amazon-bedrock-haystack 5.1.0__tar.gz → 5.3.0__tar.gz

{amazon_bedrock_haystack-5.1.0 → amazon_bedrock_haystack-5.3.0}/CHANGELOG.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## [integrations/amazon_bedrock-v5.2.0] - 2025-10-22
+
+### 🚀 Features
+
+- `AmazonBedrockChatGenerator` update tools param to ToolsType (#2415)
+
+## [integrations/amazon_bedrock-v5.1.0] - 2025-09-29
+
+### 🚀 Features
+
+- S3Downloader - add `s3_key_generation_function` param to customize S3 key generation (#2343)
+
 ## [integrations/amazon_bedrock-v5.0.0] - 2025-09-22
 
 ### 🧹 Chores

{amazon_bedrock_haystack-5.1.0 → amazon_bedrock_haystack-5.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: amazon-bedrock-haystack
-Version: 5.1.0
+Version: 5.3.0
 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
@@ -21,7 +21,7 @@ Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: >=3.9
 Requires-Dist: aioboto3>=14.0.0
 Requires-Dist: boto3>=1.28.57
-Requires-Dist: haystack-ai>=2.17.1
+Requires-Dist: haystack-ai>=2.19.0
 Description-Content-Type: text/markdown
 
 # amazon-bedrock-haystack

amazon_bedrock_haystack-5.3.0/pydoc/config_docusaurus.yml

@@ -0,0 +1,41 @@
+loaders:
+- ignore_when_discovered:
+  - __init__
+  modules:
+  - haystack_integrations.common.amazon_bedrock.errors
+  - haystack_integrations.components.embedders.amazon_bedrock.document_embedder
+  - haystack_integrations.components.embedders.amazon_bedrock.text_embedder
+  - haystack_integrations.components.embedders.amazon_bedrock.document_image_embedder
+  - haystack_integrations.components.generators.amazon_bedrock.generator
+  - haystack_integrations.components.generators.amazon_bedrock.adapters
+  - haystack_integrations.common.amazon_bedrock.errors
+  - haystack_integrations.components.generators.amazon_bedrock.chat.chat_generator
+  - haystack_integrations.components.rankers.amazon_bedrock.ranker
+  - haystack_integrations.components.downloaders.s3.s3_downloader
+  - haystack_integrations.common.s3.utils
+  - haystack_integrations.common.s3.errors
+  search_path:
+  - ../src
+  type: haystack_pydoc_tools.loaders.CustomPythonLoader
+processors:
+- do_not_filter_modules: false
+  documented_only: true
+  expression: null
+  skip_empty_modules: true
+  type: filter
+- expression: name not in ['BedrockRanker']
+  type: filter
+- type: smart
+- type: crossref
+renderer:
+  description: Amazon Bedrock integration for Haystack
+  id: integrations-amazon-bedrock
+  markdown:
+    add_member_class_prefix: false
+    add_method_class_prefix: true
+    classdef_code_block: false
+    descriptive_class_title: false
+    descriptive_module_title: true
+    filename: amazon_bedrock.md
+  title: Amazon Bedrock
+  type: haystack_pydoc_tools.renderers.DocusaurusRenderer

{amazon_bedrock_haystack-5.1.0 → amazon_bedrock_haystack-5.3.0}/pyproject.toml

@@ -23,7 +23,7 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai>=2.17.1", "boto3>=1.28.57", "aioboto3>=14.0.0"]
+dependencies = ["haystack-ai>=2.19.0", "boto3>=1.28.57", "aioboto3>=14.0.0"]
 
 [project.urls]
 Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/amazon_bedrock#readme"
@@ -46,7 +46,7 @@ installer = "uv"
 dependencies = ["haystack-pydoc-tools", "ruff"]
 
 [tool.hatch.envs.default.scripts]
-docs = ["pydoc-markdown pydoc/config.yml"]
+docs = ["pydoc-markdown pydoc/config_docusaurus.yml"]
 fmt = "ruff check --fix {args} && ruff format {args}"
 fmt-check = "ruff check {args} && ruff format --check {args}"
 
@@ -66,7 +66,7 @@ dependencies = [
 unit = 'pytest -m "not integration" {args:tests}'
 integration = 'pytest -m "integration" {args:tests}'
 all = 'pytest {args:tests}'
-cov-retry = 'all --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x'
+cov-retry = 'pytest --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x {args:tests}'
 
 types = """mypy -p haystack_integrations.common.amazon_bedrock \
 -p haystack_integrations.components.embedders.amazon_bedrock \
@@ -92,7 +92,7 @@ module = [
 ignore_missing_imports = true
 
 [tool.ruff]
-target-version = "py38"
+target-version = "py39"
 line-length = 120
 
 [tool.ruff.lint]

{amazon_bedrock_haystack-5.1.0 → amazon_bedrock_haystack-5.3.0}/src/haystack_integrations/components/downloaders/s3/s3_downloader.py

@@ -5,7 +5,7 @@
 import os
 from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path
-from typing import Any, Callable, Dict, List, Optional
+from typing import Any, Callable, Optional
 
 from botocore.config import Config
 from haystack import component, default_from_dict, default_to_dict, logging
@@ -36,9 +36,9 @@ class S3Downloader:
         aws_session_token: Optional[Secret] = Secret.from_env_var("AWS_SESSION_TOKEN", strict=False),  # noqa: B008
         aws_region_name: Optional[Secret] = Secret.from_env_var("AWS_DEFAULT_REGION", strict=False),  # noqa: B008
         aws_profile_name: Optional[Secret] = Secret.from_env_var("AWS_PROFILE", strict=False),  # noqa: B008
-        boto3_config: Optional[Dict[str, Any]] = None,
+        boto3_config: Optional[dict[str, Any]] = None,
         file_root_path: Optional[str] = None,
-        file_extensions: Optional[List[str]] = None,
+        file_extensions: Optional[list[str]] = None,
         file_name_meta_key: str = "file_name",
         max_workers: int = 32,
         max_cache_size: int = 100,
@@ -126,11 +126,11 @@ class S3Downloader:
             self.file_root_path.mkdir(parents=True, exist_ok=True)
             self._storage = S3Storage.from_env(session=self._session, config=self._config)
 
-    @component.output_types(documents=List[Document])
+    @component.output_types(documents=list[Document])
     def run(
         self,
-        documents: List[Document],
-    ) -> Dict[str, List[Document]]:
+        documents: list[Document],
+    ) -> dict[str, list[Document]]:
         """Download files from AWS S3 Buckets to local filesystem.
 
         Return enriched `Document`s with the path of the downloaded file.
@@ -160,7 +160,7 @@ class S3Downloader:
         downloaded_documents = [d for d in iterable if d is not None]
         return {"documents": downloaded_documents}
 
-    def _filter_documents_by_extensions(self, documents: List[Document]) -> List[Document]:
+    def _filter_documents_by_extensions(self, documents: list[Document]) -> list[Document]:
         """Filter documents by file extensions."""
         if not self.file_extensions:
             return documents
@@ -202,7 +202,7 @@ class S3Downloader:
         document.meta["file_path"] = str(file_path)
         return document
 
-    def _cleanup_cache(self, documents: List[Document]) -> None:
+    def _cleanup_cache(self, documents: list[Document]) -> None:
         """
         Remove least-recently-accessed cache files when cache exceeds `max_cache_size`.
 
@@ -224,7 +224,7 @@ class S3Downloader:
                 except Exception as error:
                     logger.warning("Failed to remove cache file at {path} with error: {e}", path=p, e=error)
 
-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
         """Serialize the component to a dictionary."""
 
         s3_key_generation_function_name = (
@@ -247,7 +247,7 @@ class S3Downloader:
         )
 
     @classmethod
-    def from_dict(cls, data: Dict[str, Any]) -> "S3Downloader":
+    def from_dict(cls, data: dict[str, Any]) -> "S3Downloader":
         """
         Deserializes the component from a dictionary.
         :param data:

{amazon_bedrock_haystack-5.1.0 → amazon_bedrock_haystack-5.3.0}/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py

@@ -1,5 +1,5 @@
 import json
-from typing import Any, Dict, List, Literal, Optional
+from typing import Any, Literal, Optional
 
 from botocore.config import Config
 from botocore.exceptions import ClientError
@@ -18,10 +18,11 @@ logger = logging.getLogger(__name__)
 
 SUPPORTED_EMBEDDING_MODELS = [
     "amazon.titan-embed-text-v1",
-    "cohere.embed-english-v3",
-    "cohere.embed-multilingual-v3",
     "amazon.titan-embed-text-v2:0",
     "amazon.titan-embed-image-v1",
+    "cohere.embed-english-v3",
+    "cohere.embed-multilingual-v3",
+    "cohere.embed-v4:0",
 ]
 
 
@@ -59,10 +60,11 @@ class AmazonBedrockDocumentEmbedder:
         self,
         model: Literal[
             "amazon.titan-embed-text-v1",
-            "cohere.embed-english-v3",
-            "cohere.embed-multilingual-v3",
             "amazon.titan-embed-text-v2:0",
             "amazon.titan-embed-image-v1",
+            "cohere.embed-english-v3",
+            "cohere.embed-multilingual-v3",
+            "cohere.embed-v4:0",
         ],
         aws_access_key_id: Optional[Secret] = Secret.from_env_var("AWS_ACCESS_KEY_ID", strict=False),  # noqa: B008
         aws_secret_access_key: Optional[Secret] = Secret.from_env_var(  # noqa: B008
@@ -73,9 +75,9 @@ class AmazonBedrockDocumentEmbedder:
         aws_profile_name: Optional[Secret] = Secret.from_env_var("AWS_PROFILE", strict=False),  # noqa: B008
         batch_size: int = 32,
         progress_bar: bool = True,
-        meta_fields_to_embed: Optional[List[str]] = None,
+        meta_fields_to_embed: Optional[list[str]] = None,
         embedding_separator: str = "\n",
-        boto3_config: Optional[Dict[str, Any]] = None,
+        boto3_config: Optional[dict[str, Any]] = None,
         **kwargs: Any,
     ) -> None:
         """
@@ -149,7 +151,7 @@ class AmazonBedrockDocumentEmbedder:
             )
             raise AmazonBedrockConfigurationError(msg) from exception
 
-    def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:
+    def _prepare_texts_to_embed(self, documents: list[Document]) -> list[str]:
         """
         Prepare the texts to embed by concatenating the Document text with the metadata fields to embed.
         """
@@ -162,7 +164,7 @@ class AmazonBedrockDocumentEmbedder:
             texts_to_embed.append(text_to_embed)
         return texts_to_embed
 
-    def _embed_cohere(self, documents: List[Document]) -> List[Document]:
+    def _embed_cohere(self, documents: list[Document]) -> list[Document]:
         """
         Internal method to embed Documents using Cohere models.
         Batch inference is supported.
@@ -191,15 +193,19 @@ class AmazonBedrockDocumentEmbedder:
                 msg = f"Could not perform inference for Amazon Bedrock model {self.model} due to:\n{exception}"
                 raise AmazonBedrockInferenceError(msg) from exception
 
-            response_body = json.loads(response.get("body").read())
-            all_embeddings.extend(response_body["embeddings"])
+            cohere_embeddings = json.loads(response.get("body").read())["embeddings"]
+            # depending on the model, Cohere returns a dict with the embedding types as keys or a list of lists
+            embeddings_list = (
+                next(iter(cohere_embeddings.values())) if isinstance(cohere_embeddings, dict) else cohere_embeddings
+            )
+            all_embeddings.extend(embeddings_list)
 
         for doc, emb in zip(documents, all_embeddings):
             doc.embedding = emb
 
         return documents
 
-    def _embed_titan(self, documents: List[Document]) -> List[Document]:
+    def _embed_titan(self, documents: list[Document]) -> list[Document]:
         """
         Internal method to embed Documents using Amazon Titan models.
         NOTE: Batch inference is not supported, so embeddings are created one by one.
@@ -227,8 +233,8 @@ class AmazonBedrockDocumentEmbedder:
 
         return documents
 
-    @component.output_types(documents=List[Document])
-    def run(self, documents: List[Document]) -> Dict[str, List[Document]]:
+    @component.output_types(documents=list[Document])
+    def run(self, documents: list[Document]) -> dict[str, list[Document]]:
         """Embed the provided `Document`s using the specified model.
 
         :param documents: The `Document`s to embed.
@@ -253,7 +259,7 @@ class AmazonBedrockDocumentEmbedder:
 
         return {"documents": documents_with_embeddings}
 
-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
         """
         Serializes the component to a dictionary.
 
@@ -277,7 +283,7 @@ class AmazonBedrockDocumentEmbedder:
         )
 
     @classmethod
-    def from_dict(cls, data: Dict[str, Any]) -> "AmazonBedrockDocumentEmbedder":
+    def from_dict(cls, data: dict[str, Any]) -> "AmazonBedrockDocumentEmbedder":
         """
         Deserializes the component from a dictionary.
 

{amazon_bedrock_haystack-5.1.0 → amazon_bedrock_haystack-5.3.0}/src/haystack_integrations/components/embedders/amazon_bedrock/document_image_embedder.py

@@ -4,7 +4,7 @@
 
 import json
 from dataclasses import replace
-from typing import Any, Dict, List, Literal, Optional, Tuple
+from typing import Any, Literal, Optional
 
 from botocore.config import Config
 from botocore.exceptions import ClientError
@@ -27,7 +27,12 @@ from haystack_integrations.common.amazon_bedrock.utils import get_aws_session
 
 logger = logging.getLogger(__name__)
 
-SUPPORTED_EMBEDDING_MODELS = ["amazon.titan-embed-image-v1", "cohere.embed-english-v3", "cohere.embed-multilingual-v3"]
+SUPPORTED_EMBEDDING_MODELS = [
+    "amazon.titan-embed-image-v1",
+    "cohere.embed-english-v3",
+    "cohere.embed-multilingual-v3",
+    "cohere.embed-v4:0",
+]
 
 
 @component
@@ -69,7 +74,12 @@ class AmazonBedrockDocumentImageEmbedder:
     def __init__(
         self,
         *,
-        model: Literal["amazon.titan-embed-image-v1", "cohere.embed-english-v3", "cohere.embed-multilingual-v3"],
+        model: Literal[
+            "amazon.titan-embed-image-v1",
+            "cohere.embed-english-v3",
+            "cohere.embed-multilingual-v3",
+            "cohere.embed-v4:0",
+        ],
         aws_access_key_id: Optional[Secret] = Secret.from_env_var("AWS_ACCESS_KEY_ID", strict=False),  # noqa: B008
         aws_secret_access_key: Optional[Secret] = Secret.from_env_var(  # noqa: B008
             "AWS_SECRET_ACCESS_KEY", strict=False
@@ -79,9 +89,9 @@ class AmazonBedrockDocumentImageEmbedder:
         aws_profile_name: Optional[Secret] = Secret.from_env_var("AWS_PROFILE", strict=False),  # noqa: B008
         file_path_meta_field: str = "file_path",
         root_path: Optional[str] = None,
-        image_size: Optional[Tuple[int, int]] = None,
+        image_size: Optional[tuple[int, int]] = None,
         progress_bar: bool = True,
-        boto3_config: Optional[Dict[str, Any]] = None,
+        boto3_config: Optional[dict[str, Any]] = None,
         **kwargs: Any,
     ) -> None:
         """
@@ -93,6 +103,7 @@ class AmazonBedrockDocumentImageEmbedder:
             - "amazon.titan-embed-image-v1"
             - "cohere.embed-english-v3"
             - "cohere.embed-multilingual-v3"
+            - "cohere.embed-v4:0"
         :param aws_access_key_id: AWS access key ID.
         :param aws_secret_access_key: AWS secret access key.
         :param aws_session_token: AWS session token.
@@ -135,14 +146,14 @@ class AmazonBedrockDocumentImageEmbedder:
         self.kwargs = kwargs
         self.embedding_types = None
 
-        if emmbedding_types := self.kwargs.get("embedding_types"):
-            if len(emmbedding_types) > 1:
+        if embedding_types := self.kwargs.get("embedding_types"):
+            if len(embedding_types) > 1:
                 msg = (
                     "You have provided multiple embedding_types for Cohere model. "
                     "AmazonBedrockDocumentImageEmbedder only supports one embedding_type at a time."
                 )
                 raise ValueError(msg)
-            self.embedding_types = emmbedding_types
+            self.embedding_types = embedding_types
 
         def resolve_secret(secret: Optional[Secret]) -> Optional[str]:
             return secret.resolve_value() if secret else None
@@ -296,7 +307,7 @@ class AmazonBedrockDocumentImageEmbedder:
 
         return {"documents": docs_with_embeddings}
 
-    def _embed_titan(self, images: List[str]) -> List[List[float]]:
+    def _embed_titan(self, images: list[str]) -> list[list[float]]:
         """
         Internal method to embed base64 images using Amazon Titan models.
 
@@ -326,7 +337,7 @@ class AmazonBedrockDocumentImageEmbedder:
 
         return all_embeddings
 
-    def _embed_cohere(self, image_uris: List[str]) -> List[List[float]]:
+    def _embed_cohere(self, image_uris: list[str]) -> list[list[float]]:
         """
         Internal method to embed base64 images using Cohere models.
 
@@ -351,15 +362,13 @@ class AmazonBedrockDocumentImageEmbedder:
                 raise AmazonBedrockInferenceError(msg) from exception
 
             response_body = json.loads(response.get("body").read())
-            embeddings = response_body["embeddings"]
+            cohere_embeddings = response_body["embeddings"]
 
-            # if embedding_types is specified, cohere returns a dict with the embedding types as keys
-            if isinstance(embeddings, dict):
-                for embedding in embeddings.values():
-                    all_embeddings.append(embedding[0])
-            else:
-                # if embedding_types is not specified, cohere returns
-                # a nested list of float embeddings
-                all_embeddings.append(embeddings[0])
+            # depending on the model and embedding_types, Cohere returns a dict with the embedding types as keys
+            # or a list of lists
+            embeddings_list = (
+                next(iter(cohere_embeddings.values())) if isinstance(cohere_embeddings, dict) else cohere_embeddings
+            )
+            all_embeddings.extend(embeddings_list)
 
         return all_embeddings

{amazon_bedrock_haystack-5.1.0 → amazon_bedrock_haystack-5.3.0}/src/haystack_integrations/components/embedders/amazon_bedrock/text_embedder.py

@@ -1,5 +1,5 @@
 import json
-from typing import Any, Dict, List, Literal, Optional
+from typing import Any, Literal, Optional
 
 from botocore.config import Config
 from botocore.exceptions import ClientError
@@ -16,10 +16,11 @@ logger = logging.getLogger(__name__)
 
 SUPPORTED_EMBEDDING_MODELS = [
     "amazon.titan-embed-text-v1",
-    "cohere.embed-english-v3",
-    "cohere.embed-multilingual-v3",
     "amazon.titan-embed-text-v2:0",
     "amazon.titan-embed-image-v1",
+    "cohere.embed-english-v3",
+    "cohere.embed-multilingual-v3",
+    "cohere.embed-v4:0",
 ]
 
 
@@ -52,10 +53,11 @@ class AmazonBedrockTextEmbedder:
         self,
         model: Literal[
             "amazon.titan-embed-text-v1",
-            "cohere.embed-english-v3",
-            "cohere.embed-multilingual-v3",
             "amazon.titan-embed-text-v2:0",
             "amazon.titan-embed-image-v1",
+            "cohere.embed-english-v3",
+            "cohere.embed-multilingual-v3",
+            "cohere.embed-v4:0",
         ],
         aws_access_key_id: Optional[Secret] = Secret.from_env_var("AWS_ACCESS_KEY_ID", strict=False),  # noqa: B008
         aws_secret_access_key: Optional[Secret] = Secret.from_env_var(  # noqa: B008
@@ -64,7 +66,7 @@ class AmazonBedrockTextEmbedder:
         aws_session_token: Optional[Secret] = Secret.from_env_var("AWS_SESSION_TOKEN", strict=False),  # noqa: B008
         aws_region_name: Optional[Secret] = Secret.from_env_var("AWS_DEFAULT_REGION", strict=False),  # noqa: B008
         aws_profile_name: Optional[Secret] = Secret.from_env_var("AWS_PROFILE", strict=False),  # noqa: B008
-        boto3_config: Optional[Dict[str, Any]] = None,
+        boto3_config: Optional[dict[str, Any]] = None,
         **kwargs: Any,
     ) -> None:
         """
@@ -127,8 +129,8 @@ class AmazonBedrockTextEmbedder:
             )
             raise AmazonBedrockConfigurationError(msg) from exception
 
-    @component.output_types(embedding=List[float])
-    def run(self, text: str) -> Dict[str, List[float]]:
+    @component.output_types(embedding=list[float])
+    def run(self, text: str) -> dict[str, list[float]]:
         """Embeds the input text using the Amazon Bedrock model.
 
         :param text: The input text to embed.
@@ -168,7 +170,12 @@ class AmazonBedrockTextEmbedder:
         response_body = json.loads(response.get("body").read())
 
         if "cohere" in self.model:
-            embedding = response_body["embeddings"][0]
+            cohere_embeddings = response_body["embeddings"]
+            # depending on the model, Cohere returns a dict with the embedding types as keys or a list of lists
+            embeddings_list = (
+                next(iter(cohere_embeddings.values())) if isinstance(cohere_embeddings, dict) else cohere_embeddings
+            )
+            embedding = embeddings_list[0]
         elif "titan" in self.model:
             embedding = response_body["embedding"]
         else:
@@ -177,7 +184,7 @@ class AmazonBedrockTextEmbedder:
 
         return {"embedding": embedding}
 
-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
         """
         Serializes the component to a dictionary.
 
@@ -197,7 +204,7 @@ class AmazonBedrockTextEmbedder:
         )
 
     @classmethod
-    def from_dict(cls, data: Dict[str, Any]) -> "AmazonBedrockTextEmbedder":
+    def from_dict(cls, data: dict[str, Any]) -> "AmazonBedrockTextEmbedder":
         """
         Deserializes the component from a dictionary.