chroma-haystack 3.2.0__tar.gz → 3.4.0__tar.gz

{chroma_haystack-3.2.0 → chroma_haystack-3.4.0}/CHANGELOG.md

@@ -1,6 +1,25 @@
 # Changelog
 
-## [integrations/chroma-v3.1.0] - 2025-04-14
+## [integrations/chroma-v3.3.0] - 2025-06-09
+
+### 🚀 Features
+
+- Chroma - fix typing + ship types by adding py.typed files (#1910)
+
+
+## [integrations/chroma-v3.2.0] - 2025-06-06
+
+### 🚀 Features
+
+- Add async support for Chroma + improve typing (#1697)
+
+
+### 🧹 Chores
+
+- Align core-integrations Hatch scripts (#1898)
+
+
+## [integrations/chroma-v2.0.3] - 2025-04-04
 
 ### 🐛 Bug Fixes
 

{chroma_haystack-3.2.0 → chroma_haystack-3.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: chroma-haystack
-Version: 3.2.0
+Version: 3.4.0
 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
@@ -18,34 +18,20 @@ 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>=1.0.0
+Requires-Dist: chromadb>=1.0.2
 Requires-Dist: haystack-ai>=2.11.0
 Description-Content-Type: text/markdown
 
-# Chroma Document Store for Haystack
+# chroma-haystack
 
 [![PyPI - Version](https://img.shields.io/pypi/v/chroma-haystack.svg)](https://pypi.org/project/chroma-haystack)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/chroma-haystack.svg)](https://pypi.org/project/chroma-haystack)
-[![test](https://github.com/masci/chroma-haystack/actions/workflows/test.yml/badge.svg)](https://github.com/masci/chroma-haystack/actions/workflows/test.yml)
 
------
+- [Integration page](https://haystack.deepset.ai/integrations/chroma-documentstore)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/chroma/CHANGELOG.md)
 
-**Table of Contents**
+---
 
-- [Chroma Document Store for Haystack](#chroma-document-store-for-haystack)
-  - [Installation](#installation)
-  - [Examples](#examples)
-  - [License](#license)
+## Contributing
 
-## Installation
-
-```console
-pip install chroma-haystack
-```
-
-## Examples
-You can find a code example showing how to use the Document Store and the Retriever under the `example/` folder of this repo or in [this Colab](https://colab.research.google.com/drive/1YpDetI8BRbObPDEVdfqUcwhEX9UUXP-m?usp=sharing).
-
-## License
-
-`chroma-haystack` is distributed under the terms of the [Apache-2.0](https://spdx.org/licenses/Apache-2.0.html) license.
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

chroma_haystack-3.4.0/README.md

@@ -0,0 +1,13 @@
+# chroma-haystack
+
+[![PyPI - Version](https://img.shields.io/pypi/v/chroma-haystack.svg)](https://pypi.org/project/chroma-haystack)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/chroma-haystack.svg)](https://pypi.org/project/chroma-haystack)
+
+- [Integration page](https://haystack.deepset.ai/integrations/chroma-documentstore)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/chroma/CHANGELOG.md)
+
+---
+
+## Contributing
+
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

chroma_haystack-3.4.0/pydoc/config_docusaurus.yml

@@ -0,0 +1,31 @@
+loaders:
+- ignore_when_discovered:
+  - __init__
+  modules:
+  - haystack_integrations.components.retrievers.chroma.retriever
+  - haystack_integrations.document_stores.chroma.document_store
+  - haystack_integrations.document_stores.chroma.errors
+  - haystack_integrations.document_stores.chroma.utils
+  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
+- type: smart
+- type: crossref
+renderer:
+  description: Chroma integration for Haystack
+  id: integrations-chroma
+  markdown:
+    add_member_class_prefix: false
+    add_method_class_prefix: true
+    classdef_code_block: false
+    descriptive_class_title: false
+    descriptive_module_title: true
+    filename: chroma.md
+  title: Chroma
+  type: haystack_pydoc_tools.renderers.DocusaurusRenderer

{chroma_haystack-3.2.0 → chroma_haystack-3.4.0}/pyproject.toml

@@ -23,7 +23,7 @@ classifiers = [
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
-dependencies = ["haystack-ai>=2.11.0", "chromadb>=1.0.0"]
+dependencies = ["haystack-ai>=2.11.0", "chromadb>=1.0.2"]
 
 [project.urls]
 Documentation = "https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/chroma#readme"
@@ -66,16 +66,17 @@ integration = 'pytest -m "integration" {args:tests}'
 all = 'pytest {args:tests}'
 cov-retry = 'all --cov=haystack_integrations --reruns 3 --reruns-delay 30 -x'
 
-types = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
+types = "mypy -p haystack_integrations.components.retrievers.chroma -p haystack_integrations.document_stores.chroma {args}"
+
+[tool.mypy]
+install_types = true
+non_interactive = true
+check_untyped_defs = true
+disallow_incomplete_defs = true
 
 [tool.hatch.metadata]
 allow-direct-references = true
 
-[tool.black]
-target-version = ["py38"]
-line-length = 120
-skip-string-normalization = true
-
 [tool.ruff]
 target-version = "py38"
 line-length = 120
@@ -160,7 +161,3 @@ exclude_lines = ["no cov", "if __name__ == .__main__.:", "if TYPE_CHECKING:"]
 [tool.pytest.ini_options]
 minversion = "6.0"
 markers = ["integration: integration tests"]
-
-[[tool.mypy.overrides]]
-module = ["haystack_integrations.*"]
-ignore_missing_imports = true

{chroma_haystack-3.2.0 → chroma_haystack-3.4.0}/src/haystack_integrations/components/retrievers/chroma/retriever.py

@@ -71,7 +71,7 @@ class ChromaQueryTextRetriever:
         query: str,
         filters: Optional[Dict[str, Any]] = None,
         top_k: Optional[int] = None,
-    ):
+    ) -> Dict[str, Any]:
         """
         Run the retriever on the given input data.
 
@@ -96,7 +96,7 @@ class ChromaQueryTextRetriever:
         query: str,
         filters: Optional[Dict[str, Any]] = None,
         top_k: Optional[int] = None,
-    ):
+    ) -> Dict[str, Any]:
         """
         Asynchronously run the retriever on the given input data.
 
@@ -115,7 +115,7 @@ class ChromaQueryTextRetriever:
         """
         filters = apply_filter_policy(self.filter_policy, self.filters, filters)
         top_k = top_k or self.top_k
-        return {"documents": await self.document_store.search_async([query], top_k, filters)[0]}
+        return {"documents": (await self.document_store.search_async([query], top_k, filters))[0]}
 
     @classmethod
     def from_dict(cls, data: Dict[str, Any]) -> "ChromaQueryTextRetriever":
@@ -184,7 +184,7 @@ class ChromaEmbeddingRetriever:
         query_embedding: List[float],
         filters: Optional[Dict[str, Any]] = None,
         top_k: Optional[int] = None,
-    ):
+    ) -> Dict[str, Any]:
         """
         Run the retriever on the given input data.
 
@@ -211,7 +211,7 @@ class ChromaEmbeddingRetriever:
         query_embedding: List[float],
         filters: Optional[Dict[str, Any]] = None,
         top_k: Optional[int] = None,
-    ):
+    ) -> Dict[str, Any]:
         """
         Asynchronously run the retriever on the given input data.
 
@@ -232,7 +232,7 @@ class ChromaEmbeddingRetriever:
         top_k = top_k or self.top_k
 
         query_embeddings = [query_embedding]
-        return {"documents": await self.document_store.search_embeddings_async(query_embeddings, top_k, filters)[0]}
+        return {"documents": (await self.document_store.search_embeddings_async(query_embeddings, top_k, filters))[0]}
 
     @classmethod
     def from_dict(cls, data: Dict[str, Any]) -> "ChromaEmbeddingRetriever":

{chroma_haystack-3.2.0 → chroma_haystack-3.4.0}/src/haystack_integrations/document_stores/chroma/document_store.py

@@ -2,12 +2,14 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
-from typing import Any, Dict, List, Literal, Optional
+from typing import Any, Dict, List, Literal, Optional, Sequence, cast
 
 import chromadb
+from chromadb.api.models.AsyncCollection import AsyncCollection
 from chromadb.api.types import GetResult, QueryResult
 from haystack import default_from_dict, default_to_dict, logging
 from haystack.dataclasses import Document
+from haystack.document_stores.errors import DocumentStoreError
 from haystack.document_stores.types import DuplicatePolicy
 
 from .filters import _convert_filters
@@ -37,7 +39,7 @@ class ChromaDocumentStore:
         port: Optional[int] = None,
         distance_function: Literal["l2", "cosine", "ip"] = "l2",
         metadata: Optional[dict] = None,
-        **embedding_function_params,
+        **embedding_function_params: Any,
     ):
         """
         Creates a new ChromaDocumentStore instance.
@@ -86,8 +88,8 @@ class ChromaDocumentStore:
         self._host = host
         self._port = port
 
-        self._collection = None
-        self._async_collection = None
+        self._collection: Optional[chromadb.Collection] = None
+        self._async_collection: Optional[AsyncCollection] = None
 
     def _ensure_initialized(self):
         if not self._collection:
@@ -112,6 +114,8 @@ class ChromaDocumentStore:
                 # Local persistent storage
                 client = chromadb.PersistentClient(path=self._persist_path)
 
+            self._client = client  # store client for potential future use
+
             self._metadata = self._metadata or {}
             if "hnsw:space" not in self._metadata:
                 self._metadata["hnsw:space"] = self._distance_function
@@ -148,6 +152,8 @@ class ChromaDocumentStore:
                 port=self._port,
             )
 
+            self._async_client = client  # store client for potential future use
+
             self._metadata = self._metadata or {}
             if "hnsw:space" not in self._metadata:
                 self._metadata["hnsw:space"] = self._distance_function
@@ -407,6 +413,86 @@ class ChromaDocumentStore:
 
         await self._async_collection.delete(ids=document_ids)
 
+    def delete_all_documents(self, *, recreate_index: bool = False) -> None:
+        """
+        Deletes all documents in the document store.
+
+        A fast way to clear all documents from the document store while preserving any collection settings and mappings.
+        :param recreate_index: Whether to recreate the index after deleting all documents.
+        """
+        self._ensure_initialized()  # _ensure_initialized ensures _client is not None and a collection exists
+        assert self._collection is not None
+
+        try:
+            if recreate_index:
+                # Store existing collection metadata and embedding function
+                metadata = self._collection.metadata
+                embedding_function = self._collection._embedding_function
+                collection_name = self._collection_name
+
+                # Delete the collection
+                self._client.delete_collection(name=collection_name)
+
+                # Recreate the collection with previous metadata
+                self._collection = self._client.create_collection(
+                    name=collection_name,
+                    metadata=metadata,
+                    embedding_function=embedding_function,
+                )
+
+            else:
+                collection = self._collection.get()
+                ids = collection.get("ids", [])
+                self._collection.delete(ids=ids)  # type: ignore
+                logger.info(
+                    "Deleted all the {n_docs} documents from the collection '{name}'.",
+                    name=self._collection_name,
+                    n_docs=len(ids),
+                )
+        except Exception as e:
+            msg = f"Failed to delete all documents from ChromaDB: {e!s}"
+            raise DocumentStoreError(msg) from e
+
+    async def delete_all_documents_async(self, *, recreate_index: bool = False) -> None:
+        """
+        Asynchronously deletes all documents in the document store.
+
+        A fast way to clear all documents from the document store while preserving any collection settings and mappings.
+        :param recreate_index: Whether to recreate the index after deleting all documents.
+        """
+        await self._ensure_initialized_async()  # ensures _async_client is not None
+        assert self._async_collection is not None
+
+        try:
+            if recreate_index:
+                # Store existing collection metadata and embedding function
+                metadata = self._async_collection.metadata
+                embedding_function = self._async_collection._embedding_function
+                collection_name = self._collection_name
+
+                # Delete the collection
+                await self._async_client.delete_collection(name=collection_name)
+
+                # Recreate the collection with previous metadata
+                self._async_collection = await self._async_client.create_collection(
+                    name=collection_name,
+                    metadata=metadata,
+                    embedding_function=embedding_function,
+                )
+            else:
+                collection = await self._async_collection.get()
+                ids = collection.get("ids", [])
+                await self._async_collection.delete(ids=ids)  # type: ignore
+                logger.info(
+                    "Deleted all the {n_docs} documents from the collection '{name}'.",
+                    name=self._collection_name,
+                    n_docs=len(ids),
+                )
+
+        except Exception as e:
+            msg = f"Failed to delete all documents from ChromaDB: {e!s}"
+            raise DocumentStoreError(msg) from e
+
     def search(
         self,
         queries: List[str],
@@ -482,7 +568,7 @@ class ChromaDocumentStore:
 
         kwargs = self._prepare_query_kwargs(filters)
         results = self._collection.query(
-            query_embeddings=query_embeddings,
+            query_embeddings=cast(List[Sequence[float]], query_embeddings),
             n_results=top_k,
             **kwargs,
         )
@@ -513,7 +599,7 @@ class ChromaDocumentStore:
 
         kwargs = self._prepare_query_kwargs(filters)
         results = await self._async_collection.query(
-            query_embeddings=query_embeddings,
+            query_embeddings=cast(List[Sequence[float]], query_embeddings),
             n_results=top_k,
             **kwargs,
         )

{chroma_haystack-3.2.0 → chroma_haystack-3.4.0}/src/haystack_integrations/document_stores/chroma/utils.py

@@ -2,6 +2,8 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
+from typing import Any
+
 from chromadb.api.types import EmbeddingFunction
 from chromadb.utils.embedding_functions import (
     CohereEmbeddingFunction,
@@ -34,7 +36,7 @@ FUNCTION_REGISTRY = {
 }
 
 
-def get_embedding_function(function_name: str, **kwargs) -> EmbeddingFunction:
+def get_embedding_function(function_name: str, **kwargs: Any) -> EmbeddingFunction:
     """Load an embedding function by name.
 
     :param function_name: the name of the embedding function.

{chroma_haystack-3.2.0 → chroma_haystack-3.4.0}/tests/test_document_store.py

@@ -4,6 +4,7 @@
 
 import logging
 import operator
+import time
 import uuid
 from typing import List
 from unittest import mock
@@ -381,3 +382,41 @@ class TestDocumentStore(CountDocumentsTest, DeleteDocumentsTest, FilterDocuments
         # check that empty filters behave as no filters
         result_empty_filters = document_store.search(["Third"], filters={}, top_k=1)
         assert result == result_empty_filters
+
+    def test_delete_all_documents_index_recreation(self, document_store: ChromaDocumentStore):
+        # write some documents
+        docs = [Document(id="1", content="A first document"), Document(id="2", content="Second document")]
+        document_store.write_documents(docs)
+
+        # get the current document_store config
+        config_before = document_store._collection.get(document_store._collection_name)
+
+        # delete all documents with recreating the index
+        document_store.delete_all_documents(recreate_index=True)
+        assert document_store.count_documents() == 0
+
+        # assure that with the same config
+        config_after = document_store._collection.get(document_store._collection_name)
+
+        assert config_before == config_after
+
+        # ensure the collection still exists by writing documents again
+        document_store.write_documents(docs)
+        assert document_store.count_documents() == 2
+
+    def test_delete_all_documents_no_index_recreation(self, document_store: ChromaDocumentStore):
+        docs = [Document(id="1", content="A first document"), Document(id="2", content="Second document")]
+        document_store.write_documents(docs)
+        assert document_store.count_documents() == 2
+
+        document_store.delete_all_documents()
+        time.sleep(2)  # need to wait for the deletion to be reflected in count_documents
+        assert document_store.count_documents() == 0
+
+        new_doc = Document(id="3", content="New document after delete all")
+        document_store.write_documents([new_doc])
+        assert document_store.count_documents() == 1
+
+        results = document_store.filter_documents()
+        assert len(results) == 1
+        assert results[0].content == "New document after delete all"

{chroma_haystack-3.2.0 → chroma_haystack-3.4.0}/tests/test_document_store_async.py

@@ -120,3 +120,53 @@ class TestDocumentStoreAsync:
         # check that empty filters behave as no filters
         result_empty_filters = document_store.search(["Third"], filters={}, top_k=1)
         assert result == result_empty_filters
+
+    @pytest.mark.asyncio
+    async def test_delete_all_documents_index_recreation(self, document_store: ChromaDocumentStore):
+        # write some documents
+        docs = [
+            Document(id="1", content="First document", meta={"category": "test"}),
+            Document(id="2", content="Second document", meta={"category": "test"}),
+            Document(id="3", content="Third document", meta={"category": "other"}),
+        ]
+        await document_store.write_documents_async(docs)
+
+        # get the current document_store config
+        config_before = await document_store._async_collection.get(document_store._collection_name)
+
+        # delete all documents with recreating the index
+        await document_store.delete_all_documents_async(recreate_index=True)
+        assert await document_store.count_documents_async() == 0
+
+        # assure that with the same config
+        config_after = await document_store._async_collection.get(document_store._collection_name)
+
+        assert config_before == config_after
+
+        # ensure the collection still exists by writing documents again
+        await document_store.write_documents_async(docs)
+        assert await document_store.count_documents_async() == 3
+
+    @pytest.mark.asyncio
+    async def test_delete_all_documents_async(self, document_store):
+        docs = [
+            Document(id="1", content="First document", meta={"category": "test"}),
+            Document(id="2", content="Second document", meta={"category": "test"}),
+            Document(id="3", content="Third document", meta={"category": "other"}),
+        ]
+        await document_store.write_documents_async(docs)
+        assert await document_store.count_documents_async() == 3
+
+        # delete all documents
+        await document_store.delete_all_documents_async()
+        assert await document_store.count_documents_async() == 0
+
+        # verify index still exists and can accept new documents and retrieve
+        new_doc = Document(id="4", content="New document after delete all")
+        await document_store.write_documents_async([new_doc])
+        assert await document_store.count_documents_async() == 1
+
+        results = await document_store.filter_documents_async()
+        assert len(results) == 1
+        assert results[0].id == "4"
+        assert results[0].content == "New document after delete all"

chroma_haystack-3.2.0/README.md

@@ -1,27 +0,0 @@
-# Chroma Document Store for Haystack
-
-[![PyPI - Version](https://img.shields.io/pypi/v/chroma-haystack.svg)](https://pypi.org/project/chroma-haystack)
-[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/chroma-haystack.svg)](https://pypi.org/project/chroma-haystack)
-[![test](https://github.com/masci/chroma-haystack/actions/workflows/test.yml/badge.svg)](https://github.com/masci/chroma-haystack/actions/workflows/test.yml)
-
------
-
-**Table of Contents**
-
-- [Chroma Document Store for Haystack](#chroma-document-store-for-haystack)
-  - [Installation](#installation)
-  - [Examples](#examples)
-  - [License](#license)
-
-## Installation
-
-```console
-pip install chroma-haystack
-```
-
-## Examples
-You can find a code example showing how to use the Document Store and the Retriever under the `example/` folder of this repo or in [this Colab](https://colab.research.google.com/drive/1YpDetI8BRbObPDEVdfqUcwhEX9UUXP-m?usp=sharing).
-
-## License
-
-`chroma-haystack` is distributed under the terms of the [Apache-2.0](https://spdx.org/licenses/Apache-2.0.html) license.