distilabel v1.2.0

argilla-io · Jun 18, 2024 · 3910aca · 3910aca
2 parents f9057f0 + 63ee8c5
commit 3910aca
Show file tree

Hide file tree

Showing 224 changed files with 18,861 additions and 5,809 deletions.
diff --git a/.github/workflows/codspeed.yml b/.github/workflows/codspeed.yml
@@ -0,0 +1,42 @@
+name: Benchmarks
+
+on:
+  push:
+    branches:
+      - "main"
+  pull_request:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  benchmarks:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.12"
+          # Looks like it's not working very well for other people:
+          # https://github.com/actions/setup-python/issues/436
+          # cache: "pip"
+          # cache-dependency-path: pyproject.toml
+
+      - uses: actions/cache@v3
+        id: cache
+        with:
+          path: ${{ env.pythonLocation }}
+          key: ${{ runner.os }}-python-${{ env.pythonLocation }}-${{ hashFiles('pyproject.toml') }}-benchmarks-v00
+
+      - name: Install dependencies
+        if: steps.cache.outputs.cache-hit != 'true'
+        run: ./scripts/install_dependencies.sh
+
+      - name: Run benchmarks
+        uses: CodSpeedHQ/action@v2
+        with:
+          token: ${{ secrets.CODSPEED_TOKEN }}
+          run: pytest tests/ --codspeed
diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
@@ -45,6 +45,10 @@ jobs:
 
       - run: mike deploy dev --push
         if: github.ref == 'refs/heads/develop'
+        env:
+          GH_ACCESS_TOKEN: ${{ secrets.GH_ACCESS_TOKEN }}
 
       - run: mike deploy ${{ github.ref_name }} latest --update-aliases --push
         if: startsWith(github.ref, 'refs/tags/')
+        env:
+          GH_ACCESS_TOKEN: ${{ secrets.GH_ACCESS_TOKEN }}
diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
@@ -9,6 +9,12 @@ on:
     types:
       - opened
       - synchronize
+  workflow_dispatch:
+    inputs:
+      tmate_session:
+        description: Starts the workflow with tmate enabled.
+        required: false
+        default: "false"
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
@@ -19,7 +25,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
       fail-fast: false
 
     steps:
@@ -42,14 +48,7 @@ jobs:
 
       - name: Install dependencies
         if: steps.cache.outputs.cache-hit != 'true'
-        run: |
-          python_version=$(python -c "import sys; print(sys.version_info[:2])")
-
-          pip install -e .[dev,tests,anthropic,argilla,cohere,groq,hf-inference-endpoints,hf-transformers,litellm,llama-cpp,ollama,openai,outlines,vertexai,vllm]
-          if [ "${python_version}" != "(3, 8)" ]; then
-            pip install -e .[mistralai]
-          fi;
-          pip install git+https://github.com/argilla-io/LLM-Blender.git
+        run: ./scripts/install_dependencies.sh
 
       - name: Lint
         run: make lint
@@ -59,4 +58,3 @@ jobs:
 
       - name: Integration Tests
         run: make integration-tests
-        timeout-minutes: 5
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -11,11 +11,10 @@ repos:
           - --fuzzy-match-generates-todo
 
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: v0.1.4
+    rev: v0.4.5
     hooks:
       - id: ruff
-        args:
-          - --fix
+        args: [--fix]
       - id: ruff-format
 
 ci:

diff --git a/Makefile b/Makefile
@@ -2,12 +2,12 @@ sources = src/distilabel tests
 
 .PHONY: format
 format:
-	ruff --fix $(sources)
+	ruff check --fix $(sources)
 	ruff format $(sources)
 
 .PHONY: lint
 lint:
-	ruff $(sources)
+	ruff check $(sources)
 	ruff format --check $(sources)
 
 .PHONY: unit-tests

diff --git a/README.md b/README.md
@@ -50,7 +50,7 @@ Compute is expensive and output quality is important. We help you **focus on dat
 
 Synthesize and judge data with **latest research papers** while ensuring **flexibility, scalability and fault tolerance**. So you can focus on improving your data and training your models.
 
-## 🏘️ Community
+## Community
 
 We are an open-source community-driven project and we love to hear from you. Here are some ways to get involved:
 
@@ -68,7 +68,7 @@ Distilabel is a tool that can be used to **synthesize data and provide AI feedba
 - Our [distilabeled Intel Orca DPO dataset](https://huggingface.co/datasets/argilla/distilabel-intel-orca-dpo-pairs) and the [improved OpenHermes model](https://huggingface.co/argilla/distilabeled-OpenHermes-2.5-Mistral-7B),, show how we **improve model performance by filtering out 50%** of the original dataset through **AI feedback**.
 - The [haiku DPO data](https://github.com/davanstrien/haiku-dpo) outlines how anyone can create a **dataset for a specific task** and **the latest research papers** to improve the quality of the dataset.
 
-## 👨🏽‍💻 Installation
+## Installation
 
 ```sh
 pip install distilabel --upgrade
@@ -116,7 +116,7 @@ with Pipeline(
 
     generate_with_openai = TextGeneration(llm=OpenAILLM(model="gpt-3.5-turbo"))
 
-    load_dataset.connect(generate_with_openai)
+    load_dataset >> generate_with_openai
 
 if __name__ == "__main__":
     distiset = pipeline.run(
@@ -153,3 +153,15 @@ If you build something cool with `distilabel` consider adding one of these badge
 
 To directly contribute with `distilabel`, check our [good first issues](https://github.com/argilla-io/distilabel/issues?q=is%3Aissue+is%3Aopen+label%3A%22good+first+issue%22) or [open a new one](https://github.com/argilla-io/distilabel/issues/new/choose).
 
+## Citation
+
+```bibtex
+@misc{distilabel-argilla-2024,
+  author = {Álvaro Bartolomé Del Canto and Gabriel Martín Blázquez and Agustín Piqueres Lajarín and Daniel Vila Suero},
+  title = {Distilabel: An AI Feedback (AIF) framework for building datasets with and for LLMs},
+  year = {2024},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/argilla-io/distilabel}}
+}
+```
diff --git a/docs/api/cli.md b/docs/api/cli.md
@@ -1,6 +1,6 @@
 # Command Line Interface (CLI)
 
-This section contains the API reference for the CLI. For more information on how to use the CLI, see [Tutorial - CLI](../sections/learn/tutorial/cli/index.md).
+This section contains the API reference for the CLI. For more information on how to use the CLI, see [Tutorial - CLI](../sections/how_to_guides/advanced/cli/index.md).
 
 ## Utility functions for the `distilabel pipeline` sub-commands
 

diff --git a/docs/api/distiset.md b/docs/api/distiset.md
@@ -0,0 +1,6 @@
+# Distiset
+
+This section contains the API reference for the Distiset. For more information on how to use the CLI, see [Tutorial - CLI](../sections/how_to_guides/advanced/distiset.md).
+
+:::distilabel.distiset.Distiset
+:::distilabel.distiset.create_distiset
diff --git a/docs/api/llm/cohere.md b/docs/api/llm/cohere.md
@@ -0,0 +1,3 @@
+# CohereLLM
+
+::: distilabel.llms.cohere
diff --git a/docs/api/llm/index.md b/docs/api/llm/index.md
@@ -2,6 +2,6 @@
 
 This section contains the API reference for the `distilabel` LLMs, both for the [`LLM`][distilabel.llms.LLM] synchronous implementation, and for the [`AsyncLLM`][distilabel.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/learn/tutorial/llm/index.md).
+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.llms.base
diff --git a/docs/api/pipeline/index.md b/docs/api/pipeline/index.md
@@ -1,6 +1,6 @@
 # Pipeline
 
-This section contains the API reference for the `distilabel` pipelines. For an example on how to use the pipelines, see the [Tutorial - Pipeline](../../sections/learn/tutorial/pipeline/index.md).
+This section contains the API reference for the `distilabel` pipelines. For an example on how to use the pipelines, see the [Tutorial - Pipeline](../../sections/how_to_guides/basic/pipeline/index.md).
 
 ::: distilabel.pipeline.base
 ::: distilabel.pipeline.local
diff --git a/docs/api/step/decorator.md b/docs/api/step/decorator.md
@@ -2,6 +2,6 @@
 
 This section contains the reference for the `@step` decorator, used to create new [`Step`][distilabel.steps.Step] subclasses without having to manually define the class.
 
-For more information check the [Tutorial - Step](../../sections/learn/tutorial/step/index.md) page.
+For more information check the [Tutorial - Step](../../sections/how_to_guides/basic/step/index.md) page.
 
 ::: distilabel.steps.decorator
diff --git a/docs/api/step/generator_step.md b/docs/api/step/generator_step.md
@@ -2,6 +2,6 @@
 
 This section contains the API reference for the [`GeneratorStep`][distilabel.steps.base.GeneratorStep] class.
 
-For more information and examples on how to use existing generator steps or create custom ones, please refer to [Tutorial - Step - GeneratorStep](../../sections/learn/tutorial/step/generator_step.md).
+For more information and examples on how to use existing generator steps or create custom ones, please refer to [Tutorial - Step - GeneratorStep](../../sections/how_to_guides/basic/step/generator_step.md).
 
 ::: distilabel.steps.base.GeneratorStep
diff --git a/docs/api/step/global_step.md b/docs/api/step/global_step.md
@@ -2,6 +2,6 @@
 
 This section contains the API reference for the [`GlobalStep`][distilabel.steps.base.GlobalStep] class.
 
-For more information and examples on how to use existing global steps or create custom ones, please refer to [Tutorial - Step - GlobalStep](../../sections/learn/tutorial/step/global_step.md).
+For more information and examples on how to use existing global steps or create custom ones, please refer to [Tutorial - Step - GlobalStep](../../sections/how_to_guides/basic/step/global_step.md).
 
 ::: distilabel.steps.base.GlobalStep
diff --git a/docs/api/step/index.md b/docs/api/step/index.md
@@ -2,7 +2,7 @@
 
 This section contains the API reference for the `distilabel` step, both for the [`_Step`][distilabel.steps.base._Step] base class and the [`Step`][distilabel.steps.Step] class.
 
-For more information and examples on how to use existing steps or create custom ones, please refer to [Tutorial - Step](../../sections/learn/tutorial/step/index.md).
+For more information and examples on how to use existing steps or create custom ones, please refer to [Tutorial - Step](../../sections/how_to_guides/basic/step/index.md).
 
 ::: distilabel.steps.base
     options:

diff --git a/docs/api/step_gallery/columns.md b/docs/api/step_gallery/columns.md
@@ -1,6 +1,6 @@
 # Columns
 
-This section contains the existing steps intended to be used for commong column operations to apply to the batches.
+This section contains the existing steps intended to be used for common column operations to apply to the batches.
 
 ::: distilabel.steps.combine
 ::: distilabel.steps.expand

diff --git a/docs/api/step_gallery/extra.md b/docs/api/step_gallery/extra.md
@@ -1,5 +1,6 @@
 # Extra
 
+::: distilabel.steps.generators.data
 ::: distilabel.steps.deita
 ::: distilabel.steps.formatting
 ::: distilabel.steps.typing
diff --git a/docs/api/step_gallery/hugging_face.md b/docs/api/step_gallery/hugging_face.md
@@ -0,0 +1,7 @@
+# Hugging Face
+
+This section contains the existing steps integrated with `Hugging Face` so as to easily push the generated datasets to Hugging Face.
+
+::: distilabel.steps.LoadDataFromDisk
+::: distilabel.steps.LoadDataFromFileSystem
+::: distilabel.steps.LoadDataFromHub
diff --git a/docs/api/task/generator_task.md b/docs/api/task/generator_task.md
@@ -2,6 +2,6 @@
 
 This section contains the API reference for the `distilabel` generator tasks.
 
-For more information on how the [`GeneratorTask`][distilabel.steps.tasks.GeneratorTask] works and see some examples, check the [Tutorial - Task - GeneratorTask](../../sections/learn/tutorial/task/generator_task.md) page.
+For more information on how the [`GeneratorTask`][distilabel.steps.tasks.GeneratorTask] works and see some examples, check the [Tutorial - Task - GeneratorTask](../../sections/how_to_guides/basic/task/generator_task.md) page.
 
 ::: distilabel.steps.tasks.base.GeneratorTask
diff --git a/docs/api/task/index.md b/docs/api/task/index.md
@@ -2,7 +2,7 @@
 
 This section contains the API reference for the `distilabel` tasks.
 
-For more information on how the [`Task`][distilabel.steps.tasks.Task] works and see some examples, check the [Tutorial - Task](../../sections/learn/tutorial/task/index.md) page.
+For more information on how the [`Task`][distilabel.steps.tasks.Task] works and see some examples, check the [Tutorial - Task](../../sections/how_to_guides/basic/task/index.md) page.
 
 ::: distilabel.steps.tasks.base
     options:

diff --git a/docs/api/task/typing.md b/docs/api/task/typing.md
@@ -0,0 +1,3 @@
+# Task Typing
+
+::: distilabel.steps.tasks.typing
diff --git a/docs/api/task_gallery/index.md b/docs/api/task_gallery/index.md
@@ -9,3 +9,4 @@ This section contains the existing [`Task`][distilabel.steps.tasks.Task] subclas
         - "!_Task"
         - "!GeneratorTask"
         - "!ChatType"
+        - "!typing"
diff --git a/docs/assets/distilabel-badge-light.png b/docs/assets/distilabel-badge-light.png
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,3 @@
		# Task Typing

		::: distilabel.steps.tasks.typing