Merge branch 'main' into fix-doc-links

Author: davidsbatista

integrations/amazon_bedrock/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## [integrations/amazon_bedrock-v5.3.1] - 2025-12-19
+
+### 🐛 Bug Fixes
+
+- Relax model name validation for Bedrock Embedders (#2625)
+
+
 ## [integrations/amazon_bedrock-v5.3.0] - 2025-12-17
 
 ### 🚀 Features

integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py

@@ -1,5 +1,5 @@
 import json
-from typing import Any, Literal, Optional
+from typing import Any, Optional
 
 from botocore.config import Config
 from botocore.exceptions import ClientError
@@ -16,15 +16,6 @@
 
 logger = logging.getLogger(__name__)
 
-SUPPORTED_EMBEDDING_MODELS = [
-    "amazon.titan-embed-text-v1",
-    "amazon.titan-embed-text-v2:0",
-    "amazon.titan-embed-image-v1",
-    "cohere.embed-english-v3",
-    "cohere.embed-multilingual-v3",
-    "cohere.embed-v4:0",
-]
-
 
 @component
 class AmazonBedrockDocumentEmbedder:
@@ -58,14 +49,7 @@ class AmazonBedrockDocumentEmbedder:
 
     def __init__(
         self,
-        model: Literal[
-            "amazon.titan-embed-text-v1",
-            "amazon.titan-embed-text-v2:0",
-            "amazon.titan-embed-image-v1",
-            "cohere.embed-english-v3",
-            "cohere.embed-multilingual-v3",
-            "cohere.embed-v4:0",
-        ],
+        model: str,
         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
@@ -90,8 +74,13 @@ def __init__(
         constructor. Aside from model, three required parameters are `aws_access_key_id`, `aws_secret_access_key`,
          and `aws_region_name`.
 
-        :param model: The embedding model to use. The model has to be specified in the format outlined in the Amazon
-            Bedrock [documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html).
+        :param model: The embedding model to use.
+            Amazon Titan and Cohere embedding models are supported, for example:
+            "amazon.titan-embed-text-v1", "amazon.titan-embed-text-v2:0", "amazon.titan-embed-image-v1",
+            "cohere.embed-english-v3", "cohere.embed-multilingual-v3", "cohere.embed-v4:0".
+            To find all supported models, refer to the Amazon Bedrock
+            [documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) and
+            filter for "embedding", then select models from the Amazon Titan and Cohere series.
         :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.
@@ -109,11 +98,8 @@ def __init__(
         :raises ValueError: If the model is not supported.
         :raises AmazonBedrockConfigurationError: If the AWS environment is not configured correctly.
         """
-
-        if not model or model not in SUPPORTED_EMBEDDING_MODELS:
-            msg = "Please provide a valid model from the list of supported models: " + ", ".join(
-                SUPPORTED_EMBEDDING_MODELS
-            )
+        if "titan" not in model and "cohere" not in model:
+            msg = f"Model {model} is not supported. Only Amazon Titan and Cohere embedding models are supported."
             raise ValueError(msg)
 
         self.model = model
@@ -254,7 +240,7 @@ def run(self, documents: list[Document]) -> dict[str, list[Document]]:
         elif "titan" in self.model:
             documents_with_embeddings = self._embed_titan(documents=documents)
         else:
-            msg = f"Model {self.model} is not supported. Supported models are: {', '.join(SUPPORTED_EMBEDDING_MODELS)}."
+            msg = f"Model {self.model} is not supported. Only Amazon Titan and Cohere embedding models are supported."
             raise ValueError(msg)
 
         return {"documents": documents_with_embeddings}

integrations/amazon_bedrock/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, Literal, Optional
+from typing import Any, Optional
 
 from botocore.config import Config
 from botocore.exceptions import ClientError
@@ -27,13 +27,6 @@
 
 logger = logging.getLogger(__name__)
 
-SUPPORTED_EMBEDDING_MODELS = [
-    "amazon.titan-embed-image-v1",
-    "cohere.embed-english-v3",
-    "cohere.embed-multilingual-v3",
-    "cohere.embed-v4:0",
-]
-
 
 @component
 class AmazonBedrockDocumentImageEmbedder:
@@ -74,12 +67,7 @@ class AmazonBedrockDocumentImageEmbedder:
     def __init__(
         self,
         *,
-        model: Literal[
-            "amazon.titan-embed-image-v1",
-            "cohere.embed-english-v3",
-            "cohere.embed-multilingual-v3",
-            "cohere.embed-v4:0",
-        ],
+        model: str,
         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
@@ -97,13 +85,13 @@ def __init__(
         """
         Creates a AmazonBedrockDocumentImageEmbedder component.
 
-        :param model:
-            The Bedrock model to use for calculating embeddings. Pass a valid model ID.
-            Supported models:
-            - "amazon.titan-embed-image-v1"
-            - "cohere.embed-english-v3"
-            - "cohere.embed-multilingual-v3"
-            - "cohere.embed-v4:0"
+        :param model: The embedding model to use.
+            Amazon Titan and Cohere multimodal embedding models are supported, for example:
+            "amazon.titan-embed-image-v1", "cohere.embed-english-v3", "cohere.embed-multilingual-v3",
+            "cohere.embed-v4:0".
+            To find all supported models, refer to the Amazon Bedrock
+            [documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) and
+            filter for "embedding", then select multimodal models from the Amazon Titan and Cohere series.
         :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.
@@ -125,9 +113,10 @@ def __init__(
         :raises ValueError: If the model is not supported.
         :raises AmazonBedrockConfigurationError: If the AWS environment is not configured correctly.
         """
-        if not model or model not in SUPPORTED_EMBEDDING_MODELS:
-            msg = "Please provide a valid model from the list of supported models: " + ", ".join(
-                SUPPORTED_EMBEDDING_MODELS
+        if "titan" not in model and "cohere" not in model:
+            msg = (
+                f"Model {model} is not supported. "
+                "Only Amazon Titan and Cohere multimodal embedding models are supported."
             )
             raise ValueError(msg)
 
@@ -291,7 +280,10 @@ def run(self, documents: list[Document]) -> dict[str, list[Document]]:
         elif "titan" in self.model:
             embeddings = self._embed_titan(images=images_to_embed)
         else:
-            msg = f"Model {self.model} is not supported. Supported models are: {', '.join(SUPPORTED_EMBEDDING_MODELS)}."
+            msg = (
+                f"Model {self.model} is not supported. "
+                "Only Amazon Titan and Cohere multimodal embedding models are supported."
+            )
             raise ValueError(msg)
 
         docs_with_embeddings = []

integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/text_embedder.py

@@ -1,5 +1,5 @@
 import json
-from typing import Any, Literal, Optional
+from typing import Any, Optional
 
 from botocore.config import Config
 from botocore.exceptions import ClientError
@@ -14,15 +14,6 @@
 
 logger = logging.getLogger(__name__)
 
-SUPPORTED_EMBEDDING_MODELS = [
-    "amazon.titan-embed-text-v1",
-    "amazon.titan-embed-text-v2:0",
-    "amazon.titan-embed-image-v1",
-    "cohere.embed-english-v3",
-    "cohere.embed-multilingual-v3",
-    "cohere.embed-v4:0",
-]
-
 
 @component
 class AmazonBedrockTextEmbedder:
@@ -51,14 +42,7 @@ class AmazonBedrockTextEmbedder:
 
     def __init__(
         self,
-        model: Literal[
-            "amazon.titan-embed-text-v1",
-            "amazon.titan-embed-text-v2:0",
-            "amazon.titan-embed-image-v1",
-            "cohere.embed-english-v3",
-            "cohere.embed-multilingual-v3",
-            "cohere.embed-v4:0",
-        ],
+        model: str,
         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
@@ -79,8 +63,13 @@ def __init__(
         constructor. Aside from model, three required parameters are `aws_access_key_id`, `aws_secret_access_key`,
          and `aws_region_name`.
 
-        :param model: The embedding model to use. The model has to be specified in the format outlined in the Amazon
-            Bedrock [documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html).
+        :param model: The embedding model to use.
+            Amazon Titan and Cohere embedding models are supported, for example:
+            "amazon.titan-embed-text-v1", "amazon.titan-embed-text-v2:0", "amazon.titan-embed-image-v1",
+            "cohere.embed-english-v3", "cohere.embed-multilingual-v3", "cohere.embed-v4:0".
+            To find all supported models, refer to the Amazon Bedrock
+            [documentation](https://docs.aws.amazon.com/bedrock/latest/userguide/models-supported.html) and
+            filter for "embedding", then select models from the Amazon Titan and Cohere series.
         :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.
@@ -92,10 +81,8 @@ def __init__(
         :raises ValueError: If the model is not supported.
         :raises AmazonBedrockConfigurationError: If the AWS environment is not configured correctly.
         """
-        if not model or model not in SUPPORTED_EMBEDDING_MODELS:
-            msg = "Please provide a valid model from the list of supported models: " + ", ".join(
-                SUPPORTED_EMBEDDING_MODELS
-            )
+        if "titan" not in model and "cohere" not in model:
+            msg = f"Model {model} is not supported. Only Amazon Titan and Cohere embedding models are supported."
             raise ValueError(msg)
 
         self.model = model
@@ -179,7 +166,7 @@ def run(self, text: str) -> dict[str, list[float]]:
         elif "titan" in self.model:
             embedding = response_body["embedding"]
         else:
-            msg = f"Unsupported model {self.model}. Supported models are: {', '.join(SUPPORTED_EMBEDDING_MODELS)}"
+            msg = f"Model {self.model} is not supported. Only Amazon Titan and Cohere embedding models are supported."
             raise ValueError(msg)
 
         return {"embedding": embedding}

integrations/astra/CHANGELOG.md

@@ -1,11 +1,23 @@
 # Changelog
 
-## [integrations/astra-v3.0.1]
+## [integrations/astra-v3.1.0] - 2025-12-30
+
+### 🚀 Features
+
+- Adding `delete_by_filter` and `update_by_filter` (#2631)
+
+
+### ⚙️ CI
+
+- Change pytest command (#2475)
 
 ### 🧹 Chores
 
-- Adopt PEP 585 type hinting
+- Remove Readme API CI workflow and configs (#2573)
+
+### 🌀 Miscellaneous
 
+- Adopt PEP 585 type hinting (part 1) (#2509)
 
 ## [integrations/astra-v3.0.0] - 2025-10-21
 

integrations/astra/src/haystack_integrations/document_stores/astra/astra_client.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2023-present Anant Corporation <support@anant.us>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import json
 from typing import Any, Optional, Union
 from warnings import warn
@@ -356,3 +360,22 @@ def count_documents(self, upper_bound: int = 10000) -> int:
         :returns: the number of documents in the index
         """
         return self._astra_db_collection.count_documents({}, upper_bound=upper_bound)
+
+    def update(
+        self,
+        *,
+        filters: dict[str, Union[str, float, int, bool, list, dict]],
+        update: dict[str, Any],
+    ) -> int:
+        """
+        Update multiple documents in the Astra index that match the filter.
+
+        :param filters: the filter to match documents to update
+        :param update: the update operations to apply (e.g., {"$set": {...}})
+
+        :returns:
+            The number of documents updated
+        """
+        update_result = self._astra_db_collection.update_many(filter=filters, update=update, upsert=False)
+
+        return update_result.update_info["nModified"]

integrations/astra/src/haystack_integrations/document_stores/astra/document_store.py

@@ -1,6 +1,7 @@
 # SPDX-FileCopyrightText: 2023-present Anant Corporation <support@anant.us>
 #
 # SPDX-License-Identifier: Apache-2.0
+
 from typing import Any, Optional, Union
 
 from haystack import default_from_dict, default_to_dict, logging
@@ -400,7 +401,6 @@ def delete_documents(self, document_ids: list[str]) -> None:
         Deletes documents from the document store.
 
         :param document_ids: IDs of the documents to delete.
-        :param delete_all: if `True`, delete all documents.
         :raises MissingDocumentError: if no document was deleted but document IDs were provided.
         """
         if self.index.find_one_document({"filter": {}}) is not None:
@@ -420,7 +420,6 @@ def delete_all_documents(self) -> None:
         """
         Deletes all documents from the document store.
         """
-        deletion_counter = 0
 
         try:
             deletion_counter = self.index.delete_all_documents()
@@ -432,3 +431,59 @@ def delete_all_documents(self) -> None:
             logger.info("All documents deleted")
         else:
             logger.error("Could not delete all documents")
+
+    def delete_by_filter(self, filters: dict[str, Any]) -> int:
+        """
+        Deletes documents that match the provided filters.
+
+        :param filters: The filters to apply to find documents to delete.
+        :returns: The number of documents deleted.
+        :raises AstraDocumentStoreFilterError: if the filter is invalid or not supported.
+        """
+        if not isinstance(filters, dict):
+            msg = "Filters must be a dictionary"
+            raise AstraDocumentStoreFilterError(msg)
+
+        if "id" in filters:
+            filters["_id"] = filters.pop("id")
+
+        converted_filters = _convert_filters(filters)
+        deletion_count = self.index.delete(filters=converted_filters)
+
+        logger.info(f"{deletion_count} documents deleted by filter")
+        return deletion_count
+
+    def update_by_filter(self, filters: dict[str, Any], meta: dict[str, Any]) -> int:
+        """
+        Updates documents that match the provided filters with the given metadata.
+
+        :param filters: The filters to apply to find documents to update.
+        :param meta: The metadata fields to update. This will be merged with existing metadata.
+
+        :returns:
+            The number of documents updated.
+
+        :raises:
+            AstraDocumentStoreFilterError: if the filter is invalid or not supported.
+        """
+        if not isinstance(filters, dict):
+            msg = "Filters must be a dictionary"
+            raise AstraDocumentStoreFilterError(msg)
+
+        if not isinstance(meta, dict):
+            msg = "Meta must be a dictionary"
+            raise AstraDocumentStoreFilterError(msg)
+
+        if "id" in filters:
+            filters["_id"] = filters.pop("id")
+
+        converted_filters = _convert_filters(filters)
+
+        # use dot notation to update nested fields in the meta-object - ensures fields are created if they don't exist
+        update_fields = {f"meta.{key}": value for key, value in meta.items()}
+        update_operation = {"$set": update_fields}
+        update_count = self.index.update(filters=converted_filters, update=update_operation)  # type: ignore
+
+        logger.info(f"{update_count} documents updated by filter")
+
+        return update_count