Update min required version to python==3.9 (#770)

* Deprecate `python==3.8`

* Fix format

.github/workflows/test.yml

@@ -25,7 +25,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.10", "3.11", "3.12"]
       fail-fast: false
 
     steps:

README.md

@@ -74,7 +74,7 @@ Distilabel is a tool that can be used to **synthesize data and provide AI feedba
 pip install distilabel --upgrade
 ```
 
-Requires Python 3.8+
+Requires Python 3.9+
 
 In addition, the following extras are available:
 

docs/sections/getting_started/installation.md

@@ -9,7 +9,7 @@ hide:
 !!! NOTE
     Since `distilabel` v1.0.0 was recently released, we refactored most of the stuff, so the installation below only applies to `distilabel` v1.0.0 and above.
 
-You will need to have at least Python 3.8 or higher, up to Python 3.12, since support for the latter is still a work in progress.
+You will need to have at least Python 3.9 or higher, up to Python 3.12, since support for the latter is still a work in progress.
 
 To install the latest release of the package from PyPI you can use the following command:
 
@@ -46,7 +46,7 @@ Additionally, as part of `distilabel` some extra dependencies are available, mai
 
 - `llama-cpp`: for using [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) Python bindings for `llama.cpp` via the `LlamaCppLLM` integration.
 
-- `mistralai`: for using models available in [Mistral AI API](https://mistral.ai/news/la-plateforme/) via the `MistralAILLM` integration. Note that the [`mistralai` Python client](https://github.com/mistralai/client-python) can only be installed from Python 3.9 onwards, so this is the only `distilabel` dependency that's not supported in Python 3.8.
+- `mistralai`: for using models available in [Mistral AI API](https://mistral.ai/news/la-plateforme/) via the `MistralAILLM` integration.
 
 - `ollama`: for using [Ollama](https://ollama.com/) and their available models via `OllamaLLM` integration.
 

pyproject.toml

@@ -6,14 +6,13 @@ build-backend = "hatchling.build"
 name = "distilabel"
 description = "Distilabel is an AI Feedback (AIF) framework for building datasets with and for LLMs."
 readme = "README.md"
-requires-python = ">=3.8"
+requires-python = ">=3.9"
 license = "Apache-2.0"
 keywords = ["llm", "annotation", "alignment", "synthetic", "data", "rlaif"]
 authors = [{ name = "Argilla", email = "[email protected]" }]
 classifiers = [
     "Development Status :: 4 - Beta",
     "Programming Language :: Python",
-    "Programming Language :: Python :: 3.8",
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",

scripts/install_dependencies.sh

@@ -6,9 +6,6 @@ python_version=$(python -c "import sys; print(sys.version_info[:2])")
 
 python -m pip install uv
 
-uv pip install --system -e ".[dev,tests,anthropic,argilla,cohere,groq,hf-inference-endpoints,hf-transformers,litellm,llama-cpp,ollama,openai,outlines,vertexai]"
-if [ "${python_version}" != "(3, 8)" ]; then
-	uv pip install --system -e .[mistralai,instructor]
-fi
+uv pip install --system -e ".[dev,tests,anthropic,argilla,cohere,groq,hf-inference-endpoints,hf-transformers,litellm,llama-cpp,ollama,openai,outlines,vertexai,mistralai,instructor]"
 
 uv pip install --system git+https://github.com/argilla-io/LLM-Blender.git

src/distilabel/pipeline/local.py

@@ -101,11 +101,14 @@ def run(
 
         num_processes = self.dag.get_total_replica_count()
         ctx = mp.get_context()  # type: ignore
-        with ctx.Manager() as manager, ctx.Pool(
-            num_processes,
-            initializer=_init_worker,
-            initargs=(log_queue,),
-        ) as pool:
+        with (
+            ctx.Manager() as manager,
+            ctx.Pool(
+                num_processes,
+                initializer=_init_worker,
+                initargs=(log_queue,),
+            ) as pool,
+        ):
             self._manager = manager
             self._pool = pool
             self._output_queue = self.QueueClass()

tests/unit/llms/huggingface/test_inference_endpoints.py

@@ -48,8 +48,11 @@ def test_load_with_cached_token(
         )
 
         # Mock `huggingface_hub.constants.HF_TOKEN_PATH` to exist
-        with mock.patch("pathlib.Path.exists", return_value=True), mock.patch(
-            "builtins.open", new_callable=mock.mock_open, read_data="hf_token"
+        with (
+            mock.patch("pathlib.Path.exists", return_value=True),
+            mock.patch(
+                "builtins.open", new_callable=mock.mock_open, read_data="hf_token"
+            ),
         ):
             # Should not raise any errors
             llm.load()

tests/unit/pipeline/test_base.py

@@ -105,11 +105,14 @@ def test_load_batch_manager(self, use_cache: bool) -> None:
         pipeline._load_batch_manager(use_cache=True)
         pipeline._cache()
 
-        with mock.patch(
-            "distilabel.pipeline.base._BatchManager.load_from_cache"
-        ) as mock_load_from_cache, mock.patch(
-            "distilabel.pipeline.base._BatchManager.from_dag"
-        ) as mock_from_dag:
+        with (
+            mock.patch(
+                "distilabel.pipeline.base._BatchManager.load_from_cache"
+            ) as mock_load_from_cache,
+            mock.patch(
+                "distilabel.pipeline.base._BatchManager.from_dag"
+            ) as mock_from_dag,
+        ):
             pipeline._load_batch_manager(use_cache=use_cache)
 
         if use_cache: