feat: 985 feature argillalabeller task (#986)

* feat: add initial version of argilla labeller task

* fix: arguments in runtime parameters

* feat: add field descriptions

* feat: Update record formatting logic during structured generation

* feat: update workflows

* refactor: work based off server payloads

* fix: resolve serializatione xample records

* fix: only convert examples w when provided

* fix: set to basically zero

* fix: add temperature fix

* fix: revert changes

* fix: example records with formatted responses

* fix: set max new tokens manually

* fix: some fixes in formatting

* refactor: some code quality improvements

* feat: improv

* refactor: remove unused code

* fix: wrong prompt template

* fix: remove print statement

* fix: added pydantic rtuntimeparameter definition

* fix: creating new characters per line examples

* fix: add nuance on example in prompt template

* feat: Add guidelines to prompt template

* fix: remove pdb trace

* fix: avoid using records without correct responses

* feat: add ability to forward different questions

* test: add tests for argilla labeller

* fix: wrong docstring

* fix: wrong docstring

* refactor: rename suggestions -> suggestion

* docs: update examples

* tests: remove span question

* docs: update the examples

* Apply suggestions from code review

Co-authored-by: Gabriel Martín Blázquez <[email protected]>

* refactor: apply suggestions code review

* fix: type hinting Record import

* fix: tests

* tests: fix failing tests

---------

Co-authored-by: Gabriel Martín Blázquez <[email protected]>

src/distilabel/llms/openai.py

@@ -667,7 +667,7 @@ def _create_jsonl_row(
         """Creates a JSONL formatted row to be used by the OpenAI Batch API.
 
         Args:
-            inputs: a list of inputs in chat format to generate responses for, optionally
+            input: a list of inputs in chat format to generate responses for, optionally
                 including structured output.
             custom_id: a custom ID to use for the row.
             kwargs: the keyword arguments to use for the generation.

src/distilabel/steps/clustering/text_clustering.py

@@ -223,7 +223,6 @@ def _create_figure(
             inputs: The inputs of the step, as we will extract information from them again.
             label2docs: Map from each label to the list of documents (texts) that belong to that cluster.
             cluster_summaries: The summaries of the clusters, obtained from the LLM.
-            labels: The labels of the clusters (integers representing each predicted class).
         """
         self._logger.info("🖼️ Creating figure for the clusters...")
 

src/distilabel/steps/tasks/__init__.py

@@ -12,6 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+from distilabel.steps.tasks.argilla_labeller import ArgillaLabeller
 from distilabel.steps.tasks.base import GeneratorTask, Task
 from distilabel.steps.tasks.complexity_scorer import ComplexityScorer
 from distilabel.steps.tasks.evol_instruct.base import EvolInstruct
@@ -52,6 +53,7 @@
 __all__ = [
     "GeneratorTask",
     "Task",
+    "ArgillaLabeller",
     "ComplexityScorer",
     "EvolInstruct",
     "EvolComplexity",