* fix: set ComponentTool addtionalProperties for OpenAI tools_strict=True
* add reno
* Move the additionalProperties into the OpenAIChatGenerator
* Remove
* Put additionalProperties into the correct place
* Fix test
* Update releasenotes/notes/fix-componenttool-for-openai-tools_strict-998e5cd7ebc6ec19.yaml
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
---------
Co-authored-by: Sebastian Husch Lee <sebastian.lee@deepset.ai>
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
* Starting to refactor type util tests to be more systematic
* refactoring
* Expand tests
* Update to type utils
* Add missing subclass check
* Expand and refactor tests, introduce type_validation Literal
* More test refactoring
* Test refactoring, adding type validation variable to pipeline base
* Update relaxed version of type checking to pass all newly added tests
* trim whitespace
* Add tests
* cleanup
* Updates docstrings
* Add reno
* docs
* Fix mypy and add docstrings
* Changes based on advice from Tobi
* Remove unused imports
* Doc strings
* Add connection type validation to to_dict and from_dict
* Update tests
* Fix test
* Also save connection_type_validation at global pipeline level
* Fix tests
* Remove connection type validation from the connect level, only keep at pipeline level
* Formatting
* Fix tests
* formatting
* Revert "test: skip HF API live integration tests (#8889)"
This reverts commit 56a3a9bd61b7391ae91e3d8179b3b33918ef4932.
* Replace zephyr-7b-beta model with SmolLM2-1.7B-Instruct
* Use zephyr-7b-beta model but extend instructions
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* fix: use is not to compare to sentinel value
* chore: release notes
* Update releasenotes/notes/fix-component-checks-with-ambiguous-truth-values-949c447b3702e427.yaml
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* fix: another sentinel value
* test: also test base class
* add pandas as test dependency
* format
* Trigger CI
* mark test with xfail strict=False
---------
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
Co-authored-by: David S. Batista <dsbatista@gmail.com>
Co-authored-by: anakin87 <stefanofiorucci@gmail.com>
* Look through all streaming chunks for tools calls
* Add reno note
* mypy fixes
* Improve robustness
* Don't concatenate, use the last value
* typing
* Update releasenotes/notes/improve-tool-call-chunk-search-986474e814af17a7.yaml
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* Small refactoring
* isort
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* message conversion function
* hfapi w tools
* right test file + hf_hub version
* release note
* fix for new chatmessage; serialize chat_template
* feedback
* draft
* del HF token in tests
* adaptations
* progress
* fix type
* import sorting
* more control on deserialization
* release note
* improvements
* support name field
* fix chatpromptbuilder test
* Update chat_message.py
---------
Co-authored-by: Daria Fokina <daria.fokina@deepset.ai>
* initial import
* Update haystack/components/generators/openai.py
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
* docs: fixing
* supporting the three use cases: no system prompt, using system prompt defined at init, using system prompt defined at run time
* renaming 'run_time_system_prompt' to 'system_prompt'
* adding tests, converting methods to static
---------
Co-authored-by: Sebastian Husch Lee <sjrl@users.noreply.github.com>
* chaning default model to gpt-4o-mini
* adding release notes
* fixing some missed tests
* fixing some more missed tests
* fixing one last missed test
* fixing linting issues
* making pylint happy about an end2end test
* chaning if test to walruss operator
* fixing azure embedder from ada to text-embedding-ada-002
* Pin structlog to 24.2.0 due to unit test failures
* Remove object init parameter in huggingface_hub unit tests
* Use less restrictive structlog pin
* Add release note
* feat: Configure max_retries & timeout for AzureOpenAIChatGenerator
max_retries: if not set is read from the OPENAI_MAX_RETRIES
env variable or set to 5.
timeout: if not set is read from the OPENAI_TIMEOUT
env variable or set to 30.
Signed-off-by: Nitanshu Vashistha <nitanshu.vzard@gmail.com>
* Update haystack/components/generators/chat/azure.py
* Update haystack/components/generators/chat/azure.py
* Update max_retries-for-AzureOpenAIChatGenerator-9e49b4c7bec5c72b.yaml
---------
Signed-off-by: Nitanshu Vashistha <nitanshu.vzard@gmail.com>
Co-authored-by: David S. Batista <dsbatista@gmail.com>
max_retries: if not set is read from the OPENAI_MAX_RETRIES
env variable or set to 5.
timeout: if not set is read from the OPENAI_TIMEOUT
env variable or set to 30.
Signed-off-by: Nitanshu Vashistha <nitanshu.vzard@gmail.com>
