Skip to content

Commit 33c0680

Browse files
davidsbatistasjrlanakin87
authored
chore: removing EmbedderBasedDocumentsplitter (#426)
* removing EmbedderBasedDocumentsplitter * remove deps * more removals * readd nltk --------- Co-authored-by: Sebastian Husch Lee <10526848+sjrl@users.noreply.github.com> Co-authored-by: anakin87 <stefanofiorucci@gmail.com>
1 parent b91a298 commit 33c0680

6 files changed

Lines changed: 8 additions & 984 deletions

File tree

‎README.md‎

Lines changed: 4 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -43,7 +43,6 @@ that includes it. Once it reaches the end of its lifespan, the experiment will b
4343

4444
| Name | Type | Expected End Date | Dependencies | Cookbook | Discussion |
4545
|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------|-------------------|--------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------|
46-
| [`EmbeddingBasedDocumentSplitter`][8] | EmbeddingBasedDocumentSplitter | August 2025 | None | None | [Discuss][7] |
4746
| [`OpenAIChatGenerator`][9] | Chat Generator Component | November 2025 | None | <a href="https://colab.research.google.com/github/deepset-ai/haystack-cookbook/blob/main/notebooks/hallucination_score_calculator.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> | [Discuss][10] |
4847
| [`MarkdownHeaderLevelInferrer`][15] | Preprocessor | January 2025 | None | None | [Discuss][16] |
4948
| [`Agent`][17]; [Confirmation Policies][18]; [ConfirmationUIs][19]; [ConfirmationStrategies][20]; [`ConfirmationUIResult` and `ToolExecutionDecision`][21] [HITLBreakpointException][22] | Human in the Loop | December 2025 | rich | None | [Discuss][23] |
@@ -54,8 +53,6 @@ that includes it. Once it reaches the end of its lifespan, the experiment will b
5453
[2]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/retrievers/chat_message_retriever.py
5554
[3]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/writers/chat_message_writer.py
5655
[4]: https://github.com/deepset-ai/haystack-experimental/discussions/75
57-
[7]: https://github.com/deepset-ai/haystack-experimental/discussions/356
58-
[8]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/preprocessors/embedding_based_document_splitter.py
5956
[9]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/generators/chat/openai.py
6057
[10]: https://github.com/deepset-ai/haystack-experimental/discussions/361
6158
[15]: https://github.com/deepset-ai/haystack-experimental/blob/main/haystack_experimental/components/preprocessors/md_header_level_inferrer.py
@@ -81,10 +78,10 @@ that includes it. Once it reaches the end of its lifespan, the experiment will b
8178
| `SuperComponent` | Simplify Pipeline development | 0.8.0 |
8279
| `Pipeline` | Pipeline breakpoints for debugging | 0.12.0 |
8380
| `ImageContent`; Image Converters; multimodal support in `OpenAIChatGenerator` and `AmazonBedrockChatGenerator`; `ChatPromptBuilder` refactoring; `SentenceTransformersDocumentImageEmbedder`; `LLMDocumentContentExtractor`; new `Routers` | Multimodality | 0.12.0 |
84-
| `QueryExpander` | Query Expansion Component | 0.14.3 |
85-
| `MultiQueryEmbeddingRetriever` | MultiQueryEmbeddingRetriever | 0.14.3 |
86-
| `MultiQueryTextRetriever` | MultiQueryTextRetriever | 0.14.3 |
87-
81+
| `QueryExpander` | Query Expansion Component | 0.14.3 |
82+
| `MultiQueryEmbeddingRetriever` | MultiQueryEmbeddingRetriever | 0.14.3 |
83+
| `MultiQueryTextRetriever` | MultiQueryTextRetriever | 0.14.3 |
84+
| EmbeddingBasedDocumentSplitter | Document Splitting | 0.15.2 |
8885

8986
### Discontinued experiments
9087

‎haystack_experimental/components/preprocessors/__init__.py‎

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -8,13 +8,11 @@
88
from lazy_imports import LazyImporter
99

1010
_import_structure = {
11-
"embedding_based_document_splitter": ["EmbeddingBasedDocumentSplitter"],
1211
"md_header_level_inferrer": ["MarkdownHeaderLevelInferrer"],
1312
}
1413

1514
if TYPE_CHECKING:
16-
from .embedding_based_document_splitter import EmbeddingBasedDocumentSplitter
17-
from .md_header_level_inferrer import MarkdownHeaderLevelInferrer
15+
from .md_header_level_inferrer import MarkdownHeaderLevelInferrer as MarkdownHeaderLevelInferrer
1816

1917
else:
2018
sys.modules[__name__] = LazyImporter(name=__name__, module_file=__file__, import_structure=_import_structure)

0 commit comments

Comments
 (0)