Merge branch 'main' into bedrock_region_support

Author: SaraCalla

integrations/amazon_bedrock/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## [integrations/amazon_bedrock-v6.1.0] - 2026-01-13
+
+### 🐛 Bug Fixes
+
+- AmazonBedrockDocumentEmbedder to not modify Documents in place (#2174) (#2702)
+
+
 ## [integrations/amazon_bedrock-v6.0.0] - 2026-01-09
 
 ### 🧹 Chores

integrations/amazon_bedrock/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 @@ def _embed_cohere(self, documents: list[Document]) -> list[Document]:
             )
             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 @@ def _embed_titan(self, documents: list[Document]) -> list[Document]:
             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]]:

integrations/amazon_bedrock/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 @@ def resolve_secret(secret: Secret | None) -> str | None:
                 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:

integrations/amazon_bedrock/tests/test_document_embedder.py

@@ -257,6 +257,74 @@ def mock_invoke_model(*args, **kwargs):
             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")

integrations/github/CHANGELOG.md

@@ -1,5 +1,28 @@
 # Changelog
 
+## [integrations/github-v2.0.0] - 2026-01-12
+
+### 📚 Documentation
+
+- Add pydoc configurations for Docusaurus (#2411)
+
+### ⚙️ CI
+
+- Change pytest command (#2475)
+
+### 🧹 Chores
+
+- Remove Readme API CI workflow and configs (#2573)
+- Fix nightly test (#2580)
+- Make fmt command more forgiving (#2671)
+- [**breaking**] Github - drop Python 3.9 and use X|Y typing (#2705)
+
+### 🌀 Miscellaneous
+
+- Adopt PEP 585 type hinting (part 3) (#2510)
+- Chore: Fix tool validation test failures in github integration (#2659)
+- Fix: Fix github integration unit tests (#2703)
+
 ## [integrations/github-v1.2.1] - 2025-10-20
 
 ### 🚀 Features

integrations/github/pyproject.toml

@@ -7,23 +7,22 @@ name = "github-haystack"
 dynamic = ["version"]
 description = 'Haystack components for interacting with GitHub repositories'
 readme = "README.md"
-requires-python = ">=3.9"
+requires-python = ">=3.10"
 license = "Apache-2.0"
 keywords = []
 authors = [{ name = "deepset GmbH", email = "info@deepset.ai" }]
 classifiers = [
   "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
-  "Programming Language :: Python :: 3.9",
   "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Programming Language :: Python :: 3.13",
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai>=2.12.0"]
+dependencies = ["haystack-ai>=2.22.0"]
 
 [project.urls]
 Source = "https://github.com/deepset-ai/haystack-core-integrations/github"
@@ -77,7 +76,6 @@ check_untyped_defs = true
 disallow_incomplete_defs = true
 
 [tool.ruff]
-target-version = "py39"
 line-length = 120
 
 [tool.ruff.lint]
@@ -124,10 +122,6 @@ ignore = [
   "B008",
   "S101",
 ]
-unfixable = [
-  # Don't touch unused imports
-  "F401",
-]
 
 [tool.ruff.lint.isort]
 known-first-party = ["haystack_integrations"]

integrations/github/src/haystack_integrations/components/connectors/github/file_editor.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 from base64 import b64decode, b64encode
 from enum import Enum
-from typing import Any, Optional, Union
+from typing import Any
 
 import requests
 from haystack import component, default_from_dict, default_to_dict, logging
@@ -79,7 +79,7 @@ def __init__(
         self,
         *,
         github_token: Secret = Secret.from_env_var("GITHUB_TOKEN"),
-        repo: Optional[str] = None,
+        repo: str | None = None,
         branch: str = "main",
         raise_on_failure: bool = True,
     ):
@@ -145,7 +145,7 @@ def _update_file(self, owner: str, repo: str, path: str, content: str, message:
     def _check_last_commit(self, owner: str, repo: str, branch: str) -> bool:
         """Check if last commit was made by the current token user."""
         url = f"https://api.github.com/repos/{owner}/{repo}/commits"
-        params: dict[str, Union[str, int]] = {"per_page": 1, "sha": branch}
+        params: dict[str, str | int] = {"per_page": 1, "sha": branch}
         response = requests.get(url, headers=self._get_request_headers(), params=params, timeout=10)
         response.raise_for_status()
         last_commit = response.json()[0]
@@ -191,7 +191,7 @@ def _undo_changes(self, owner: str, repo: str, payload: dict[str, Any], branch:
             commits_url = f"https://api.github.com/repos/{owner}/{repo}/commits"
 
             # Get the previous commit SHA
-            params: dict[str, Union[str, int]] = {"per_page": 2, "sha": branch}
+            params: dict[str, str | int] = {"per_page": 2, "sha": branch}
             commits = requests.get(commits_url, headers=self._get_request_headers(), params=params, timeout=10).json()
             previous_sha = commits[1]["sha"]
 
@@ -244,10 +244,10 @@ def _delete_file(self, owner: str, repo: str, payload: dict[str, str], branch: s
     @component.output_types(result=str)
     def run(
         self,
-        command: Union[Command, str],
+        command: Command | str,
         payload: dict[str, Any],
-        repo: Optional[str] = None,
-        branch: Optional[str] = None,
+        repo: str | None = None,
+        branch: str | None = None,
     ) -> dict[str, str]:
         """
         Process GitHub file operations.

integrations/github/src/haystack_integrations/components/connectors/github/issue_viewer.py

@@ -2,7 +2,7 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 import re
-from typing import Any, Optional
+from typing import Any
 
 import requests
 from haystack import Document, component, default_from_dict, default_to_dict, logging
@@ -37,7 +37,7 @@ class GitHubIssueViewer:
     def __init__(
         self,
         *,
-        github_token: Optional[Secret] = None,
+        github_token: Secret | None = None,
         raise_on_failure: bool = True,
         retry_attempts: int = 2,
     ):

integrations/github/src/haystack_integrations/components/connectors/github/pr_creator.py

@@ -2,7 +2,7 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 import re
-from typing import Any, Optional
+from typing import Any
 
 import requests
 from haystack import component, default_from_dict, default_to_dict, logging
@@ -102,7 +102,7 @@ def _check_fork_exists(self, repo: str, fork_owner: str) -> bool:
         except requests.RequestException:
             return False
 
-    def _create_fork(self, owner: str, repo: str) -> Optional[str]:
+    def _create_fork(self, owner: str, repo: str) -> str | None:
         """Create a fork of the repository."""
         url = f"https://api.github.com/repos/{owner}/{repo}/forks"
         try:

integrations/github/src/haystack_integrations/components/connectors/github/repo_forker.py

@@ -3,7 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 import re
 import time
-from typing import Any, Optional
+from typing import Any
 
 import requests
 from haystack import component, default_from_dict, default_to_dict, logging
@@ -137,7 +137,7 @@ def _get_authenticated_user(self) -> str:
         response.raise_for_status()
         return response.json()["login"]
 
-    def _get_existing_repository(self, repo_name: str) -> Optional[str]:
+    def _get_existing_repository(self, repo_name: str) -> str | None:
         """
         Check if a repository with the given name already exists in the authenticated user's account.