Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: 985 feature argillalabeller task #986

Open
wants to merge 34 commits into
base: develop
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
34 commits
Select commit Hold shift + click to select a range
9c8dacc
feat: add initial version of argilla labeller task
davidberenstein1957 Sep 17, 2024
9d0b8ef
fix: arguments in runtime parameters
davidberenstein1957 Sep 18, 2024
969772c
feat: add field descriptions
davidberenstein1957 Sep 18, 2024
6771a34
feat: Update record formatting logic during structured generation
davidberenstein1957 Sep 19, 2024
3364427
feat: update workflows
davidberenstein1957 Sep 19, 2024
d4d072c
refactor: work based off server payloads
davidberenstein1957 Sep 19, 2024
e34c2be
fix: resolve serializatione xample records
davidberenstein1957 Sep 20, 2024
4884e47
fix: only convert examples w when provided
davidberenstein1957 Sep 20, 2024
974b510
fix: set to basically zero
davidberenstein1957 Sep 20, 2024
9bb65d1
fix: add temperature fix
davidberenstein1957 Sep 20, 2024
806a919
fix: revert changes
davidberenstein1957 Sep 20, 2024
2be5fcc
fix: example records with formatted responses
davidberenstein1957 Sep 20, 2024
2556361
fix: set max new tokens manually
davidberenstein1957 Sep 23, 2024
a98fc80
Merge branch 'develop' into feat/985-feature-argillalabeller-task
davidberenstein1957 Sep 23, 2024
d858db0
fix: some fixes in formatting
davidberenstein1957 Sep 24, 2024
2c3eeb8
refactor: some code quality improvements
davidberenstein1957 Sep 24, 2024
b98f676
feat: improv
davidberenstein1957 Sep 24, 2024
52bc264
refactor: remove unused code
davidberenstein1957 Sep 24, 2024
89b8df1
fix: wrong prompt template
davidberenstein1957 Sep 24, 2024
8ae2fb3
fix: remove print statement
davidberenstein1957 Sep 24, 2024
2f8ef4d
fix: added pydantic rtuntimeparameter definition
davidberenstein1957 Sep 24, 2024
fbd6a57
fix: creating new characters per line examples
davidberenstein1957 Sep 24, 2024
62852b3
fix: add nuance on example in prompt template
davidberenstein1957 Sep 24, 2024
9b2cad7
feat: Add guidelines to prompt template
davidberenstein1957 Sep 24, 2024
46a7441
fix: remove pdb trace
davidberenstein1957 Sep 24, 2024
1a0aaf2
fix: avoid using records without correct responses
davidberenstein1957 Sep 24, 2024
71da8e6
feat: add ability to forward different questions
davidberenstein1957 Sep 26, 2024
9607c47
test: add tests for argilla labeller
davidberenstein1957 Sep 26, 2024
70f2163
fix: wrong docstring
davidberenstein1957 Sep 26, 2024
58d1209
fix: wrong docstring
davidberenstein1957 Sep 26, 2024
eba4f25
refactor: rename suggestions -> suggestion
davidberenstein1957 Sep 26, 2024
0cad68c
docs: update examples
davidberenstein1957 Sep 26, 2024
5925f9a
tests: remove span question
davidberenstein1957 Sep 26, 2024
a2fa85f
docs: update the examples
davidberenstein1957 Sep 26, 2024
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/distilabel/llms/openai.py
Original file line number Diff line number Diff line change
Expand Up @@ -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.
Expand Down
1 change: 0 additions & 1 deletion src/distilabel/steps/clustering/text_clustering.py
Original file line number Diff line number Diff line change
Expand Up @@ -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...")

Expand Down
2 changes: 2 additions & 0 deletions src/distilabel/steps/tasks/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down Expand Up @@ -52,6 +53,7 @@
__all__ = [
"GeneratorTask",
"Task",
"ArgillaLabeller",
"ComplexityScorer",
"EvolInstruct",
"EvolComplexity",
Expand Down
Loading
Loading