chore: add license header to all modules (#7675)

* add license header to modules
* check license header at linting time

.github/workflows/linting.yml

@@ -14,6 +14,15 @@ env:
   HATCH_VERSION: "1.9.3"
 
 jobs:
+  license-header:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Check License Header
+        run: docker run --rm -v "$(pwd):/github/workspace" ghcr.io/korandoru/hawkeye check
+
   mypy:
     runs-on: ubuntu-latest
     steps:

.github/workflows/linting_skipper.yml

@@ -10,6 +10,12 @@ on:
       - "**/pyproject.toml"
 
 jobs:
+  license-header:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Skip mypy
+        run: echo "Skipped mypy"
+
   mypy:
     runs-on: ubuntu-latest
     steps:

e2e/__init__.py

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0

e2e/conftest.py

@@ -1,6 +1,11 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from pathlib import Path
 
 import pytest
+
 from haystack.testing.test_utils import set_all_seeds
 
 set_all_seeds(0)

e2e/pipelines/test_dense_doc_search.py

@@ -1,14 +1,18 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import json
 
 from haystack import Pipeline
-from haystack.components.embedders import SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder
 from haystack.components.converters import PyPDFToDocument, TextFileToDocument
+from haystack.components.embedders import SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder
+from haystack.components.joiners import DocumentJoiner
 from haystack.components.preprocessors import DocumentCleaner, DocumentSplitter
+from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
 from haystack.components.routers import FileTypeRouter
-from haystack.components.joiners import DocumentJoiner
 from haystack.components.writers import DocumentWriter
 from haystack.document_stores.in_memory import InMemoryDocumentStore
-from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
 
 
 def test_dense_doc_search_pipeline(tmp_path, samples_path):

e2e/pipelines/test_evaluation_pipeline.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import os
 from typing import List
 

e2e/pipelines/test_extractive_qa_pipeline.py

@@ -1,9 +1,13 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import json
 
-from haystack import Pipeline, Document
-from haystack.document_stores.in_memory import InMemoryDocumentStore
-from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
+from haystack import Document, Pipeline
 from haystack.components.readers import ExtractiveReader
+from haystack.components.retrievers.in_memory import InMemoryBM25Retriever
+from haystack.document_stores.in_memory import InMemoryDocumentStore
 
 
 def test_extractive_qa_pipeline(tmp_path):

e2e/pipelines/test_hybrid_doc_search_pipeline.py

@@ -1,12 +1,16 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import json
 
-from haystack import Pipeline, Document
-from haystack.components.embedders import SentenceTransformersTextEmbedder, SentenceTransformersDocumentEmbedder
-from haystack.components.rankers import TransformersSimilarityRanker
+from haystack import Document, Pipeline
+from haystack.components.embedders import SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder
 from haystack.components.joiners.document_joiner import DocumentJoiner
+from haystack.components.rankers import TransformersSimilarityRanker
+from haystack.components.retrievers.in_memory import InMemoryBM25Retriever, InMemoryEmbeddingRetriever
 from haystack.document_stores.in_memory import InMemoryDocumentStore
 from haystack.document_stores.types import DuplicatePolicy
-from haystack.components.retrievers.in_memory import InMemoryBM25Retriever, InMemoryEmbeddingRetriever
 
 
 def test_hybrid_doc_search_pipeline(tmp_path):

e2e/pipelines/test_named_entity_extractor.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import pytest
 
 from haystack import ComponentError, Document, Pipeline

e2e/pipelines/test_preprocessing_pipeline.py

@@ -1,10 +1,14 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import json
 
 from haystack import Pipeline
-from haystack.components.embedders import SentenceTransformersDocumentEmbedder
-from haystack.components.converters import TextFileToDocument
-from haystack.components.preprocessors import DocumentSplitter, DocumentCleaner
 from haystack.components.classifiers import DocumentLanguageClassifier
+from haystack.components.converters import TextFileToDocument
+from haystack.components.embedders import SentenceTransformersDocumentEmbedder
+from haystack.components.preprocessors import DocumentCleaner, DocumentSplitter
 from haystack.components.routers import FileTypeRouter, MetadataRouter
 from haystack.components.writers import DocumentWriter
 from haystack.document_stores.in_memory import InMemoryDocumentStore

e2e/pipelines/test_rag_pipelines_e2e.py

@@ -1,15 +1,20 @@
-import os
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import json
+import os
+
 import pytest
 
-from haystack import Pipeline, Document
-from haystack.document_stores.in_memory import InMemoryDocumentStore
-from haystack.components.writers import DocumentWriter
-from haystack.components.retrievers.in_memory import InMemoryBM25Retriever, InMemoryEmbeddingRetriever
-from haystack.components.embedders import SentenceTransformersTextEmbedder, SentenceTransformersDocumentEmbedder
-from haystack.components.generators import OpenAIGenerator
+from haystack import Document, Pipeline
 from haystack.components.builders.answer_builder import AnswerBuilder
 from haystack.components.builders.prompt_builder import PromptBuilder
+from haystack.components.embedders import SentenceTransformersDocumentEmbedder, SentenceTransformersTextEmbedder
+from haystack.components.generators import OpenAIGenerator
+from haystack.components.retrievers.in_memory import InMemoryBM25Retriever, InMemoryEmbeddingRetriever
+from haystack.components.writers import DocumentWriter
+from haystack.document_stores.in_memory import InMemoryDocumentStore
 
 
 @pytest.mark.skipif(

haystack/__init__.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import haystack.logging
 from haystack.core.component import component
 from haystack.core.errors import ComponentError, DeserializationError

haystack/components/__init__.py

@@ -0,0 +1,3 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0

haystack/components/audio/__init__.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from haystack.components.audio.whisper_local import LocalWhisperTranscriber
 from haystack.components.audio.whisper_remote import RemoteWhisperTranscriber
 

haystack/components/audio/whisper_local.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import tempfile
 from pathlib import Path
 from typing import Any, Dict, List, Literal, Optional, Union, get_args

haystack/components/audio/whisper_remote.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import io
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union

haystack/components/builders/__init__.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from haystack.components.builders.answer_builder import AnswerBuilder
 from haystack.components.builders.dynamic_chat_prompt_builder import DynamicChatPromptBuilder
 from haystack.components.builders.dynamic_prompt_builder import DynamicPromptBuilder

haystack/components/builders/answer_builder.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import re
 from typing import Any, Dict, List, Optional
 

haystack/components/builders/dynamic_chat_prompt_builder.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from typing import Any, Dict, List, Optional, Set
 
 from jinja2 import Template, meta

haystack/components/builders/dynamic_prompt_builder.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from typing import Any, Dict, List, Optional, Set
 
 from jinja2 import Template, meta

haystack/components/builders/prompt_builder.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from typing import Any, Dict, List, Optional
 
 from jinja2 import Template, meta

haystack/components/caching/__init__.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from haystack.components.caching.cache_checker import CacheChecker
 
 __all__ = ["CacheChecker"]

haystack/components/caching/cache_checker.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import importlib
 from typing import Any, Dict, List
 

haystack/components/classifiers/__init__.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from haystack.components.classifiers.document_language_classifier import DocumentLanguageClassifier
 
 __all__ = ["DocumentLanguageClassifier"]

haystack/components/classifiers/document_language_classifier.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from typing import Dict, List, Optional
 
 from haystack import Document, component, logging

haystack/components/connectors/__init__.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from haystack.components.connectors.openapi_service import OpenAPIServiceConnector
 
 __all__ = ["OpenAPIServiceConnector"]

haystack/components/connectors/openapi_service.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import json
 from collections import defaultdict
 from copy import copy

haystack/components/converters/__init__.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from haystack.components.converters.azure import AzureOCRDocumentConverter
 from haystack.components.converters.html import HTMLToDocument
 from haystack.components.converters.markdown import MarkdownToDocument

haystack/components/converters/azure.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import copy
 import hashlib
 from collections import defaultdict

haystack/components/converters/html.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from pathlib import Path
 from typing import Any, ClassVar, Dict, List, Literal, Optional, Union
 

haystack/components/converters/markdown.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 

haystack/components/converters/openapi_functions.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import json
 import os
 from pathlib import Path

haystack/components/converters/output_adapter.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from typing import Any, Callable, Dict, Optional, Set
 
 import jinja2.runtime

haystack/components/converters/pdfminer.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import io
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union

haystack/components/converters/pypdf.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import io
 import warnings
 from pathlib import Path

haystack/components/converters/tika.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import io
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union

haystack/components/converters/txt.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 

haystack/components/converters/utils.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Union
 

haystack/components/embedders/__init__.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 from haystack.components.embedders.azure_document_embedder import AzureOpenAIDocumentEmbedder
 from haystack.components.embedders.azure_text_embedder import AzureOpenAITextEmbedder
 from haystack.components.embedders.hugging_face_api_document_embedder import HuggingFaceAPIDocumentEmbedder

haystack/components/embedders/azure_document_embedder.py

@@ -1,3 +1,7 @@
+# SPDX-FileCopyrightText: 2022-present deepset GmbH <[email protected]>
+#
+# SPDX-License-Identifier: Apache-2.0
+
 import os
 from typing import Any, Dict, List, Optional, Tuple