Merge branch 'main' into patch-1

integrations/chroma/example/example.py

@@ -1,19 +1,21 @@
 # Colab: https://colab.research.google.com/drive/1YpDetI8BRbObPDEVdfqUcwhEX9UUXP-m?usp=sharing
+
 import os
 from pathlib import Path
 
 from haystack import Pipeline
 from haystack.components.converters import TextFileToDocument
 from haystack.components.writers import DocumentWriter
 
-from haystack_integrations.document_stores.chroma import ChromaDocumentStore
 from haystack_integrations.components.retrievers.chroma import ChromaQueryTextRetriever
+from haystack_integrations.document_stores.chroma import ChromaDocumentStore
+
+# Chroma is used in-memory so we use the same instances in the two pipelines below
+document_store = ChromaDocumentStore()
 
 HERE = Path(__file__).resolve().parent
 file_paths = [HERE / "data" / Path(name) for name in os.listdir("data")]
 
-# Chroma is used in-memory so we use the same instances in the two pipelines below
-document_store = ChromaDocumentStore()
 
 indexing = Pipeline()
 indexing.add_component("converter", TextFileToDocument())

integrations/chroma/pyproject.toml

@@ -70,8 +70,8 @@ dependencies = [
 ]
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = ["ruff check {args:.}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
+style = ["ruff check {args:. --exclude tests/}", "black --check --diff {args:.}"]
+fmt = ["black {args:.}", "ruff --fix {args:. --exclude tests/}", "style"]
 all = ["style", "typing"]
 
 [tool.hatch.metadata]
@@ -85,7 +85,7 @@ skip-string-normalization = true
 [tool.ruff]
 target-version = "py38"
 line-length = 120
-select = [
+lint.select = [
   "A",
   "ARG",
   "B",
@@ -112,7 +112,7 @@ select = [
   "W",
   "YTT",
 ]
-ignore = [
+lint.ignore = [
   # Allow non-abstract empty methods in abstract base classes
   "B027",
   # Allow boolean positional values in function calls, like `dict.get(... True)`
@@ -130,21 +130,22 @@ ignore = [
   # Ignore unused params
   "ARG002",
 ]
-unfixable = [
+lint.unfixable = [
   # Don't touch unused imports
   "F401",
 ]
 exclude = ["example"]
 
 [tool.ruff.isort]
-known-first-party = ["src"]
+known-first-party = ["src", "example", "tests"]
 
 [tool.ruff.flake8-tidy-imports]
 ban-relative-imports = "parents"
 
 [tool.ruff.per-file-ignores]
 # Tests can use magic values, assertions, and relative imports
 "tests/**/*" = ["PLR2004", "S101", "TID252"]
+"example/**/*" = ["T201"]
 
 [tool.coverage.run]
 source = ["haystack_integrations"]

integrations/chroma/src/haystack_integrations/components/retrievers/chroma/retriever.py

@@ -6,6 +6,7 @@
 from haystack import Document, component, default_from_dict, default_to_dict
 from haystack.document_stores.types import FilterPolicy
 from haystack.document_stores.types.filter_policy import apply_filter_policy
+
 from haystack_integrations.document_stores.chroma import ChromaDocumentStore
 
 

integrations/chroma/tests/test_document_store.py

@@ -16,6 +16,7 @@
     DeleteDocumentsTest,
     LegacyFilterDocumentsTest,
 )
+
 from haystack_integrations.document_stores.chroma import ChromaDocumentStore
 
 

integrations/chroma/tests/test_retriever.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: Apache-2.0
 import pytest
 from haystack.document_stores.types import FilterPolicy
+
 from haystack_integrations.components.retrievers.chroma import ChromaQueryTextRetriever
 from haystack_integrations.document_stores.chroma import ChromaDocumentStore
 

integrations/cohere/examples/cohere_embedding.py

@@ -1,6 +1,7 @@
 from haystack import Document, Pipeline
 from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
 from haystack.document_stores.in_memory import InMemoryDocumentStore
+
 from haystack_integrations.components.embedders.cohere.document_embedder import CohereDocumentEmbedder
 from haystack_integrations.components.embedders.cohere.text_embedder import CohereTextEmbedder
 

integrations/cohere/examples/cohere_generation.py

@@ -20,6 +20,7 @@
 from haystack.components.joiners import BranchJoiner
 from haystack.components.validators import JsonSchemaValidator
 from haystack.dataclasses import ChatMessage
+
 from haystack_integrations.components.generators.cohere import CohereChatGenerator
 
 # Defines a JSON schema for validating a person's data. The schema specifies that a valid object must

integrations/cohere/examples/cohere_ranker.py

@@ -1,6 +1,7 @@
 from haystack import Document, Pipeline
 from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
 from haystack.document_stores.in_memory import InMemoryDocumentStore
+
 from haystack_integrations.components.rankers.cohere import CohereRanker
 
 # Note set your API key by running the below command in your terminal

integrations/cohere/pyproject.toml

@@ -41,7 +41,12 @@ root = "../.."
 git_describe_command = 'git describe --tags --match="integrations/cohere-v[0-9]*"'
 
 [tool.hatch.envs.default]
-dependencies = ["coverage[toml]>=6.5", "pytest", "pytest-rerunfailures", "haystack-pydoc-tools"]
+dependencies = [
+  "coverage[toml]>=6.5",
+  "pytest",
+  "pytest-rerunfailures",
+  "haystack-pydoc-tools",
+]
 [tool.hatch.envs.default.scripts]
 test = "pytest {args:tests}"
 test-cov = "coverage run -m pytest {args:tests}"
@@ -59,8 +64,11 @@ detached = true
 dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = ["ruff check {args:.}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
+style = [
+  "ruff check {args:. --exclude tests/}",
+  "black --check --diff {args:.}",
+]
+fmt = ["black {args:.}", "ruff --fix {args:. --exclude tests/}", "style"]
 all = ["style", "typing"]
 
 [tool.black]

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

@@ -6,9 +6,9 @@
 
 from haystack import Document, component, default_from_dict, default_to_dict
 from haystack.utils import Secret, deserialize_secrets_inplace
-from haystack_integrations.components.embedders.cohere.utils import get_async_response, get_response
 
 from cohere import AsyncClient, Client
+from haystack_integrations.components.embedders.cohere.utils import get_async_response, get_response
 
 
 @component

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

@@ -6,9 +6,9 @@
 
 from haystack import component, default_from_dict, default_to_dict
 from haystack.utils import Secret, deserialize_secrets_inplace
-from haystack_integrations.components.embedders.cohere.utils import get_async_response, get_response
 
 from cohere import AsyncClient, Client
+from haystack_integrations.components.embedders.cohere.utils import get_async_response, get_response
 
 
 @component

integrations/fastembed/examples/example.py

@@ -1,6 +1,7 @@
 from haystack import Document, Pipeline
 from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
 from haystack.document_stores.in_memory import InMemoryDocumentStore
+
 from haystack_integrations.components.embedders.fastembed import FastembedDocumentEmbedder, FastembedTextEmbedder
 
 document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")

integrations/fastembed/examples/sparse_example.py

@@ -4,6 +4,7 @@
 # involving indexing and retrieval of documents.
 
 from haystack import Document
+
 from haystack_integrations.components.embedders.fastembed import FastembedSparseDocumentEmbedder
 
 document_list = [

integrations/fastembed/pyproject.toml

@@ -66,8 +66,8 @@ detached = true
 dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243", "numpy"]
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = ["ruff check {args:.}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
+style = ["ruff check {args:. --exclude tests/, examples/}", "black --check --diff {args:.}"]
+fmt = ["black {args:.}", "ruff --fix {args:. --exclude tests/, examples/}", "style"]
 all = ["style", "typing"]
 
 [tool.black]

integrations/fastembed/tests/test_fastembed_document_embedder.py

@@ -3,6 +3,7 @@
 import numpy as np
 import pytest
 from haystack import Document, default_from_dict
+
 from haystack_integrations.components.embedders.fastembed.fastembed_document_embedder import (
     FastembedDocumentEmbedder,
 )

integrations/fastembed/tests/test_fastembed_sparse_document_embedder.py

@@ -4,6 +4,7 @@
 import pytest
 from haystack import Document, default_from_dict
 from haystack.dataclasses.sparse_embedding import SparseEmbedding
+
 from haystack_integrations.components.embedders.fastembed.fastembed_sparse_document_embedder import (
     FastembedSparseDocumentEmbedder,
 )

integrations/fastembed/tests/test_fastembed_sparse_text_embedder.py

@@ -4,6 +4,7 @@
 import pytest
 from haystack import default_from_dict
 from haystack.dataclasses.sparse_embedding import SparseEmbedding
+
 from haystack_integrations.components.embedders.fastembed.fastembed_sparse_text_embedder import (
     FastembedSparseTextEmbedder,
 )

integrations/fastembed/tests/test_fastembed_text_embedder.py

@@ -3,6 +3,7 @@
 import numpy as np
 import pytest
 from haystack import default_from_dict
+
 from haystack_integrations.components.embedders.fastembed.fastembed_text_embedder import (
     FastembedTextEmbedder,
 )

integrations/jina/pyproject.toml

@@ -62,8 +62,8 @@ detached = true
 dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = ["ruff check {args:.}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
+style = ["ruff check {args:. --exclude tests/}", "black --check --diff {args:.}"]
+fmt = ["black {args:.}", "ruff --fix {args:. --exclude tests/}", "style"]
 all = ["style", "typing"]
 
 [tool.black]

integrations/jina/tests/test_document_embedder.py

@@ -8,6 +8,7 @@
 import requests
 from haystack import Document
 from haystack.utils import Secret
+
 from haystack_integrations.components.embedders.jina import JinaDocumentEmbedder
 
 

integrations/jina/tests/test_ranker.py

@@ -8,6 +8,7 @@
 import requests
 from haystack import Document
 from haystack.utils import Secret
+
 from haystack_integrations.components.rankers.jina import JinaRanker
 
 

integrations/jina/tests/test_text_embedder.py

@@ -7,6 +7,7 @@
 import pytest
 import requests
 from haystack.utils import Secret
+
 from haystack_integrations.components.embedders.jina import JinaTextEmbedder
 
 

integrations/langfuse/pyproject.toml

@@ -67,8 +67,8 @@ dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
 
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = ["ruff check {args:.}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
+style = ["ruff check {args:. --exclude tests/}", "black --check --diff {args:.}"]
+fmt = ["black {args:.}", "ruff --fix {args:. --exclude tests/}", "style"]
 all = ["style", "typing"]
 
 [tool.hatch.metadata]

integrations/langfuse/src/haystack_integrations/components/connectors/langfuse/langfuse_connector.py

@@ -1,6 +1,6 @@
 from haystack import component, tracing
-from haystack_integrations.tracing.langfuse import LangfuseTracer
 
+from haystack_integrations.tracing.langfuse import LangfuseTracer
 from langfuse import Langfuse
 
 

integrations/mistral/examples/indexing_pipeline.py

@@ -7,6 +7,7 @@
 from haystack.components.preprocessors import DocumentSplitter
 from haystack.components.writers import DocumentWriter
 from haystack.document_stores.in_memory import InMemoryDocumentStore
+
 from haystack_integrations.components.embedders.mistral.document_embedder import MistralDocumentEmbedder
 
 document_store = InMemoryDocumentStore()

integrations/mistral/examples/streaming_chat_with_rag.py

@@ -11,6 +11,7 @@
 from haystack.components.writers import DocumentWriter
 from haystack.dataclasses import ChatMessage
 from haystack.document_stores.in_memory import InMemoryDocumentStore
+
 from haystack_integrations.components.embedders.mistral.document_embedder import MistralDocumentEmbedder
 from haystack_integrations.components.embedders.mistral.text_embedder import MistralTextEmbedder
 from haystack_integrations.components.generators.mistral import MistralChatGenerator

integrations/mistral/pyproject.toml

@@ -41,7 +41,12 @@ root = "../.."
 git_describe_command = 'git describe --tags --match="integrations/mistral-v[0-9]*"'
 
 [tool.hatch.envs.default]
-dependencies = ["coverage[toml]>=6.5", "pytest", "pytest-rerunfailures", "haystack-pydoc-tools"]
+dependencies = [
+  "coverage[toml]>=6.5",
+  "pytest",
+  "pytest-rerunfailures",
+  "haystack-pydoc-tools",
+]
 [tool.hatch.envs.default.scripts]
 test = "pytest {args:tests}"
 test-cov = "coverage run -m pytest {args:tests}"
@@ -59,8 +64,11 @@ detached = true
 dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = ["ruff check {args:.}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
+style = [
+  "ruff check {args:. --exclude tests/}",
+  "black --check --diff {args:.}",
+]
+fmt = ["black {args:.}", "ruff --fix {args:. --exclude tests/}", "style"]
 all = ["style", "typing"]
 
 [tool.black]

integrations/mongodb_atlas/examples/example.py

@@ -13,6 +13,7 @@
 from haystack.components.embedders import SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder
 from haystack.components.preprocessors import DocumentSplitter
 from haystack.components.writers import DocumentWriter
+
 from haystack_integrations.components.retrievers.mongodb_atlas import MongoDBAtlasEmbeddingRetriever
 from haystack_integrations.document_stores.mongodb_atlas import MongoDBAtlasDocumentStore
 

integrations/mongodb_atlas/pyproject.toml

@@ -66,8 +66,8 @@ detached = true
 dependencies = ["black>=23.1.0", "mypy>=1.0.0", "ruff>=0.0.243"]
 [tool.hatch.envs.lint.scripts]
 typing = "mypy --install-types --non-interactive --explicit-package-bases {args:src/ tests}"
-style = ["ruff check {args:.}", "black --check --diff {args:.}"]
-fmt = ["black {args:.}", "ruff --fix {args:.}", "style"]
+style = ["ruff check {args:. --exclude tests/, examples/}", "black --check --diff {args:.}"]
+fmt = ["black {args:.}", "ruff --fix {args:. --exclude tests/, examples/}", "style"]
 all = ["style", "typing"]
 
 [tool.black]

integrations/mongodb_atlas/src/haystack_integrations/components/retrievers/mongodb_atlas/embedding_retriever.py

@@ -7,6 +7,7 @@
 from haystack.dataclasses import Document
 from haystack.document_stores.types import FilterPolicy
 from haystack.document_stores.types.filter_policy import apply_filter_policy
+
 from haystack_integrations.document_stores.mongodb_atlas import MongoDBAtlasDocumentStore
 
 

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

@@ -10,12 +10,13 @@
 from haystack.document_stores.errors import DocumentStoreError, DuplicateDocumentError
 from haystack.document_stores.types import DuplicatePolicy
 from haystack.utils import Secret, deserialize_secrets_inplace
-from haystack_integrations.document_stores.mongodb_atlas.filters import _normalize_filters
 from pymongo import InsertOne, MongoClient, ReplaceOne, UpdateOne
 from pymongo.collection import Collection
 from pymongo.driver_info import DriverInfo
 from pymongo.errors import BulkWriteError
 
+from haystack_integrations.document_stores.mongodb_atlas.filters import _normalize_filters
+
 logger = logging.getLogger(__name__)
 
 

integrations/mongodb_atlas/tests/test_document_store.py

@@ -11,11 +11,12 @@
 from haystack.document_stores.types import DuplicatePolicy
 from haystack.testing.document_store import DocumentStoreBaseTests
 from haystack.utils import Secret
-from haystack_integrations.document_stores.mongodb_atlas import MongoDBAtlasDocumentStore
 from pandas import DataFrame
 from pymongo import MongoClient
 from pymongo.driver_info import DriverInfo
 
+from haystack_integrations.document_stores.mongodb_atlas import MongoDBAtlasDocumentStore
+
 
 @patch("haystack_integrations.document_stores.mongodb_atlas.document_store.MongoClient")
 def test_init_is_lazy(_mock_client):

integrations/mongodb_atlas/tests/test_embedding_retrieval.py

@@ -6,6 +6,7 @@
 
 import pytest
 from haystack.document_stores.errors import DocumentStoreError
+
 from haystack_integrations.document_stores.mongodb_atlas import MongoDBAtlasDocumentStore