docs: update docstrings of JinaDocumentEmbedder and JinaTextEmbedder (#…

…1092) * chore: update function doc * chore: polished function doc * chore: polished function doc * chore: update function doc * Update integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py Co-authored-by: Julian Risch <[email protected]> * Update integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py Co-authored-by: Julian Risch <[email protected]> * chore: update function doc * fix: lint issues * chore: update function doc --------- Co-authored-by: Julian Risch <[email protected]>
deepset-ai · Oct 2, 2024 · 60c4d4a · 60c4d4a
1 parent cfacb6b
commit 60c4d4a
Show file tree

Hide file tree

Showing 2 changed files with 20 additions and 0 deletions.
diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/document_embedder.py
@@ -62,6 +62,16 @@ def __init__(
                              to keep the logs clean.
         :param meta_fields_to_embed: List of meta fields that should be embedded along with the Document text.
         :param embedding_separator: Separator used to concatenate the meta fields to the Document text.
+        :param task: The downstream task for which the embeddings will be used.
+            The model will return the optimized embeddings for that task.
+            Check the list of available tasks on [Jina documentation](https://jina.ai/embeddings/).
+        :param dimensions: Number of desired dimension.
+            Smaller dimensions are easier to store and retrieve, with minimal performance impact thanks to MRL.
+        :param late_chunking: A boolean to enable or disable late chunking.
+            Apply the late chunking technique to leverage the model's long-context capabilities for
+            generating contextual chunk embeddings.
+
+            The support of `task` and `late_chunking` parameters is only available for jina-embeddings-v3.
         """
         resolved_api_key = api_key.resolve_value()
 

diff --git a/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py b/integrations/jina/src/haystack_integrations/components/embedders/jina/text_embedder.py
@@ -52,6 +52,16 @@ def __init__(
             Check the list of available models on [Jina documentation](https://jina.ai/embeddings/).
         :param prefix: A string to add to the beginning of each text.
         :param suffix: A string to add to the end of each text.
+        :param task: The downstream task for which the embeddings will be used.
+            The model will return the optimized embeddings for that task.
+            Check the list of available tasks on [Jina documentation](https://jina.ai/embeddings/).
+        :param dimensions: Number of desired dimension.
+            Smaller dimensions are easier to store and retrieve, with minimal performance impact thanks to MRL.
+        :param late_chunking: A boolean to enable or disable late chunking.
+            Apply the late chunking technique to leverage the model's long-context capabilities for
+            generating contextual chunk embeddings.
+
+            The support of `task` and `late_chunking` parameters is only available for jina-embeddings-v3.
         """
 
         resolved_api_key = api_key.resolve_value()