amazon-bedrock-haystack 6.0.0__tar.gz → 6.1.0__tar.gz

{amazon_bedrock_haystack-6.0.0 → amazon_bedrock_haystack-6.1.0}/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## [integrations/amazon_bedrock-v6.0.0] - 2026-01-09
+
+### 🧹 Chores
+
+- [**breaking**] Amazon_bedrock - drop Python 3.9 and use X|Y typing (#2685)
+
+
 ## [integrations/amazon_bedrock-v5.4.0] - 2026-01-08
 
 ### 🚀 Features

{amazon_bedrock_haystack-6.0.0 → amazon_bedrock_haystack-6.1.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: amazon-bedrock-haystack
-Version: 6.0.0
+Version: 6.1.0
 Summary: An integration of AWS S3 and Bedrock as a Downloader and Generator components.
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/amazon_bedrock#readme
 Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues

{amazon_bedrock_haystack-6.0.0 → amazon_bedrock_haystack-6.1.0}/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py

@@ -1,4 +1,5 @@
 import json
+from dataclasses import replace
 from typing import Any
 
 from botocore.config import Config
@@ -186,10 +187,11 @@ class AmazonBedrockDocumentEmbedder:
             )
             all_embeddings.extend(embeddings_list)
 
+        new_documents = []
         for doc, emb in zip(documents, all_embeddings, strict=True):
-            doc.embedding = emb
+            new_documents.append(replace(doc, embedding=emb))
 
-        return documents
+        return new_documents
 
     def _embed_titan(self, documents: list[Document]) -> list[Document]:
         """
@@ -214,10 +216,11 @@ class AmazonBedrockDocumentEmbedder:
             embedding = response_body["embedding"]
             all_embeddings.append(embedding)
 
+        new_documents = []
         for doc, emb in zip(documents, all_embeddings, strict=True):
-            doc.embedding = emb
+            new_documents.append(replace(doc, embedding=emb))
 
-        return documents
+        return new_documents
 
     @component.output_types(documents=list[Document])
     def run(self, documents: list[Document]) -> dict[str, list[Document]]:

{amazon_bedrock_haystack-6.0.0 → amazon_bedrock_haystack-6.1.0}/src/haystack_integrations/components/rankers/amazon_bedrock/ranker.py

@@ -1,3 +1,4 @@
+from dataclasses import replace
 from typing import Any
 
 from botocore.exceptions import ClientError
@@ -251,8 +252,7 @@ class AmazonBedrockRanker:
                 idx = result["index"]
                 score = result["relevanceScore"]
                 doc = documents[idx]
-                doc.score = score
-                sorted_docs.append(doc)
+                sorted_docs.append(replace(doc, score=score))
 
             return {"documents": sorted_docs}
         except ClientError as client_error:

{amazon_bedrock_haystack-6.0.0 → amazon_bedrock_haystack-6.1.0}/tests/test_document_embedder.py

@@ -257,6 +257,74 @@ class TestAmazonBedrockDocumentEmbedder:
             assert doc.content == docs[i].content
             assert doc.embedding == [0.1, 0.2, 0.3]
 
+    def test_run_cohere_does_not_modify_original_documents(self, mock_boto3_session):
+        embedder = AmazonBedrockDocumentEmbedder(model="cohere.embed-english-v3")
+
+        original_docs = [
+            Document(content="test 1", id="doc1"),
+            Document(content="test 2", id="doc2"),
+        ]
+
+        # Store original IDs to verify they're the same objects
+        original_doc_ids = [id(doc) for doc in original_docs]
+        original_embeddings = [doc.embedding for doc in original_docs]
+
+        with patch.object(embedder, "_client") as mock_client:
+            mock_client.invoke_model.return_value = {
+                "body": io.StringIO('{"embeddings": [[0.1, 0.2], [0.3, 0.4]]}'),
+            }
+
+            result = embedder.run(documents=original_docs)
+
+        # Verify originals are unchanged
+        assert all(doc.embedding is None for doc in original_docs)
+        assert original_embeddings == [None, None]
+
+        # Verify returned documents are NEW instances
+        returned_doc_ids = [id(doc) for doc in result["documents"]]
+        assert original_doc_ids != returned_doc_ids
+
+        # Verify returned documents have embeddings
+        assert result["documents"][0].embedding == [0.1, 0.2]
+        assert result["documents"][1].embedding == [0.3, 0.4]
+        assert result["documents"][0].content == "test 1"
+        assert result["documents"][1].content == "test 2"
+
+    def test_run_titan_does_not_modify_original_documents(self, mock_boto3_session):
+        embedder = AmazonBedrockDocumentEmbedder(model="amazon.titan-embed-text-v1")
+
+        original_docs = [
+            Document(content="test 1", id="doc1"),
+            Document(content="test 2", id="doc2"),
+        ]
+
+        # Store original IDs to verify they're the same objects
+        original_doc_ids = [id(doc) for doc in original_docs]
+        original_embeddings = [doc.embedding for doc in original_docs]
+
+        with patch.object(embedder, "_client") as mock_client:
+            # Titan returns one embedding at a time
+            mock_client.invoke_model.side_effect = [
+                {"body": io.StringIO('{"embedding": [0.1, 0.2]}')},
+                {"body": io.StringIO('{"embedding": [0.3, 0.4]}')},
+            ]
+
+            result = embedder.run(documents=original_docs)
+
+        # Verify originals are unchanged
+        assert all(doc.embedding is None for doc in original_docs)
+        assert original_embeddings == [None, None]
+
+        # Verify returned documents are NEW instances
+        returned_doc_ids = [id(doc) for doc in result["documents"]]
+        assert original_doc_ids != returned_doc_ids
+
+        # Verify returned documents have embeddings
+        assert result["documents"][0].embedding == [0.1, 0.2]
+        assert result["documents"][1].embedding == [0.3, 0.4]
+        assert result["documents"][0].content == "test 1"
+        assert result["documents"][1].content == "test 2"
+
     @pytest.mark.integration
     @pytest.mark.skipif(
         not os.getenv("AWS_ACCESS_KEY_ID")