chroma-haystack 2.0.1__tar.gz → 2.0.2__tar.gz

{chroma_haystack-2.0.1 → chroma_haystack-2.0.2}/CHANGELOG.md

@@ -1,5 +1,22 @@
 # Changelog
 
+## [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

{chroma_haystack-2.0.1 → chroma_haystack-2.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chroma-haystack
-Version: 2.0.1
+Version: 2.0.2
 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,>=0.6.0
+Requires-Dist: haystack-ai>=2.11.0
 Description-Content-Type: text/markdown
 
 # Chroma Document Store for Haystack

{chroma_haystack-2.0.1 → chroma_haystack-2.0.2}/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>=0.6.0,<1"]
 
 [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-2.0.2}/src/haystack_integrations/document_stores/chroma/document_store.py

@@ -1,12 +1,11 @@
 # SPDX-FileCopyrightText: 2023-present John Doe <jd@example.com>
 #
 # 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
@@ -250,18 +249,16 @@ 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 +274,11 @@ 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 +289,10 @@ 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-2.0.2}/tests/test_document_store.py

@@ -237,15 +237,15 @@ 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):