chroma-haystack 2.0.1__tar.gz → 2.0.3__tar.gz

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/CHANGELOG.md

@@ -1,222 +1,375 @@
 # Changelog
 
+## [integrations/chroma-v2.0.2] - 2025-04-04
+
+
+
+
+### ⚙️ CI
+
+
+- Review testing workflows (#1541)
+
+
+### 🌀 Miscellaneous
+
+
+- Fix: Pin chroma (#1608)
+
+## [integrations/chroma-v3.0.0] - 2025-03-11
+
+
+
+
+### 🧹 Chores
+
+
+- Use Haystack logging across integrations (#1484)
+
+
+### 🌀 Miscellaneous
+
+
+- Fix: Chroma - relax dataframe/blob test (#1404)
+
+- Pin haystack and remove dataframe checks (#1501)
+
+## [integrations/chroma-v2.0.1] - 2025-02-14
+
+
+### 🌀 Miscellaneous
+
+
+
+- Better handle discarded fields (#1373)
+
 ## [integrations/chroma-v1.0.1] - 2025-02-14
 
+
 ### 🧹 Chores
 
+
 - Inherit from `FilterDocumentsTestWithDataframe` in Document Stores (#1290)
 
+
 ### 🌀 Miscellaneous
 
+
+
 - Fix: Chroma - make `filter_documents` method return embeddings (#1361)
 
 ## [integrations/chroma-v2.0.0] - 2025-01-02
 
+
 ### 🧹 Chores
 
+
 - Fix linting/isort (#1215)
+
 - Chroma - pin `tokenizers` (#1223)
 
+
 ### 🌀 Miscellaneous
 
+
+
 - Unpin tokenizers (#1233)
+
 - Fix: updates for Chroma 0.6.0 (#1270)
 
 ## [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)
 
+
 ### ⚙️ CI
 
+
 - Adopt uv as installer (#1142)
 
 
+
 ## [integrations/chroma-v0.22.1] - 2024-09-30
 
+
 ### 🌀 Miscellaneous
 
+
+
 - Empty filters should behave as no filters (#1117)
 
 ## [integrations/chroma-v0.22.0] - 2024-09-30
 
+
 ### 🚀 Features
 
+
 - Chroma - allow remote HTTP connection (#1094)
+
 - Chroma - defer the DB connection (#1107)
 
+
 ### 🐛 Bug Fixes
 
+
 - Refactor: fix chroma linting; do not use numpy (#1063)
+
 - Filters in chroma integration (#1072)
 
+
 ### 🧪 Testing
 
+
 - Do not retry tests in `hatch run test` command (#954)
 
+
 ### 🧹 Chores
 
+
 - Chroma - ruff update, don't ruff tests (#983)
+
 - Update ruff linting scripts and settings (#1105)
 
+
 ### 🌀 Miscellaneous
 
+
+
 - Chore: ChromaDocumentStore lint fix (#1065)
 
 ## [integrations/chroma-v0.21.1] - 2024-07-17
 
+
 ### 🐛 Bug Fixes
 
+
 - `ChromaDocumentStore` - discard `meta` items when the type of their value is not supported in Chroma (#907)
 
 
+
 ## [integrations/chroma-v0.21.0] - 2024-07-16
 
+
 ### 🚀 Features
 
+
 - Add metadata parameter to ChromaDocumentStore. (#906)
 
 
+
 ## [integrations/chroma-v0.20.1] - 2024-07-15
 
+
 ### 🚀 Features
 
+
 - Added distance_function property to ChromadocumentStore (#817)
+
 - Add filter_policy to chroma integration (#826)
 
+
 ### 🐛 Bug Fixes
 
+
 - Allow search in ChromaDocumentStore without metadata (#863)
+
 - `Chroma` - Fallback to default filter policy when deserializing retrievers without the init parameter (#897)
 
+
 ### ⚙️ CI
 
+
 - Retry tests to reduce flakyness (#836)
 
+
 ### 🧹 Chores
 
+
 - Update ruff invocation to include check parameter (#853)
 
+
 ### 🌀 Miscellaneous
 
+
+
 - Ci: install `pytest-rerunfailures` where needed; add retry config to `test-cov` script (#845)
+
 - Chore: Minor retriever pydoc fix (#884)
 
 ## [integrations/chroma-v0.18.0] - 2024-05-31
 
+
 ### 🌀 Miscellaneous
 
+
 - Chore: pin chromadb>=0.5.0 (#777)
 
 ## [integrations/chroma-v0.17.0] - 2024-05-10
 
+
 ### 🌀 Miscellaneous
 
+
 - Chore: change the pydoc renderer class (#718)
+
 - Implement filters for chromaQueryTextRetriever via existing haystack filters logic (#705)
 
 ## [integrations/chroma-v0.16.0] - 2024-05-02
 
+
 ### 📚 Documentation
 
+
 - Small consistency improvements (#536)
+
 - Disable-class-def (#556)
 
+
 ### 🌀 Miscellaneous
 
+
 - Make tests show coverage (#566)
+
 - Refactor tests (#574)
+
 - Remove references to Python 3.7 (#601)
+
 - Make Document Stores initially skip `SparseEmbedding` (#606)
+
 - Pin databind-core (#619)
+
 - Chore: add license classifiers (#680)
+
 - Feature/bump chromadb dep to 0.5.0 (#700)
 
 ## [integrations/chroma-v0.15.0] - 2024-03-01
 
+
 ### 🌀 Miscellaneous
 
+
 - Release chroma on python 3.8 (#512)
 
 ## [integrations/chroma-v0.14.0] - 2024-02-29
 
+
 ### 🐛 Bug Fixes
 
+
 - Fix order of API docs (#447)
+
 - Serialize the path to the local db (#506)
 
+
 ### 📚 Documentation
 
+
 - Update category slug (#442)
+
 - Review chroma integration (#501)
 
+
 ### 🌀 Miscellaneous
 
+
 - Small improvements (#443)
+
 - Fix: make write_documents compatible with the DocumentStore protocol (#505)
 
 ## [integrations/chroma-v0.13.0] - 2024-02-13
 
+
 ### 🌀 Miscellaneous
 
+
 - Chroma: rename retriever (#407)
 
 ## [integrations/chroma-v0.12.0] - 2024-02-06
 
+
 ### 🚀 Features
 
+
 - Generate API docs (#262)
 
+
 ### 🌀 Miscellaneous
 
+
 - Add typing_extensions pin to Chroma integration (#295)
+
 - Allows filters and persistent document stores for Chroma (#342)
 
 ## [integrations/chroma-v0.11.0] - 2024-01-18
 
+
 ### 🐛 Bug Fixes
 
+
 - Chroma DocumentStore creation for pre-existing collection name (#157)
 
+
 ### 🌀 Miscellaneous
 
+
 - Mount chroma integration under `haystack_integrations.*` (#193)
+
 - Remove ChromaSingleQueryRetriever (#240)
 
 ## [integrations/chroma-v0.9.0] - 2023-12-20
 
+
 ### 🐛 Bug Fixes
 
+
 - Fix project URLs (#96)
 
+
 ### 🚜 Refactor
 
+
 - Use `hatch_vcs` to manage integrations versioning (#103)
 
+
 ### 🌀 Miscellaneous
 
+
 - Chore: pin chroma version (#104)
+
 - Fix: update to the latest Document format (#127)
 
 ## [integrations/chroma-v0.8.1] - 2023-12-05
 
+
 ### 🐛 Bug Fixes
 
+
 - Document Stores: fix protocol import (#77)
 
 ## [integrations/chroma-v0.8.0] - 2023-12-04
 
+
 ### 🐛 Bug Fixes
 
+
 - Fix license headers
 
+
 ### 🌀 Miscellaneous
 
+
 - Reorganize repository (#62)
+
 - Update import paths (#64)
+
 - Patch chroma filters tests (#67)
+
 - Remove Document Store decorator (#76)
 
 <!-- generated by git-cliff -->

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chroma-haystack
-Version: 2.0.1
+Version: 2.0.3
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/chroma#readme
 Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
 Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/chroma
@@ -13,11 +13,13 @@ Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
 Requires-Python: >=3.9
-Requires-Dist: chromadb>=0.6.0
-Requires-Dist: haystack-ai
+Requires-Dist: chromadb>=1.0.0
+Requires-Dist: haystack-ai>=2.11.0
 Description-Content-Type: text/markdown
 
 # Chroma Document Store for Haystack

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/pyproject.toml

@@ -18,13 +18,12 @@ classifiers = [
   "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",
-  "chromadb>=0.6.0",
-  ]
+dependencies = ["haystack-ai>=2.11.0", "chromadb>=1.0.0"]
 
 [project.urls]
 Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/chroma#readme"
@@ -60,9 +59,6 @@ cov = ["test-cov", "cov-report"]
 cov-retry = ["test-cov-retry", "cov-report"]
 docs = ["pydoc-markdown pydoc/config.yml"]
 
-[[tool.hatch.envs.all.matrix]]
-python = ["3.9", "3.10"]
-
 [tool.hatch.envs.lint]
 installer = "uv"
 detached = true

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/src/haystack_integrations/components/retrievers/chroma/__init__.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from .retriever import ChromaEmbeddingRetriever, ChromaQueryTextRetriever
 
 __all__ = ["ChromaEmbeddingRetriever", "ChromaQueryTextRetriever"]

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/src/haystack_integrations/components/retrievers/chroma/retriever.py

@@ -1,6 +1,7 @@
-# SPDX-FileCopyrightText: 2023-present John Doe <jd@example.com>
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
+
 from typing import Any, Dict, List, Optional, Union
 
 from haystack import Document, component, default_from_dict, default_to_dict

chroma_haystack-2.0.3/src/haystack_integrations/document_stores/chroma/__init__.py

@@ -0,0 +1,7 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+from .document_store import ChromaDocumentStore
+
+__all__ = ["ChromaDocumentStore"]

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/src/haystack_integrations/document_stores/chroma/document_store.py

@@ -1,12 +1,12 @@
-# SPDX-FileCopyrightText: 2023-present John Doe <jd@example.com>
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
-import logging
+
 from typing import Any, Dict, List, Literal, Optional
 
 import chromadb
 from chromadb.api.types import GetResult, QueryResult
-from haystack import default_from_dict, default_to_dict
+from haystack import default_from_dict, default_to_dict, logging
 from haystack.dataclasses import Document
 from haystack.document_stores.types import DuplicatePolicy
 from numpy import ndarray
@@ -117,7 +117,8 @@ class ChromaDocumentStore:
             if "hnsw:space" not in self._metadata:
                 self._metadata["hnsw:space"] = self._distance_function
 
-            if self._collection_name in client.list_collections():
+            existing_collection_names = [c.name for c in client.list_collections()]
+            if self._collection_name in existing_collection_names:
                 self._collection = client.get_collection(self._collection_name, embedding_function=self._embedding_func)
 
                 if self._metadata != self._collection.metadata:
@@ -250,18 +251,16 @@ class ChromaDocumentStore:
             if doc.content is None:
                 logger.warning(
                     "ChromaDocumentStore cannot store documents with `content=None`. "
-                    "Document with id %s will be skipped.",
-                    doc.id,
+                    "Document with id {doc_id} will be skipped.",
+                    doc_id=doc.id,
                 )
                 continue
-            elif (hasattr(doc, "dataframe") and doc.dataframe is not None) or (
-                hasattr(doc, "blob") and doc.blob is not None
-            ):
+            elif hasattr(doc, "blob") and doc.blob is not None:
                 logger.warning(
-                    "Document with id %s contains `dataframe` or `blob` fields. "
-                    "ChromaDocumentStore cannot store `dataframe` or `blob` fields. "
-                    "These fields will be ignored. ",
-                    doc.id,
+                    "Document with id {doc_id} contains the `blob` field. "
+                    "ChromaDocumentStore cannot store `blob` fields. "
+                    "This field will be ignored.",
+                    doc_id=doc.id,
                 )
             data = {"ids": [doc.id], "documents": [doc.content]}
 
@@ -277,11 +276,11 @@ class ChromaDocumentStore:
 
                 if discarded_keys:
                     logger.warning(
-                        "Document %s contains `meta` values of unsupported types for the keys: %s. "
-                        "These items will be discarded. Supported types are: %s.",
-                        doc.id,
-                        ", ".join(discarded_keys),
-                        ", ".join([t.__name__ for t in SUPPORTED_TYPES_FOR_METADATA_VALUES]),
+                        "Document {doc_id} contains `meta` values of unsupported types for the keys: {keys}. "
+                        "These items will be discarded. Supported types are: {types}.",
+                        doc_id=doc.id,
+                        keys=", ".join(discarded_keys),
+                        types=", ".join([t.__name__ for t in SUPPORTED_TYPES_FOR_METADATA_VALUES]),
                     )
 
                 if valid_meta:
@@ -292,10 +291,10 @@ class ChromaDocumentStore:
 
             if hasattr(doc, "sparse_embedding") and doc.sparse_embedding is not None:
                 logger.warning(
-                    "Document %s has the `sparse_embedding` field set,"
-                    "but storing sparse embeddings in Chroma is not currently supported."
+                    "Document {doc_id} has the `sparse_embedding` field set, "
+                    "but storing sparse embeddings in Chroma is not currently supported. "
                     "The `sparse_embedding` field will be ignored.",
-                    doc.id,
+                    doc_id=doc.id,
                 )
 
             self._collection.add(**data)

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/src/haystack_integrations/document_stores/chroma/errors.py

@@ -1,6 +1,7 @@
-# SPDX-FileCopyrightText: 2023-present John Doe <jd@example.com>
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
+
 from haystack.document_stores.errors import DocumentStoreError
 from haystack.errors import FilterError
 

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/src/haystack_integrations/document_stores/chroma/filters.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from collections import defaultdict
 from dataclasses import dataclass
 from typing import Any, Dict, List, Optional

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/src/haystack_integrations/document_stores/chroma/utils.py

@@ -1,6 +1,7 @@
-# SPDX-FileCopyrightText: 2023-present John Doe <jd@example.com>
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
+
 from chromadb.api.types import EmbeddingFunction
 from chromadb.utils.embedding_functions import (
     CohereEmbeddingFunction,

chroma_haystack-2.0.3/tests/__init__.py

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/tests/test_document_store.py

@@ -1,6 +1,7 @@
-# SPDX-FileCopyrightText: 2023-present John Doe <jd@example.com>
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
+
 import logging
 import operator
 import sys
@@ -237,15 +238,15 @@ class TestDocumentStore(CountDocumentsTest, DeleteDocumentsTest, FilterDocuments
         document_store.write_documents([Document(content=None)])
         assert document_store.filter_documents() == []
 
-    def test_dataframe_and_blob_are_not_stored(self, document_store: ChromaDocumentStore):
+    def test_blob_not_stored(self, document_store: ChromaDocumentStore):
         bs = ByteStream(data=b"test")
         doc_mixed = Document(content="test", blob=bs)
-        doc_mixed.dataframe = "non null content"  # just a placeholder
 
         document_store.write_documents([doc_mixed])
 
-        expected_doc = Document(id=doc_mixed.id, content="test")
-        assert document_store.filter_documents() == [expected_doc]
+        retrieved_doc = document_store.filter_documents()[0]
+        assert retrieved_doc.content == "test"
+        assert retrieved_doc.blob is None
 
     @pytest.mark.integration
     def test_to_dict(self, request):
@@ -347,8 +348,7 @@ class TestDocumentStore(CountDocumentsTest, DeleteDocumentsTest, FilterDocuments
                     "hnsw:M": 103,
                 },
             )
-
-        new_store._ensure_initialized()
+            new_store._ensure_initialized()
 
         assert (
             "Collection already exists. The `distance_function` and `metadata` parameters will be ignored."

{chroma_haystack-2.0.1 → chroma_haystack-2.0.3}/tests/test_retriever.py

@@ -1,6 +1,7 @@
 # SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
+
 import pytest
 from haystack.document_stores.types import FilterPolicy
 

chroma_haystack-2.0.1/src/haystack_integrations/document_stores/chroma/__init__.py

@@ -1,3 +0,0 @@
-from .document_store import ChromaDocumentStore
-
-__all__ = ["ChromaDocumentStore"]

chroma_haystack-2.0.1/tests/__init__.py

@@ -1,3 +0,0 @@
-# SPDX-FileCopyrightText: 2023-present John Doe <jd@example.com>
-#
-# SPDX-License-Identifier: Apache-2.0