* Adding support for table Documents when serializing Labels in Haystack
* Fix table label equality test
* Add serialization support and __eq__ support for table answers
* Made convenience functions for converting dataframes. Added some TODOs. Epxanded schema tests for table labels. Updated Multilabel to not convert Dataframes into strings.
* get Answer and Label to_json working with DataFrame
* Fix from_dict method of Label
* Use Dict and remove unneccessary if check
* Using pydantic instead of builtins for type detection
* Update haystack/schema.py
Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
* Update haystack/schema.py
Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
* Update haystack/schema.py
Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
* Separated table label equivalency tests and added pytest.mark.unit
* Added unit test for _dict_factory
* Using more descriptive variable names
* Adding json files to test to_json and from_json functions
* Added sample files for tests
---------
Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
If using the local model in pipeline YAML. The PromptModel cannot select
the HFLocalInvocationLayer, because of the get_task cannot support the
offline model.
*Local model usage:
add the task_name parameter in model_kwargs for local model. for
example text-generation or text2text-generation.
- name: PModel
type: PromptModel
params:
model_name_or_path: /local_model_path
model_kwargs:
task_name: text-generation
- name: Prompter
params:
model_name_or_path: PModel
default_prompt_template: question-answering
type: PromptNode
Signed-off-by: yuanwu <yuan.wu@intel.com>
* fixed test base for hub 0.13.3
* check if test succeed from branch
* 2nd check if test succeed from branch
* removed dependency changes
---------
Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
* Upgrade to transformers 4.28.1
* Commenting out failing piece of test
* trailing-whitespace
* Adjust regex for error match - it changed between releases
* Remove RAG tests failing with transformers update
* Deprecate Seq2SeqGenerator
* changed the warning to include suggestion
* Added example and msg to API reference docs
* Added RAG deprecation
* renamed name to adapt to naming conven
* update docstrings
---------
Co-authored-by: Mayank Jobanputra <mayankjobanputra@gmail.com>
Co-authored-by: Darja Fokina <daria.f93@gmail.com>
* fix recursion of death when deserializing prompttemplate
* add test
* set api_key
* fix test
* add generic test
* work in feedback on tests
---------
Co-authored-by: bogdankostic <bogdankostic@web.de>
* bug: fix load local HF Models in PromptNode pipeline
* Update hugging_face.py
remove duplicate validator
* update: black formatted
* update: update doc string, replace pop with get
* test HFLocalInvocationLayer with local model
* extract elasticsearch
* update pyproject.toml
* make more import optional
* move MockBaseRetriever in conftest
* install es in the es integration tests
* force support for gpt-35-turbo
Cos Tiktoken doesn't support it yet - see https://github.com/openai/tiktoken/pull/72
* Update openai_utils.py
* Appeasing the linting gods
Why hast thou forsaken me ?
* Remove trailing whitespace
* chg: remove redundant elif block
* Starting adding support for TableCell
* Update tests to use row and col
* Added schema test to check to_dict and from_dict works for Table documents. Also updated Doc.__eq__ to work for tables.
* Update eval test to use TableCell
* Added more schema tests for table docs, labels and answers.
* Add boolean to toggle between Span and TableCell
* Add deprecation message
* Test that table answers work as responses in the rest API
---------
Co-authored-by: agnieszka-m <amarzec13@gmail.com>
* clean up the ES instance in a more robust way
* do not sleep, refresh the index instead
* remove client warnings
* fix unit tests
* fix opensearch compatibility
* fix unit tests
* update ES version
* bump elasticsearch-py
* adjust docs
* use recreate_index param
* use same fixture strategy for Opensearch
* Update lg
---------
Co-authored-by: agnieszka-m <amarzec13@gmail.com>
* Added warning messages for documents that are skipped by RouteDocuments. Begun adding support for new option return_remaining and List of List support for metadata value splitting.
* Simplify _split_by_content_type
* Added new unit test and updated _calculate_outgoing_edges
* Added some TODOs and turned assert into raising an error.
* Update logging messages and make new fixture in tests
* Update _split_by_metadata_values to work with return_remaining
* Remove unneeded code
* Documentation
* Add proper support for list of lists
* Fix mypy errors
* Added assert to make mypy happy
* Update haystack/nodes/other/route_documents.py
Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
* PR comments
* Remove check for logging level
* make mypy happy
* Update docstring of metadata_values
* Removed duplicate check. Make explicit check for metadata_values
---------
Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
