v8.0.0

v8.0.0

Features

• You can now customise the embedding model when creating an index using the DocumentIndexClient.
• You can now use the InstructableEmbed embedding strategy when creating an index using the DocumentIndexClient. See the document_index.ipynb notebook for more information and an example.

Breaking Changes

• The way you configure indexes in the DocumentIndexClient has changed. See the document_index.ipynb notebook for more information.
• The EmbeddingType alias has been renamed to Representation to better align with the underlying API.
• The embedding_type field has been removed from the IndexConfiguration class. You now configure embedding-related parameters via the embedding field.
• You now always need to specify an embedding model when creating an index. Previously, this was always luminous-base.

Full changelog: v7.3.1...v8.0.0

v7.3.1

7.3.1

Features

• Update dependencies

Full changelog: v0.7.3.0...v7.3.1

v7.3.0

7.3.0

(Note: The git tag of this version is incorrect (0.7.3.0). However, the version number in the pyproject.toml is set correctly to 7.3.0)

Features

• Add support for Llama3InstructModel in PromptBasedClassify
• Add TextControl to 'to_instruct_prompt' for instruct models
  • Add 'attention_manipulation_with_text_controls.ipynb' to tutorial notebooks
• Introduced InstructionFinetuningDataHandler to provide methods for storing, retrieving and updating finetuning data samples given an InstructionFinetuningDataRepository. Also has methods for filtered sample retrieval and for dataset formatting.
• Introduced InstructionFinetuningDataRepository for storing and retrieving finetuning samples. Comes in two implementations:
  • PostgresInstructionFinetuningDataRepository to work with data stored in a Postgres database.
  • FileInstructionFinetuningDataRepository to work with data stored in the local file-system.
• Compute precision, recall and f1-score by class in SingleLabelClassifyAggregationLogic
• Add submit_dataset function to StudioClient
  • Add how_to_upload_existing_datasets_to_studio.ipynb to how-tos

Fixes

• Improved some docstring inconsistencies across the codebase and switched the docstring checker to pydoclint.

Full changelog: v7.2.0...v7.3.0

v7.2.0

7.2.0

Features

• Add support for stages and files in Data client.

Fixes

• Update names of pharia-1 models to lowercase, aligning with fresh deployments of the api-scheduler.

Full Changelog: v7.1.0...v7.2.0

v7.1.0

7.1.0

Features

• Add Catalan and Polish support to DetectLanguage.
• Add utility function run_is_already_computed to Runner to check if a run with the given metadata has already been computed.
  • The parameter_optimization notebook describes how to use the run_is_already_computed function.

Fixes

• The default max_retry_time for the LimitedConcurrencyClient is now set to 3 minutes from a day. If you have long-running evaluations that need this, you can re-set a long retry time in the constructor.

Full Changelog: v7.0.0...v7.1.0

v7.0.0

7.0.0

Features

• You can now specify a hybrid_index when creating an index for the document index to use hybrid (semantic and keyword) search.
• min_score and max_results are now optional parameters in DocumentIndexClient.SearchQuery.
• k is now an optional parameter in DocumentIndexRetriever.
• List all indexes of a namespace with DocumentIndexClient.list_indexes.
• Remove an index from a namespace with DocumentIndexClient.delete_index.
• ChatModel now inherits from ControlModel. Although we recommend to use the new chat interface, you can use the Pharia1ChatModel with tasks that rely on ControlModel now.

Fixes

• DocumentIndexClient now properly sets chunk_overlap when creating an index configuration.

Breaking Changes

• The default model for Llama3InstructModel is now llama-3.1-8b-instruct instead of llama-3-8b-instruct. We also removed the llama3.0 models from the recommended models of the Llama3InstructModel.

• The default value of threshold in the DocumentIndexRetriever has changed from 0.5 to 0.0. This accommodates fusion scoring for searches over hybrid indexes.

  Full Changelog: v6.0.0...v7.0.0

v6.0.0

6.0.0

Features

• Remove cap for max_concurrency in LimitedConcurrencyClient.
• Introduce abstract LanguageModel class to integrate with LLMs from any API
  • Every LanguageModel supports echo to retrieve log probs for an expected completion given a prompt
• Introduce abstract ChatModel class to integrate with chat models from any API
  • Introducing Pharia1ChatModel for usage with pharia-1 models.
  • Introducing Llama3ChatModel for usage with llama models.
• Upgrade ArgillaWrapperClient to use Argilla v2.x
• (Beta) Add DataClient and StudioDatasetRepository as connectors to Studio for submitting data.
• Add the optional argument generate_highlights to MultiChunkQa, RetrieverBasedQa and SingleChunkQa. This makes it possible to disable highlighting for performance reasons.

Fixes

• Increase number of returned log_probs in EloQaEvaluationLogic to avoid missing a valid answer

Deprecations

• Removed DefaultArgillaClient
• Deprecated Llama2InstructModel

Breaking Changes

• We needed to upgrade argilla-server image version from argilla-server:v1.26.0 to argilla-server:v1.29.0 to maintain compatibility.

  • Note: We also updated our elasticsearch argilla backend to 8.12.2

  Full Changelog: v5.1.0...v6.0.0

v5.1.0

5.1.0

Features

• Updated DocumentIndexClient with support for metadata filters.
  • Add documentation for filtering to document_index.ipynb.
• Add StudioClient as a connector for submitting traces.
• You can now specify a chunk_overlap when creating an index in the Document Index.
• Add support for monitoring progress in the document index connector when embedding documents.

Fixes

• TaskSpan now properly sets its status to Error on crash.

Deprecations

• Deprecate old Trace Viewer as the new StudioClient replaces it. This affects Tracer.submit_to_trace_viewer.

Full Changelog: v5.0.3...v5.1.0

v5.0.3

5.03.

Fixes

• fix: Corrected docstrings for 'calculate_bleu'-function

Full Changelog: v5.0.2...v5.0.3

5.0.2

Fixes

• Reverted a bug introduced in MultipleChunkRetrieverQa text highlighting.

Full Changelog: v5.0.1...v5.0.2