* Generate eval result in separate method
* Adapt benchmarking utils
* Adapt running retriever benchmarks
* Adapt error message
* Raise error if file doesn't exist
* Raise error if path doesn't exist or is a directory
* bump ES version in CI
disable ssl
wait for service to start
set env vars
do not use choco to install ES
re-enable jobs deps
skip test on windows CI because of OOM
allocate more memory for ES
uniform ES installation and use default heap size
skip tests causing OOM
increase job timeout
restore memory limit for ES8
* Use latest elasticsearch version
* HFInferenceEndpointInvocationLayer streaming support
* Small fixes
* Add unit test
* PR feedback
* Alphabetically sort params
* Convert PromptNode tests to HFInferenceEndpointInvocationLayer invoke tests
* Rewrite streaming with sseclient
* More PR updates
* Implement and test _ensure_token_limit
* Further optimize DefaultPromptHandler
* Fix CohereInvocationLayer mistypes
* PR feedback
* Break up unit tests, simplify
* Simplify unit tests even further
* PR feedback on unit test simplification
* Proper code identation under patch context manager
* More unit tests, slight adjustments
* Remove unrelated CohereInvocationLayer change
This reverts commit 82337151e8328d982f738e5da9129ff99350ea0c.
* Revert "Further optimize DefaultPromptHandler"
This reverts commit 606a761b6e3333f27df51a304cfbd1906c806e05.
* lg update
mostly full stops at the end of docstrings
---------
Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
Co-authored-by: Silvano Cerza <silvanocerza@gmail.com>
Co-authored-by: Darja Fokina <daria.f93@gmail.com>
* add generation_kwargs
* add documentation
* enable max_new_tokens customization
* add code formatting
* add unit test
* fix formatting
* test with black
* add a new unit test
* remove doc and update tests
* unpack generation_kwargs
* ix comment
* update unit test
* remove generation_kwargs
* not pass `generation_kwargs`
* update tests
* add max_length
* fix formatting
* revert
* reformatting
* Add support for multi line tool input
* Fix failing agent test, additional test_tools_manager.py tests
* Allow empty tool input, add more tests
* More unit tests
* String formatting
* Small str fix
* Add max_tokens to BaseGenerator params
* Make mypy happy
* Rebase and resolve conflicts
* Fix signature issues
* Update lg
* Add a mocked unit test method
* end-of-file-fixer corrected file
* Convert to unit test
* Mark test as integration
* make the test unit
---------
Co-authored-by: agnieszka-m <amarzec13@gmail.com>
Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
* refactor: make the scope param configurable
the scope parameter is used when authenticating using
AuthClientPassword and AuthClientCredentials
* feat: add support for AuthClientCredentials
add support for authenticating using the OIDC Client Credentials
authentication flow
* feat: add support for AuthBearerToken
Add support for authenticating using OIDC and bearer tokens
* Update lg
* refactor how client is built
Signed-off-by: hsm207 <hsm207@users.noreply.github.com>
* unit test the auth methods
Signed-off-by: hsm207 <hsm207@users.noreply.github.com>
* Update test_weaviate.py
* revert formatting change
* Fix type hints
---------
Signed-off-by: hsm207 <hsm207@users.noreply.github.com>
Co-authored-by: John Doe <johndoe@example.com>
Co-authored-by: agnieszka-m <amarzec13@gmail.com>
Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
* #4320 implemented dynamic max_answers for SquadProcessor, fixed IndexError when max_answers is less than the number of answers in the dataset
* #4320 added two unit tests for dataset_from_dicts testing default and manual max_answers
* apply suggestions from code review
Co-authored-by: bogdankostic <bogdankostic@web.de>
* simplify comment, fix mypy & pylint errors, fix old test
* adjust max_answers to each dataset individually
---------
Co-authored-by: bogdankostic <bogdankostic@web.de>
* fix json serialization
* add missing markers
* pylint
* fix decoder bug
* pylint
* add some more tests
* linting & windows
* windows
* windows
* windows paths again
* Add step to loook up tokenizers by prefix in openai_utils
* Updated tiktoken min version + openai_utils test
* Added test case for GPT-4 and Azure model naming
* Broken down tests
* Added default case
---------
Co-authored-by: ZanSara <sara.zanzottera@deepset.ai>
* Updated text_label tests to match tabel_label tests. Also added answer text as part of the Answer.__eq__ comparison.
* Updated text document unit tests to match ones from table docs
* Converting text answer unit tests to match table answer
* Update some document tests
* Minor update
* Separating unit tests
* preserve root_node and add tests
* Added if statement to fix failing tests
---------
Co-authored-by: Silvano Cerza <3314350+silvanocerza@users.noreply.github.com>
Co-authored-by: Sebastian Husch Lee <sjrl423@gmail.com>
* Deprecate name parameter
* Adapt existing tests and uses of PromptTemplate
* Move parameter `name` to end
* Adapt existing tests
* lg update
---------
Co-authored-by: Darja Fokina <daria.f93@gmail.com>
* Add support for dicts to Weaviate
* Add support for _split_overlap to Pinecone
* Add tests
* Fix Pylint
* Fix Pylint
* Fix test
* Implement PR feedback
* Extract ToolsManager, add it to Agent by the composition
* PR feedback Massi
---------
Co-authored-by: Massimiliano Pippi <mpippi@gmail.com>
Co-authored-by: Darja Fokina <daria.f93@gmail.com>
