = [
+    "pre-commit>=3.5.0",
+    "ruff==0.12.7",  # Fixed version to ensure consistent formatting across all environments
+]
+
+# Test toolchain (no heavy project runtime deps)
+test = [
+    "pytest>=7.0",
+    "pytest-cov>=4.0",
+    "pytest-xdist>=3.0",
+    "pytest-timeout>=2.0",
+    "python-dotenv>=1.0.0",
+]
+
+# dependencies by apps/ should list here
+dev = [
+    "matplotlib",
+    "huggingface-hub>=0.20.0",
+]
+
 [tool.ruff]
 target-version = "py39"
 line-length = 100