Merge pull request #1100 from argilla-io/develop

`1.5.0`

.github/ISSUE_TEMPLATE/1-add_documentation_report.yml

@@ -0,0 +1,26 @@
+name: "\U0001F4DA Add a documentation report"
+description: "Have you spotted a typo or mistake in our docs?"
+title: "[DOCS]"
+labels: ["documentation"]
+assignees: []
+
+body:
+  - type: markdown
+    attributes:
+      value: "Thank you for reporting a documentation mistake! Before you get started, please [search to see](https://github.com/argilla-io/distilabel/issues) if an issue already exists for the bug you encountered."
+
+  - type: textarea
+    id: doc_report
+    attributes:
+      label: "Which page or section is this issue related to?"
+      description: "Please include the URL and/or source."
+    validations:
+          required: false
+
+  - type: textarea
+    id: doc_review
+    attributes:
+      label: "What are you documenting, or what change are you making in the documentation?"
+      description: "If a documentation needs to be created, please specify its coverage.\n If there's a typo or something needs revisiting, please indicate it and show code/text/screenshots."
+    validations:
+          required: false

.github/ISSUE_TEMPLATE/2-bug_python.yml

@@ -0,0 +1,70 @@
+name: "\U0001FAB2 Bug report"
+description: "Report bugs and unexpected behavior."
+title: "[BUG]"
+labels: ["bug", "ml-internal"]
+assignees: []
+
+body:
+  - type: markdown
+    attributes:
+      value: "Thank you for reporting a bug! Before you get started, please [search to see](https://github.com/argilla-io/distilabel/issues) if an issue already exists for the bug you encountered."
+
+  - type: textarea
+    id: bug_description
+    attributes:
+      label: "Describe the bug"
+      description: "A clear and concise description of the bug."
+    validations:
+      required: true
+
+  - type: textarea
+    id: stacktrace
+    attributes:
+      label: "To reproduce"
+      description: "The code to reproduce the behavior."
+      placeholder: |
+        ```python
+        my_python_code
+        ```
+    validations:
+      required: false
+
+  - type: textarea
+    id: expected_behavior
+    attributes:
+      label: "Expected behavior"
+      description: "A clear and concise description of what you expected to happen."
+    validations:
+      required: false
+
+  - type: textarea
+    id: screenshots
+    attributes:
+      label: "Screenshots"
+      description: "If applicable, add screenshots to help explain your problem."
+    validations:
+      required: false
+
+  - type: textarea
+    id: environment
+    attributes:
+      label: "Environment"
+      description: "Since version 1.16.0 you can use `python -m argilla info` command to easily get the used versions."
+      value: |
+        - Distilabel Version [e.g. 1.0.0]:
+        - Python Version [e.g. 3.11]:
+    validations:
+      required: false
+
+  - type: textarea
+    id: additional_context
+    attributes:
+      label: "Additional context"
+      description: "Add any other relevant information."
+    validations:
+      required: false
+
+  - type: markdown
+    attributes:
+      value: |
+        📌  Make sure you have provided all the required information in each section so we can support you properly.

.github/ISSUE_TEMPLATE/3-feature_request.yml

@@ -0,0 +1,44 @@
+name: "\U0001F195 Feature request"
+description: "Share cool new ideas for the project."
+title: "[FEATURE]"
+labels: ["enhancement", "ml-internal"]
+assignees: []
+
+
+body:
+  - type: markdown
+    attributes:
+      value: "Thank you for sharing your feature request! Please fill out the sections below."
+
+  - type: textarea
+    id: feature_request
+    attributes:
+      label: "Is your feature request related to a problem? Please describe."
+      description: "A clear and concise description of what the problem is."
+      placeholder: "I'm always frustrated when..."
+    validations:
+          required: false
+
+  - type: textarea
+    id: feature_description
+    attributes:
+      label: "Describe the solution you'd like"
+      description: "A clear and concise description of what you want to happen."
+    validations:
+      required: false
+
+  - type: textarea
+    id: feature_alternatives
+    attributes:
+      label: "Describe alternatives you've considered"
+      description: "A clear and concise description of any alternative solutions or features you've considered."
+    validations:
+      required: false
+
+  - type: textarea
+    id: additional_context
+    attributes:
+      label: "Additional context"
+      description: "Add any other context or screenshots about the feature request here."
+    validations:
+      required: false

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: false
+contact_links:
+  - name: 🗯 Community Discussions
+    url: http://hf.co/join/discord
+    about: Our Discord Community loves to discuss distilabel and NLP topics

.github/workflows/test.yml

@@ -50,6 +50,12 @@ jobs:
         if: steps.cache.outputs.cache-hit != 'true'
         run: ./scripts/install_dependencies.sh
 
+      - name: Setup tmate session
+        uses: mxschmitt/action-tmate@v3
+        if: ${{ matrix.python-version == '3.12' && github.event_name == 'workflow_dispatch' && inputs.tmate_session }}
+        with:
+          limit-access-to-actor: true
+
       - name: Lint
         run: make lint
 

.gitignore

@@ -77,4 +77,4 @@ venv.bak/
 # Other
 *.log
 *.swp
-.DS_Store
+.DS_Store

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/Lucas-C/pre-commit-hooks
-    rev: v1.5.4
+    rev: v1.5.5
     hooks:
       - id: insert-license
         name: "Insert license header in Python source files"
@@ -10,8 +10,8 @@ repos:
           - LICENSE_HEADER
           - --fuzzy-match-generates-todo
 
-  - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: v0.6.2
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.1
     hooks:
       - id: ruff
         args: [--fix]

README.md

@@ -94,6 +94,7 @@ In addition, the following extras are available:
 - `vertexai`: for using [Google Vertex AI](https://cloud.google.com/vertex-ai) proprietary models via the `VertexAILLM` integration.
 - `vllm`: for using [vllm](https://github.com/vllm-project/vllm) serving engine via the `vLLM` integration.
 - `sentence-transformers`: for generating sentence embeddings using [sentence-transformers](https://github.com/UKPLab/sentence-transformers).
+- `mlx`: for using [MLX](https://github.com/ml-explore/mlx) models via the `MlxLLM` integration.
 
 ### Structured generation
 
@@ -118,7 +119,7 @@ pip install "distilabel[hf-inference-endpoints]" --upgrade
 Then run:
 
 ```python
-from distilabel.llms import InferenceEndpointsLLM
+from distilabel.models import InferenceEndpointsLLM
 from distilabel.pipeline import Pipeline
 from distilabel.steps import LoadDataFromHub
 from distilabel.steps.tasks import TextGeneration

docs/api/models/embedding/embedding_gallery.md

@@ -0,0 +1,8 @@
+# Embedding Gallery
+
+This section contains the existing [`Embeddings`][distilabel.models.embeddings] subclasses implemented in `distilabel`.
+
+::: distilabel.models.embeddings
+    options:
+        filters:
+        - "!^Embeddings$"

docs/api/embedding/index.md → docs/api/models/embedding/index.md

@@ -4,4 +4,4 @@ This section contains the API reference for the `distilabel` embeddings.
 
 For more information on how the [`Embeddings`][distilabel.steps.tasks.Task] works and see some examples.
 
-::: distilabel.embeddings.base
+::: distilabel.models.embeddings.base

docs/api/models/image_generation/image_generation_gallery.md

@@ -0,0 +1,10 @@
+# ImageGenerationModel Gallery
+
+This section contains the existing [`ImageGenerationModel`][distilabel.models.image_generation] subclasses implemented in `distilabel`.
+
+::: distilabel.models.image_generation
+    options:
+        filters:
+        - "!^ImageGenerationModel$"
+        - "!^AsyngImageGenerationModel$"
+        - "!typing"

docs/api/models/image_generation/index.md

@@ -0,0 +1,7 @@
+# ImageGenerationModel
+
+This section contains the API reference for the `distilabel` image generation models, both for the [`ImageGenerationModel`][distilabel.models.image_generation.ImageGenerationModel] synchronous implementation, and for the [`AsyncImageGenerationModel`][distilabel.models.image_generation.AsyncImageGenerationModel] asynchronous one.
+
+For more information and examples on how to use existing LLMs or create custom ones, please refer to [Tutorial - ImageGenerationModel](../../../sections/how_to_guides/basic/task/image_task.md).
+
+::: distilabel.models.image_generation.base

docs/api/models/llm/index.md

@@ -0,0 +1,7 @@
+# LLM
+
+This section contains the API reference for the `distilabel` LLMs, both for the [`LLM`][distilabel.models.llms.LLM] synchronous implementation, and for the [`AsyncLLM`][distilabel.models.llms.AsyncLLM] asynchronous one.
+
+For more information and examples on how to use existing LLMs or create custom ones, please refer to [Tutorial - LLM](../../../sections/how_to_guides/basic/llm/index.md).
+
+::: distilabel.models.llms.base

docs/api/models/llm/llm_gallery.md

@@ -0,0 +1,10 @@
+# LLM Gallery
+
+This section contains the existing [`LLM`][distilabel.models.llms] subclasses implemented in `distilabel`.
+
+::: distilabel.models.llms
+    options:
+        filters:
+        - "!^LLM$"
+        - "!^AsyncLLM$"
+        - "!typing"

docs/api/task/image_task.md

@@ -0,0 +1,7 @@
+# ImageTask
+
+This section contains the API reference for the `distilabel` image generation tasks.
+
+For more information on how the [`ImageTask`][distilabel.steps.tasks.ImageTask] works and see some examples, check the [Tutorial - Task - ImageTask](../../sections/how_to_guides/basic/task/generator_task.md) page.
+
+::: distilabel.steps.tasks.base.ImageTask

docs/api/task/task_gallery.md

@@ -8,5 +8,6 @@ This section contains the existing [`Task`][distilabel.steps.tasks.Task] subclas
         - "!Task"
         - "!_Task"
         - "!GeneratorTask"
+        - "!ImageTask"
         - "!ChatType"
         - "!typing"