[Enhancement] Add pre-commit config

.pre-commit-config.yaml

@@ -0,0 +1,74 @@
+default_language_version:
+  python: python3.9
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v6.0.0
+    hooks:
+      - id: trailing-whitespace
+        args: [--markdown-linebreak-ext=md]
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        args: [--fix=auto]
+      - id: check-merge-conflict
+      - id: check-json
+      - id: check-yaml
+      - id: check-toml
+      - id: check-ast
+      - id: debug-statements
+      - id: detect-private-key
+      - id: pretty-format-json
+        args: [--autofix, --no-ensure-ascii, --indent=2]
+      - id: check-illegal-windows-names
+      - id: check-case-conflict
+      - id: check-symlinks
+      - id: check-executables-have-shebangs
+      - id: check-shebang-scripts-are-executable
+      - id: requirements-txt-fixer
+      - id: no-commit-to-branch
+        args: [--branch, main]
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        name: Sort imports with isort
+        files: ^(sygra|tests)/.*\.py$
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.2.1
+    hooks:
+      - id: ruff
+        name: Lint with Ruff
+        args: [--fix, --unsafe-fixes, --exit-non-zero-on-fix, --show-fixes]
+        files: ^(sygra|tests)/
+
+  - repo: local
+    hooks:
+      - id: mypy-poetry
+        name: Type check with mypy
+        entry: poetry run mypy sygra
+        language: system
+        pass_filenames: false
+        stages: [ pre-commit ]
+
+  - repo: https://github.com/psf/black
+    rev: 24.8.0
+    hooks:
+      - id: black
+        name: Format code with Black
+        files: ^(sygra|tests)/.*\.py$
+
+  - repo: https://github.com/python-poetry/poetry
+    rev: 1.7.0
+    hooks:
+      - id: poetry-check
+
+  - repo: local
+    hooks:
+      - id: pytest
+        name: Run tests with pytest
+        entry: poetry run pytest -q tests
+        language: system
+        pass_filenames: false
+        stages: [ pre-commit ]

CONTRIBUTING.md

@@ -23,6 +23,30 @@ When everything is set up, you can refer to the
 
 sections to setup a synthetic data generation pipeline.
 
+## Pre-commit hooks
+
+We use [pre-commit](https://pre-commit.com/) to keep the codebase consistent. Hooks are run automatically on `git commit` (and some on `pre-push`).
+
+### One-time setup
+
+```bash
+# Install dependencies (includes pre-commit as a dev dep)
+poetry install
+
+# Install Git hooks for this repo
+poetry run pre-commit install
+poetry run pre-commit install -t pre-push
+
+# (optional) Warm the caches so your first commit is fast
+poetry run pre-commit run --all-files
+```
+
+#### Why pre-commit?
+
+- Fast feedback on style/format issues
+- Consistent code across contributors
+- Fewer “nit” comments in PR reviews
+
 ## How to submit a bug report
 
 [Open an issue on Github](https://github.com/ServiceNow/sygra/issues/new/choose) and select "Bug report". If you are not sure whether it is a bug or not, submit an issue and we will be able to help you.

pyproject.toml

@@ -56,6 +56,7 @@ dependencies = [
   "sentence-transformers>=5.1,<6.0",
   "soundfile>=0.13,<1.0",
   "types-pyyaml>=6.0,<7.0",
+  "fasttext-wheel (>=0.9.2,<0.10.0)",
 ]
 
 [project.optional-dependencies]

sygra/models/__init__.py

@@ -37,18 +37,7 @@ def from_name(model_name: str, **kwargs) -> Optional[dict[str, Any]]:
                     base_config["parameters"] = {}
 
                 params: dict[str, Any] = cast(dict[str, Any], base_config["parameters"])
-                params.update(
-                    {
-                        "temperature": kwargs.get(
-                            "temperature",
-                            params.get("temperature", 0.7),
-                        ),
-                        "max_tokens": kwargs.get(
-                            "max_tokens",
-                            params.get("max_tokens", 1000),
-                        ),
-                    }
-                )
+                params.update(kwargs)
 
                 return base_config
             else: