* Fixes to setting StreamingChunk.index properly and refactoring tests for conversion
* Make _convert_chat_completion_chunk_to_streaming_chunk a member of OpenAIChatGenerator so we can overwrite it in integrations that inherit from it
* Fixes
* Modify streaming chunk to accept a list of tool call deltas.
* Fix tests
* Fix mypy and update original reno
* Undo change
* Update conversion to return a single streaming chunk
* update to print streaming chunk
* Fix types
* PR comments
* feat: add resource name for Haystack Component Datadog spans
* fest: format resource name
Signed-off-by: Ahmad Zidan <ahmad.zidan@traveloka.com>
* feat: add release notes
Signed-off-by: Ahmad Zidan <ahmad.zidan@traveloka.com>
---------
Signed-off-by: Ahmad Zidan <ahmad.zidan@traveloka.com>
Co-authored-by: Sebastian Husch Lee <10526848+sjrl@users.noreply.github.com>
* Fix serialization of outputs_to_string in Tool and ComponentTool
* Add reno
* Fix mypy, simplify logic
* fix pylint
* Fix test
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* feat: add support for torch xpu device support
* test: xpu based tests ci/cd
* test: add xpu code device support
---------
Co-authored-by: Sebastian Husch Lee <10526848+sjrl@users.noreply.github.com>
Co-authored-by: David S. Batista <dsbatista@gmail.com>
* Refactoring to better align run and run_async and reduce duplicate code
* Docstrings and align run and run_async
* More changes
* add missing type
* Refactor async part a bit
* Fix import error
* Fix mypy
* Fixes and tests
* Add reno
* Change variable name
* Add test and fix for passing streaming_callback to a component tool
* Add unit test
* Remove unused import
* Fix reno
* Start expanding StreamingChunk
* First pass at expanding Streaming Chunk
* Working version!
* Some tweaks and also make ToolInvoker stream a chunk with a finish reason
* Properly update test
* Change to tool_name, remove kw_only since its python 3.10 only and update HuggingFaceAPIChatGenerator to start following new StreamingChunk
* Add reno
* Some cleanup
* Fix unit tests
* Fix mypy and integration test
* Fix pylint
* Start refactoring huggingface local api
* Refactor openai generator and chat generator to reuse util methods
* Did some reorg
* Reusue utility method in HuggingFaceAPI
* Get rid of unneeded default values in tests
* Update conversion of streaming chunks to chat message to not rely on openai dataclass anymore
* Fix tests and loosen check in StreamingChunk post_init
* Fixes
* Fix license header
* Add start and index to HFAPIGenerator
* Fix mypy
* Clean up
* Update haystack/components/generators/utils.py
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
* Update haystack/components/generators/utils.py
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
* Change StreamingChunk.start to only a bool
* PR comments
* Fix unit test
* PR comment
* Fix test
---------
Co-authored-by: Julian Risch <julian.risch@deepset.ai>
* Refactor HFAPI Chat Generator
* Add component info to generators
* Fix type hint
* Add reno
* Fix unit tests
* Remove incorrect dev comment
* Move _convert_streaming_chunks_to_chat_message to utils file
* feat(component.rankers): Add HuggingFace API (text-embeddings-inference for rerank) ranker component
* update test flow & doc loaders
* Support run_async for HuggingFaceAPIRanker
* Add release note for HuggingFace API support in component.rankers
* Add release note for HuggingFace API support in component.rankers
* Add release note for HuggingFace API support in component.rankers
* Add release note for HuggingFace API support in component.rankers
* fix:
1. `hugging_face_api.HuggingFaceAPIRanker` rename to `hugging_face_tei.HuggingFaceAPIRanker`
2. HuggingFaceAPIRanker: use our Secret API for token
3. add the missing modules for `docs/pydoc/config/rankers_api.yml`
4. added function `async_request_with_retry` for `haystack/utils/requests_utils.py` and added unittest on `test/utils/test_requests_utils.py`
4. HuggingFaceAPIRanker: refactor the retry function to support configuration based on attempts and status code.
5. HuggingFaceAPIRanker: refactor the test into unit tests using mocks
* fix(HuggingFaceTEIRanker): change the token check logic to use the resolve_value method.
* fix(format): run `hatch run format`
* fix:
- Force keyword-only arguments in __init__ method by adding *,
- Clarify token docstring that it's not always required
- Copy documents to avoid modifying original objects
- Remove test file from slow workflow
- Add monkeypatch eånvironment variable cleanup in tests
- Fix missing module in rankers_api.yml and sort modules alphabetically
- Remove unnecessary test info from release notes
* fix HuggingFaceTEIRanker：
- "None" of "Optional[Secret]" has no attribute "resolve_value"
- run/run_async: too many parameters
* fix(HuggingFaceTEIRanker) :Revise the docstring of the HuggingFaceTEIRanker, improve the parameter descriptions, ensure consistency and clarity. Add error handling information to enhance the readability of the API response.
* fix：unit test for HuggingFaceTEIRanker raise message
* fix fmt
* minor refinements
* refine release note
---------
Co-authored-by: anakin87 <stefanofiorucci@gmail.com>
* chore: Make the Haystack core "type complete"
For libraries with a `py.typed` marker, it is [recommended][1] to
make all public interfaces "type complete", i.e. to explicitly
annotate all function parameters and return types. Doing so has the
following benefits:
- It maximizes the type information available to users and IDEs.
- It ensures that the argument and return types are the intended ones.
- It sidesteps differences in type inference between the different
type checker implementations.
This change makes a first step towards type completeness by enabling
the Mypy `disallow_incomplete_defs` for the core modules (excluding
`haystack.components.*` and `haystack.testing.*`) and fixing the
resulting errors.
[1]: https://typing.python.org/en/latest/guides/libraries.html#how-much-of-my-library-needs-types
* chore: Add `python_version = 3.9` to Mypy config
This catches type constructs that are only supported in later Python
versions.
* Remove unused import
* try to fix linting
---------
Co-authored-by: Stefano Fiorucci <stefanofiorucci@gmail.com>
* test(extractors): Add unit test for LLMMetadataExtractor with no content
Adds a new unit test `test_run_with_document_content_none` to `TestLLMMetadataExtractor`.
This test verifies that `LLMMetadataExtractor` correctly handles documents where `document.content` is None or an empty string.
It ensures that:
- Such documents are added to the `failed_documents` list.
- The correct error message ("Document has no content, skipping LLM call.") is present in their metadata.
- No actual LLM call is attempted for these documents.
This test provides coverage for the fix that prevents an AttributeError when processing documents with no content.
* chore: update comment to reflect new behavior in _run_on_thread method
* docs: Add release note for LLMMetadataExtractor no content fix
* Update releasenotes/notes/fix-llm-metadata-extractor-no-content-910067ea72094f18.yaml
* Update fix-llm-metadata-extractor-no-content-910067ea72094f18.yaml
---------
Co-authored-by: David S. Batista <dsbatista@gmail.com>
