From 648793a3724940d8b4a0bbbad9398d7c80a807c1 Mon Sep 17 00:00:00 2001
From: AnesBenmerzoug <anes.benmerzoug@gmail.com>
Date: Wed, 6 Nov 2024 10:19:14 +0100
Subject: [PATCH 1/9] Allow passing boto3 config to AmazonBedrockChatGenerator

---
 .../amazon_bedrock/chat/chat_generator.py          | 14 +++++++++++++-
 .../amazon_bedrock/tests/test_chat_generator.py    |  5 +++++
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py b/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
index 6bb3cc301..44aba9b37 100644
--- a/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
+++ b/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
@@ -3,6 +3,7 @@
 import re
 from typing import Any, Callable, ClassVar, Dict, List, Optional, Type
 
+from botocore.config import Config
 from botocore.exceptions import ClientError
 from haystack import component, default_from_dict, default_to_dict
 from haystack.dataclasses import ChatMessage, StreamingChunk
@@ -77,6 +78,7 @@ def __init__(
         stop_words: Optional[List[str]] = None,
         streaming_callback: Optional[Callable[[StreamingChunk], None]] = None,
         truncate: Optional[bool] = True,
+        boto3_config: Optional[Dict[str, Any]] = None,
     ):
         """
         Initializes the `AmazonBedrockChatGenerator` with the provided parameters. The parameters are passed to the
@@ -110,6 +112,11 @@ def __init__(
           [StreamingChunk](https://docs.haystack.deepset.ai/docs/data-classes#streamingchunk) object and
         switches the streaming mode on.
         :param truncate: Whether to truncate the prompt messages or not.
+        :param boto3_config: The configuration for the boto3 client.
+        
+        :raises ValueError: If the model name is empty or None.
+        :raises AmazonBedrockConfigurationError: If the AWS environment is not configured correctly or the model is
+            not supported.
         """
         if not model:
             msg = "'model' cannot be None or empty string"
@@ -121,6 +128,7 @@ def __init__(
         self.aws_region_name = aws_region_name
         self.aws_profile_name = aws_profile_name
         self.truncate = truncate
+        self.boto3_config = boto3_config
 
         # get the model adapter for the given model
         model_adapter_cls = self.get_model_adapter(model=model)
@@ -141,7 +149,10 @@ def resolve_secret(secret: Optional[Secret]) -> Optional[str]:
                 aws_region_name=resolve_secret(aws_region_name),
                 aws_profile_name=resolve_secret(aws_profile_name),
             )
-            self.client = session.client("bedrock-runtime")
+            config: Optional[Config] = None
+            if self.boto3_config:
+                config = Config(**self.boto3_config)
+            self.client = session.client("bedrock-runtime", config=config)
         except Exception as exception:
             msg = (
                 "Could not connect to Amazon Bedrock. Make sure the AWS environment is configured correctly. "
@@ -256,6 +267,7 @@ def to_dict(self) -> Dict[str, Any]:
             generation_kwargs=self.model_adapter.generation_kwargs,
             streaming_callback=callback_name,
             truncate=self.truncate,
+            boto3_config=self.boto3_config,
         )
 
     @classmethod
diff --git a/integrations/amazon_bedrock/tests/test_chat_generator.py b/integrations/amazon_bedrock/tests/test_chat_generator.py
index 571e03eb2..02b75bab6 100644
--- a/integrations/amazon_bedrock/tests/test_chat_generator.py
+++ b/integrations/amazon_bedrock/tests/test_chat_generator.py
@@ -48,6 +48,7 @@ def test_to_dict(mock_boto3_session):
             "stop_words": [],
             "streaming_callback": "haystack.components.generators.utils.print_streaming_chunk",
             "truncate": True,
+            "boto3_config": None,
         },
     }
 
@@ -71,12 +72,16 @@ def test_from_dict(mock_boto3_session):
                 "generation_kwargs": {"temperature": 0.7},
                 "streaming_callback": "haystack.components.generators.utils.print_streaming_chunk",
                 "truncate": True,
+                "boto3_config": {
+                    "read_timeout": 1000,
+                },
             },
         }
     )
     assert generator.model == "anthropic.claude-v2"
     assert generator.model_adapter.generation_kwargs == {"temperature": 0.7}
     assert generator.streaming_callback == print_streaming_chunk
+    assert generator.boto3_config == {"read_timeout": 1000}
 
 
 def test_default_constructor(mock_boto3_session, set_env_variables):

From fea2ee7cd44932989f5966471b62effe4cb321aa Mon Sep 17 00:00:00 2001
From: AnesBenmerzoug <anes.benmerzoug@gmail.com>
Date: Wed, 6 Nov 2024 10:23:10 +0100
Subject: [PATCH 2/9] Allow passing boto3 config to
 AmazonBedrockDocumentEmbedder

---
 .../embedders/amazon_bedrock/document_embedder.py     | 11 ++++++++++-
 .../amazon_bedrock/tests/test_document_embedder.py    |  5 +++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py b/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py
index 1b8fde124..c4c216e69 100755
--- a/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py
+++ b/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py
@@ -2,6 +2,7 @@
 import logging
 from typing import Any, Dict, List, Literal, Optional
 
+from botocore.config import Config
 from botocore.exceptions import ClientError
 from haystack import component, default_from_dict, default_to_dict
 from haystack.dataclasses import Document
@@ -73,6 +74,7 @@ def __init__(
         progress_bar: bool = True,
         meta_fields_to_embed: Optional[List[str]] = None,
         embedding_separator: str = "\n",
+        boto3_config: Optional[Dict[str, Any]] = None,
         **kwargs,
     ):
         """
@@ -98,6 +100,7 @@ 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 boto3_config: The configuration for the boto3 client.
         :param kwargs: Additional parameters to pass for model inference. For example, `input_type` and `truncate` for
             Cohere models.
         :raises ValueError: If the model is not supported.
@@ -110,6 +113,8 @@ def __init__(
             )
             raise ValueError(msg)
 
+        self.boto3_config = boto3_config
+
         def resolve_secret(secret: Optional[Secret]) -> Optional[str]:
             return secret.resolve_value() if secret else None
 
@@ -121,7 +126,10 @@ def resolve_secret(secret: Optional[Secret]) -> Optional[str]:
                 aws_region_name=resolve_secret(aws_region_name),
                 aws_profile_name=resolve_secret(aws_profile_name),
             )
-            self._client = session.client("bedrock-runtime")
+            config: Optional[Config] = None
+            if self.boto3_config:
+                config = Config(**self.boto3_config)
+            self._client = session.client("bedrock-runtime", config=config)
         except Exception as exception:
             msg = (
                 "Could not connect to Amazon Bedrock. Make sure the AWS environment is configured correctly. "
@@ -269,6 +277,7 @@ def to_dict(self) -> Dict[str, Any]:
             progress_bar=self.progress_bar,
             meta_fields_to_embed=self.meta_fields_to_embed,
             embedding_separator=self.embedding_separator,
+            boto3_config=self.boto3_config,
             **self.kwargs,
         )
 
diff --git a/integrations/amazon_bedrock/tests/test_document_embedder.py b/integrations/amazon_bedrock/tests/test_document_embedder.py
index 9856c97bb..a405a0af6 100644
--- a/integrations/amazon_bedrock/tests/test_document_embedder.py
+++ b/integrations/amazon_bedrock/tests/test_document_embedder.py
@@ -86,6 +86,7 @@ def test_to_dict(self, mock_boto3_session):
                 "progress_bar": True,
                 "meta_fields_to_embed": [],
                 "embedding_separator": "\n",
+                "boto3_config": None,
             },
         }
 
@@ -106,6 +107,9 @@ def test_from_dict(self, mock_boto3_session):
                 "progress_bar": True,
                 "meta_fields_to_embed": [],
                 "embedding_separator": "\n",
+                "boto3_config": {
+                    "read_timeout": 1000,
+                },
             },
         }
 
@@ -117,6 +121,7 @@ def test_from_dict(self, mock_boto3_session):
         assert embedder.progress_bar
         assert embedder.meta_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
+        assert embedder.boto3_config == {"read_timeout": 1000}
 
     def test_init_invalid_model(self):
         with pytest.raises(ValueError):

From c9e6df9790e664671755e3b7ce85665411729f25 Mon Sep 17 00:00:00 2001
From: AnesBenmerzoug <anes.benmerzoug@gmail.com>
Date: Wed, 6 Nov 2024 10:27:31 +0100
Subject: [PATCH 3/9] Allow passing boto3 config to AmazonBedrockTextEmbedder

---
 .../amazon_bedrock/document_embedder.py       | 23 ++++++++--------
 .../embedders/amazon_bedrock/text_embedder.py | 26 ++++++++++++-------
 .../tests/test_text_embedder.py               |  5 ++++
 3 files changed, 33 insertions(+), 21 deletions(-)

diff --git a/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py b/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py
index c4c216e69..9dc8cbcc5 100755
--- a/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py
+++ b/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/document_embedder.py
@@ -113,7 +113,18 @@ def __init__(
             )
             raise ValueError(msg)
 
+        self.model = model
+        self.aws_access_key_id = aws_access_key_id
+        self.aws_secret_access_key = aws_secret_access_key
+        self.aws_session_token = aws_session_token
+        self.aws_region_name = aws_region_name
+        self.aws_profile_name = aws_profile_name
+        self.batch_size = batch_size
+        self.progress_bar = progress_bar
+        self.meta_fields_to_embed = meta_fields_to_embed or []
+        self.embedding_separator = embedding_separator
         self.boto3_config = boto3_config
+        self.kwargs = kwargs
 
         def resolve_secret(secret: Optional[Secret]) -> Optional[str]:
             return secret.resolve_value() if secret else None
@@ -137,18 +148,6 @@ def resolve_secret(secret: Optional[Secret]) -> Optional[str]:
             )
             raise AmazonBedrockConfigurationError(msg) from exception
 
-        self.model = model
-        self.aws_access_key_id = aws_access_key_id
-        self.aws_secret_access_key = aws_secret_access_key
-        self.aws_session_token = aws_session_token
-        self.aws_region_name = aws_region_name
-        self.aws_profile_name = aws_profile_name
-        self.batch_size = batch_size
-        self.progress_bar = progress_bar
-        self.meta_fields_to_embed = meta_fields_to_embed or []
-        self.embedding_separator = embedding_separator
-        self.kwargs = kwargs
-
     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.
diff --git a/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/text_embedder.py b/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/text_embedder.py
index 0cceda92f..0acd51da5 100755
--- a/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/text_embedder.py
+++ b/integrations/amazon_bedrock/src/haystack_integrations/components/embedders/amazon_bedrock/text_embedder.py
@@ -2,6 +2,7 @@
 import logging
 from typing import Any, Dict, List, Literal, Optional
 
+from botocore.config import Config
 from botocore.exceptions import ClientError
 from haystack import component, default_from_dict, default_to_dict
 from haystack.utils.auth import Secret, deserialize_secrets_inplace
@@ -62,6 +63,7 @@ def __init__(
         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,
         **kwargs,
     ):
         """
@@ -81,6 +83,7 @@ def __init__(
         :param aws_session_token: AWS session token.
         :param aws_region_name: AWS region name.
         :param aws_profile_name: AWS profile name.
+        :param boto3_config: The configuration for the boto3 client.
         :param kwargs: Additional parameters to pass for model inference. For example, `input_type` and `truncate` for
             Cohere models.
         :raises ValueError: If the model is not supported.
@@ -92,6 +95,15 @@ def __init__(
             )
             raise ValueError(msg)
 
+        self.model = model
+        self.aws_access_key_id = aws_access_key_id
+        self.aws_secret_access_key = aws_secret_access_key
+        self.aws_session_token = aws_session_token
+        self.aws_region_name = aws_region_name
+        self.aws_profile_name = aws_profile_name
+        self.boto3_config = boto3_config
+        self.kwargs = kwargs
+
         def resolve_secret(secret: Optional[Secret]) -> Optional[str]:
             return secret.resolve_value() if secret else None
 
@@ -103,7 +115,10 @@ def resolve_secret(secret: Optional[Secret]) -> Optional[str]:
                 aws_region_name=resolve_secret(aws_region_name),
                 aws_profile_name=resolve_secret(aws_profile_name),
             )
-            self._client = session.client("bedrock-runtime")
+            config: Optional[Config] = None
+            if self.boto3_config:
+                config = Config(**self.boto3_config)
+            self._client = session.client("bedrock-runtime", config=config)
         except Exception as exception:
             msg = (
                 "Could not connect to Amazon Bedrock. Make sure the AWS environment is configured correctly. "
@@ -111,14 +126,6 @@ def resolve_secret(secret: Optional[Secret]) -> Optional[str]:
             )
             raise AmazonBedrockConfigurationError(msg) from exception
 
-        self.model = model
-        self.aws_access_key_id = aws_access_key_id
-        self.aws_secret_access_key = aws_secret_access_key
-        self.aws_session_token = aws_session_token
-        self.aws_region_name = aws_region_name
-        self.aws_profile_name = aws_profile_name
-        self.kwargs = kwargs
-
     @component.output_types(embedding=List[float])
     def run(self, text: str):
         """Embeds the input text using the Amazon Bedrock model.
@@ -185,6 +192,7 @@ def to_dict(self) -> Dict[str, Any]:
             aws_region_name=self.aws_region_name.to_dict() if self.aws_region_name else None,
             aws_profile_name=self.aws_profile_name.to_dict() if self.aws_profile_name else None,
             model=self.model,
+            boto3_config=self.boto3_config,
             **self.kwargs,
         )
 
diff --git a/integrations/amazon_bedrock/tests/test_text_embedder.py b/integrations/amazon_bedrock/tests/test_text_embedder.py
index 4f4e92448..2518b5c5f 100644
--- a/integrations/amazon_bedrock/tests/test_text_embedder.py
+++ b/integrations/amazon_bedrock/tests/test_text_embedder.py
@@ -59,6 +59,7 @@ def test_to_dict(self, mock_boto3_session):
                 "aws_profile_name": {"type": "env_var", "env_vars": ["AWS_PROFILE"], "strict": False},
                 "model": "cohere.embed-english-v3",
                 "input_type": "search_query",
+                "boto3_config": None,
             },
         }
 
@@ -76,6 +77,9 @@ def test_from_dict(self, mock_boto3_session):
                 "aws_profile_name": {"type": "env_var", "env_vars": ["AWS_PROFILE"], "strict": False},
                 "model": "cohere.embed-english-v3",
                 "input_type": "search_query",
+                "boto3_config": {
+                    "read_timeout": 1000,
+                },
             },
         }
 
@@ -83,6 +87,7 @@ def test_from_dict(self, mock_boto3_session):
 
         assert embedder.model == "cohere.embed-english-v3"
         assert embedder.kwargs == {"input_type": "search_query"}
+        assert embedder.boto3_config == {"read_timeout": 1000}
 
     def test_init_invalid_model(self):
         with pytest.raises(ValueError):

From 8dd906b5f555871a7c4a821724290a56651f06af Mon Sep 17 00:00:00 2001
From: AnesBenmerzoug <anes.benmerzoug@gmail.com>
Date: Wed, 6 Nov 2024 10:54:10 +0100
Subject: [PATCH 4/9] Remove whitespace from blank line

---
 .../components/generators/amazon_bedrock/chat/chat_generator.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py b/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
index 44aba9b37..3abf01069 100644
--- a/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
+++ b/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
@@ -113,7 +113,7 @@ def __init__(
         switches the streaming mode on.
         :param truncate: Whether to truncate the prompt messages or not.
         :param boto3_config: The configuration for the boto3 client.
-        
+
         :raises ValueError: If the model name is empty or None.
         :raises AmazonBedrockConfigurationError: If the AWS environment is not configured correctly or the model is
             not supported.

From e90884248c36af9d003629dec2ac6d3fdbafae91 Mon Sep 17 00:00:00 2001
From: Anes Benmerzoug <anes.benmerzoug@gmail.com>
Date: Wed, 6 Nov 2024 11:12:07 +0100
Subject: [PATCH 5/9] Reorder setting attributes for readability

---
 .../generators/amazon_bedrock/chat/chat_generator.py        | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py b/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
index 3abf01069..6e0012b1a 100644
--- a/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
+++ b/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
@@ -127,9 +127,12 @@ def __init__(
         self.aws_session_token = aws_session_token
         self.aws_region_name = aws_region_name
         self.aws_profile_name = aws_profile_name
+        self.stop_words = stop_words or []
+        self.streaming_callback = streaming_callback
         self.truncate = truncate
         self.boto3_config = boto3_config
 
+
         # get the model adapter for the given model
         model_adapter_cls = self.get_model_adapter(model=model)
         if not model_adapter_cls:
@@ -160,9 +163,6 @@ def resolve_secret(secret: Optional[Secret]) -> Optional[str]:
             )
             raise AmazonBedrockConfigurationError(msg) from exception
 
-        self.stop_words = stop_words or []
-        self.streaming_callback = streaming_callback
-
     @component.output_types(replies=List[ChatMessage])
     def run(
         self,

From 4648f73b89f9065e03239727959d7ba7f09e26e0 Mon Sep 17 00:00:00 2001
From: Anes Benmerzoug <anes.benmerzoug@gmail.com>
Date: Wed, 6 Nov 2024 11:13:38 +0100
Subject: [PATCH 6/9] Remove blank line

---
 .../components/generators/amazon_bedrock/chat/chat_generator.py  | 1 -
 1 file changed, 1 deletion(-)

diff --git a/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py b/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
index 6e0012b1a..183198bce 100644
--- a/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
+++ b/integrations/amazon_bedrock/src/haystack_integrations/components/generators/amazon_bedrock/chat/chat_generator.py
@@ -132,7 +132,6 @@ def __init__(
         self.truncate = truncate
         self.boto3_config = boto3_config
 
-
         # get the model adapter for the given model
         model_adapter_cls = self.get_model_adapter(model=model)
         if not model_adapter_cls:

From 05f04085d4c8575bf59296737f806fa279d82e3b Mon Sep 17 00:00:00 2001
From: Stefano Fiorucci <stefanofiorucci@gmail.com>
Date: Wed, 6 Nov 2024 10:28:00 +0100
Subject: [PATCH 7/9] fix: adapt our implementation to breaking changes in
 Chroma 0.5.17  (#1165)

* fix chroma breaking changes

* improve warning

* better warning
---
 integrations/chroma/pyproject.toml            |  2 +-
 .../document_stores/chroma/document_store.py  |  7 +-
 .../document_stores/chroma/filters.py         |  8 +--
 .../chroma/tests/test_document_store.py       | 65 ++++++++++++++++++-
 4 files changed, 74 insertions(+), 8 deletions(-)

diff --git a/integrations/chroma/pyproject.toml b/integrations/chroma/pyproject.toml
index 7f0943a30..cfe7a606e 100644
--- a/integrations/chroma/pyproject.toml
+++ b/integrations/chroma/pyproject.toml
@@ -22,7 +22,7 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai", "chromadb>=0.5.0", "typing_extensions>=4.8.0"]
+dependencies = ["haystack-ai", "chromadb>=0.5.17", "typing_extensions>=4.8.0"]
 
 [project.urls]
 Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/chroma#readme"
diff --git a/integrations/chroma/src/haystack_integrations/document_stores/chroma/document_store.py b/integrations/chroma/src/haystack_integrations/document_stores/chroma/document_store.py
index 6a83937a4..439e4b144 100644
--- a/integrations/chroma/src/haystack_integrations/document_stores/chroma/document_store.py
+++ b/integrations/chroma/src/haystack_integrations/document_stores/chroma/document_store.py
@@ -248,9 +248,12 @@ def write_documents(self, documents: List[Document], policy: DuplicatePolicy = D
 
             if doc.content is None:
                 logger.warning(
-                    "ChromaDocumentStore can only store the text field of Documents: "
-                    "'array', 'dataframe' and 'blob' will be dropped."
+                    "ChromaDocumentStore cannot store documents with `content=None`. "
+                    "`array`, `dataframe` and `blob` are not supported. "
+                    "Document with id %s will be skipped.",
+                    doc.id,
                 )
+                continue
             data = {"ids": [doc.id], "documents": [doc.content]}
 
             if doc.meta:
diff --git a/integrations/chroma/src/haystack_integrations/document_stores/chroma/filters.py b/integrations/chroma/src/haystack_integrations/document_stores/chroma/filters.py
index 60046b6ad..df49da673 100644
--- a/integrations/chroma/src/haystack_integrations/document_stores/chroma/filters.py
+++ b/integrations/chroma/src/haystack_integrations/document_stores/chroma/filters.py
@@ -1,6 +1,6 @@
 from collections import defaultdict
 from dataclasses import dataclass
-from typing import Any, Dict, List
+from typing import Any, Dict, List, Optional
 
 from chromadb.api.types import validate_where, validate_where_document
 
@@ -34,8 +34,8 @@ class ChromaFilter:
     """
 
     ids: List[str]
-    where: Dict[str, Any]
-    where_document: Dict[str, Any]
+    where: Optional[Dict[str, Any]]
+    where_document: Optional[Dict[str, Any]]
 
 
 def _convert_filters(filters: Dict[str, Any]) -> ChromaFilter:
@@ -80,7 +80,7 @@ def _convert_filters(filters: Dict[str, Any]) -> ChromaFilter:
         msg = f"Invalid '{test_clause}' : {e}"
         raise ChromaDocumentStoreFilterError(msg) from e
 
-    return ChromaFilter(ids=ids, where=where, where_document=where_document)
+    return ChromaFilter(ids=ids, where=where or None, where_document=where_document or None)
 
 
 def _convert_filter_clause(filters: Dict[str, Any]) -> Dict[str, Any]:
diff --git a/integrations/chroma/tests/test_document_store.py b/integrations/chroma/tests/test_document_store.py
index 987f6d8b7..ed815251e 100644
--- a/integrations/chroma/tests/test_document_store.py
+++ b/integrations/chroma/tests/test_document_store.py
@@ -13,9 +13,12 @@
 from chromadb.api.types import Documents, EmbeddingFunction, Embeddings
 from haystack import Document
 from haystack.testing.document_store import (
+    TEST_EMBEDDING_1,
+    TEST_EMBEDDING_2,
     CountDocumentsTest,
     DeleteDocumentsTest,
     FilterDocumentsTest,
+    _random_embeddings,
 )
 
 from haystack_integrations.document_stores.chroma import ChromaDocumentStore
@@ -51,6 +54,67 @@ def document_store(self) -> ChromaDocumentStore:
             get_func.return_value = _TestEmbeddingFunction()
             return ChromaDocumentStore(embedding_function="test_function", collection_name=str(uuid.uuid1()))
 
+    @pytest.fixture
+    def filterable_docs(self) -> List[Document]:
+        """
+        This fixture has been copied from haystack/testing/document_store.py and modified to
+        remove the documents that don't have textual content, as Chroma does not support writing them.
+        """
+        documents = []
+        for i in range(3):
+            documents.append(
+                Document(
+                    content=f"A Foo Document {i}",
+                    meta={
+                        "name": f"name_{i}",
+                        "page": "100",
+                        "chapter": "intro",
+                        "number": 2,
+                        "date": "1969-07-21T20:17:40",
+                    },
+                    embedding=_random_embeddings(768),
+                )
+            )
+            documents.append(
+                Document(
+                    content=f"A Bar Document {i}",
+                    meta={
+                        "name": f"name_{i}",
+                        "page": "123",
+                        "chapter": "abstract",
+                        "number": -2,
+                        "date": "1972-12-11T19:54:58",
+                    },
+                    embedding=_random_embeddings(768),
+                )
+            )
+            documents.append(
+                Document(
+                    content=f"A Foobar Document {i}",
+                    meta={
+                        "name": f"name_{i}",
+                        "page": "90",
+                        "chapter": "conclusion",
+                        "number": -10,
+                        "date": "1989-11-09T17:53:00",
+                    },
+                    embedding=_random_embeddings(768),
+                )
+            )
+            documents.append(
+                Document(
+                    content=f"Document {i} without embedding",
+                    meta={"name": f"name_{i}", "no_embedding": True, "chapter": "conclusion"},
+                )
+            )
+            documents.append(
+                Document(content=f"Doc {i} with zeros emb", meta={"name": "zeros_doc"}, embedding=TEST_EMBEDDING_1)
+            )
+            documents.append(
+                Document(content=f"Doc {i} with ones emb", meta={"name": "ones_doc"}, embedding=TEST_EMBEDDING_2)
+            )
+        return documents
+
     def assert_documents_are_equal(self, received: List[Document], expected: List[Document]):
         """
         Assert that two lists of Documents are equal.
@@ -283,7 +347,6 @@ def test_contains(self, document_store: ChromaDocumentStore, filterable_docs: Li
         )
 
     def test_multiple_contains(self, document_store: ChromaDocumentStore, filterable_docs: List[Document]):
-        filterable_docs = [doc for doc in filterable_docs if doc.content]  # remove documents without content
         document_store.write_documents(filterable_docs)
         filters = {
             "operator": "OR",

From f08beea52686c160edb435568d4ba2fa4ed9c774 Mon Sep 17 00:00:00 2001
From: HaystackBot <accounts@deepset.ai>
Date: Wed, 6 Nov 2024 09:32:25 +0000
Subject: [PATCH 8/9] Update the changelog

---
 integrations/chroma/CHANGELOG.md | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/integrations/chroma/CHANGELOG.md b/integrations/chroma/CHANGELOG.md
index c129d00ae..591c0ec39 100644
--- a/integrations/chroma/CHANGELOG.md
+++ b/integrations/chroma/CHANGELOG.md
@@ -1,5 +1,16 @@
 # Changelog
 
+## [integrations/chroma-v1.0.0] - 2024-11-06
+
+### 🐛 Bug Fixes
+
+- Fixing Chroma tests due `chromadb` update behaviour change (#1148)
+- Adapt our implementation to breaking changes in Chroma 0.5.17  (#1165)
+
+### ⚙️ Miscellaneous Tasks
+
+- Adopt uv as installer (#1142)
+
 ## [integrations/chroma-v0.22.1] - 2024-09-30
 
 ### Chroma

From acad2c098e4e475f51e451341f8918dab90b856b Mon Sep 17 00:00:00 2001
From: Anes Benmerzoug <anes.benmerzoug@gmail.com>
Date: Thu, 14 Nov 2024 02:57:11 +0100
Subject: [PATCH 9/9] Parametrize to_dict and from_dict tests with boto3_config

---
 .../tests/test_chat_generator.py              | 33 ++++++++++++-----
 .../tests/test_document_embedder.py           | 32 +++++++++++++----
 .../amazon_bedrock/tests/test_generator.py    | 36 ++++++++++++++-----
 3 files changed, 77 insertions(+), 24 deletions(-)

diff --git a/integrations/amazon_bedrock/tests/test_chat_generator.py b/integrations/amazon_bedrock/tests/test_chat_generator.py
index 02b75bab6..da783979f 100644
--- a/integrations/amazon_bedrock/tests/test_chat_generator.py
+++ b/integrations/amazon_bedrock/tests/test_chat_generator.py
@@ -1,7 +1,7 @@
 import json
 import logging
 import os
-from typing import Optional, Type
+from typing import Any, Dict, Optional, Type
 from unittest.mock import MagicMock, patch
 
 import pytest
@@ -26,7 +26,16 @@
 ]
 
 
-def test_to_dict(mock_boto3_session):
+@pytest.mark.parametrize(
+    "boto3_config",
+    [
+        None,
+        {
+            "read_timeout": 1000,
+        },
+    ],
+)
+def test_to_dict(mock_boto3_session: Any, boto3_config: Optional[Dict[str, Any]]):
     """
     Test that the to_dict method returns the correct dictionary without aws credentials
     """
@@ -34,6 +43,7 @@ def test_to_dict(mock_boto3_session):
         model="anthropic.claude-v2",
         generation_kwargs={"temperature": 0.7},
         streaming_callback=print_streaming_chunk,
+        boto3_config=boto3_config,
     )
     expected_dict = {
         "type": KLASS,
@@ -48,14 +58,23 @@ def test_to_dict(mock_boto3_session):
             "stop_words": [],
             "streaming_callback": "haystack.components.generators.utils.print_streaming_chunk",
             "truncate": True,
-            "boto3_config": None,
+            "boto3_config": boto3_config,
         },
     }
 
     assert generator.to_dict() == expected_dict
 
 
-def test_from_dict(mock_boto3_session):
+@pytest.mark.parametrize(
+    "boto3_config",
+    [
+        None,
+        {
+            "read_timeout": 1000,
+        },
+    ],
+)
+def test_from_dict(mock_boto3_session: Any, boto3_config: Optional[Dict[str, Any]]):
     """
     Test that the from_dict method returns the correct object
     """
@@ -72,16 +91,14 @@ def test_from_dict(mock_boto3_session):
                 "generation_kwargs": {"temperature": 0.7},
                 "streaming_callback": "haystack.components.generators.utils.print_streaming_chunk",
                 "truncate": True,
-                "boto3_config": {
-                    "read_timeout": 1000,
-                },
+                "boto3_config": boto3_config,
             },
         }
     )
     assert generator.model == "anthropic.claude-v2"
     assert generator.model_adapter.generation_kwargs == {"temperature": 0.7}
     assert generator.streaming_callback == print_streaming_chunk
-    assert generator.boto3_config == {"read_timeout": 1000}
+    assert generator.boto3_config == boto3_config
 
 
 def test_default_constructor(mock_boto3_session, set_env_variables):
diff --git a/integrations/amazon_bedrock/tests/test_document_embedder.py b/integrations/amazon_bedrock/tests/test_document_embedder.py
index a405a0af6..05672e9c7 100644
--- a/integrations/amazon_bedrock/tests/test_document_embedder.py
+++ b/integrations/amazon_bedrock/tests/test_document_embedder.py
@@ -1,4 +1,5 @@
 import io
+from typing import Any, Dict, Optional
 from unittest.mock import patch
 
 import pytest
@@ -66,10 +67,20 @@ def test_connection_error(self, mock_boto3_session):
                 input_type="fake_input_type",
             )
 
-    def test_to_dict(self, mock_boto3_session):
+    @pytest.mark.parametrize(
+        "boto3_config",
+        [
+            None,
+            {
+                "read_timeout": 1000,
+            },
+        ],
+    )
+    def test_to_dict(self, mock_boto3_session: Any, boto3_config: Optional[Dict[str, Any]]):
         embedder = AmazonBedrockDocumentEmbedder(
             model="cohere.embed-english-v3",
             input_type="search_document",
+            boto3_config=boto3_config,
         )
 
         expected_dict = {
@@ -86,13 +97,22 @@ def test_to_dict(self, mock_boto3_session):
                 "progress_bar": True,
                 "meta_fields_to_embed": [],
                 "embedding_separator": "\n",
-                "boto3_config": None,
+                "boto3_config": boto3_config,
             },
         }
 
         assert embedder.to_dict() == expected_dict
 
-    def test_from_dict(self, mock_boto3_session):
+    @pytest.mark.parametrize(
+        "boto3_config",
+        [
+            None,
+            {
+                "read_timeout": 1000,
+            },
+        ],
+    )
+    def test_from_dict(self, mock_boto3_session: Any, boto3_config: Optional[Dict[str, Any]]):
         data = {
             "type": TYPE,
             "init_parameters": {
@@ -107,9 +127,7 @@ def test_from_dict(self, mock_boto3_session):
                 "progress_bar": True,
                 "meta_fields_to_embed": [],
                 "embedding_separator": "\n",
-                "boto3_config": {
-                    "read_timeout": 1000,
-                },
+                "boto3_config": boto3_config,
             },
         }
 
@@ -121,7 +139,7 @@ def test_from_dict(self, mock_boto3_session):
         assert embedder.progress_bar
         assert embedder.meta_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
-        assert embedder.boto3_config == {"read_timeout": 1000}
+        assert embedder.boto3_config == boto3_config
 
     def test_init_invalid_model(self):
         with pytest.raises(ValueError):
diff --git a/integrations/amazon_bedrock/tests/test_generator.py b/integrations/amazon_bedrock/tests/test_generator.py
index be645218e..54b185da5 100644
--- a/integrations/amazon_bedrock/tests/test_generator.py
+++ b/integrations/amazon_bedrock/tests/test_generator.py
@@ -1,4 +1,4 @@
-from typing import Optional, Type
+from typing import Any, Dict, Optional, Type
 from unittest.mock import MagicMock, call, patch
 
 import pytest
@@ -17,11 +17,22 @@
 )
 
 
-def test_to_dict(mock_boto3_session):
+@pytest.mark.parametrize(
+    "boto3_config",
+    [
+        None,
+        {
+            "read_timeout": 1000,
+        },
+    ],
+)
+def test_to_dict(mock_boto3_session: Any, boto3_config: Optional[Dict[str, Any]]):
     """
     Test that the to_dict method returns the correct dictionary without aws credentials
     """
-    generator = AmazonBedrockGenerator(model="anthropic.claude-v2", max_length=99, truncate=False, temperature=10)
+    generator = AmazonBedrockGenerator(
+        model="anthropic.claude-v2", max_length=99, truncate=False, temperature=10, boto3_config=boto3_config
+    )
 
     expected_dict = {
         "type": "haystack_integrations.components.generators.amazon_bedrock.generator.AmazonBedrockGenerator",
@@ -36,14 +47,23 @@ def test_to_dict(mock_boto3_session):
             "truncate": False,
             "temperature": 10,
             "streaming_callback": None,
-            "boto3_config": None,
+            "boto3_config": boto3_config,
         },
     }
 
     assert generator.to_dict() == expected_dict
 
 
-def test_from_dict(mock_boto3_session):
+@pytest.mark.parametrize(
+    "boto3_config",
+    [
+        None,
+        {
+            "read_timeout": 1000,
+        },
+    ],
+)
+def test_from_dict(mock_boto3_session: Any, boto3_config: Optional[Dict[str, Any]]):
     """
     Test that the from_dict method returns the correct object
     """
@@ -58,16 +78,14 @@ def test_from_dict(mock_boto3_session):
                 "aws_profile_name": {"type": "env_var", "env_vars": ["AWS_PROFILE"], "strict": False},
                 "model": "anthropic.claude-v2",
                 "max_length": 99,
-                "boto3_config": {
-                    "read_timeout": 1000,
-                },
+                "boto3_config": boto3_config,
             },
         }
     )
 
     assert generator.max_length == 99
     assert generator.model == "anthropic.claude-v2"
-    assert generator.boto3_config == {"read_timeout": 1000}
+    assert generator.boto3_config == boto3_config
 
 
 def test_default_constructor(mock_boto3_session, set_env_variables):