change metadata to meta (#152)

integrations/cohere/src/cohere_haystack/embedders/document_embedder.py

@@ -45,7 +45,7 @@ def __init__(
         timeout: int = 120,
         batch_size: int = 32,
         progress_bar: bool = True,
-        metadata_fields_to_embed: Optional[List[str]] = None,
+        meta_fields_to_embed: Optional[List[str]] = None,
         embedding_separator: str = "\n",
     ):
         """
@@ -74,7 +74,7 @@ def __init__(
         :param batch_size: Number of Documents to encode at once.
         :param progress_bar: Whether to show a progress bar or not. Can be helpful to disable in production deployments
                              to keep the logs clean.
-        :param metadata_fields_to_embed: List of meta fields that should be embedded along with the Document text.
+        :param meta_fields_to_embed: List of meta fields that should be embedded along with the Document text.
         :param embedding_separator: Separator used to concatenate the meta fields to the Document text.
         """
 
@@ -98,7 +98,7 @@ def __init__(
         self.timeout = timeout
         self.batch_size = batch_size
         self.progress_bar = progress_bar
-        self.metadata_fields_to_embed = metadata_fields_to_embed or []
+        self.meta_fields_to_embed = meta_fields_to_embed or []
         self.embedding_separator = embedding_separator
 
     def to_dict(self) -> Dict[str, Any]:
@@ -116,7 +116,7 @@ def to_dict(self) -> Dict[str, Any]:
             timeout=self.timeout,
             batch_size=self.batch_size,
             progress_bar=self.progress_bar,
-            metadata_fields_to_embed=self.metadata_fields_to_embed,
+            meta_fields_to_embed=self.meta_fields_to_embed,
             embedding_separator=self.embedding_separator,
         )
 
@@ -127,14 +127,14 @@ def _prepare_texts_to_embed(self, documents: List[Document]) -> List[str]:
         texts_to_embed: List[str] = []
         for doc in documents:
             meta_values_to_embed = [
-                str(doc.meta[key]) for key in self.metadata_fields_to_embed if doc.meta.get(key) is not None
+                str(doc.meta[key]) for key in self.meta_fields_to_embed if doc.meta.get(key) is not None
             ]
 
             text_to_embed = self.embedding_separator.join(meta_values_to_embed + [doc.content or ""])  # noqa: RUF005
             texts_to_embed.append(text_to_embed)
         return texts_to_embed
 
-    @component.output_types(documents=List[Document], metadata=Dict[str, Any])
+    @component.output_types(documents=List[Document], meta=Dict[str, Any])
     def run(self, documents: List[Document]):
         """
         Embed a list of Documents.
@@ -152,7 +152,7 @@ def run(self, documents: List[Document]):
 
         if not documents:
             # return early if we were passed an empty list
-            return {"documents": [], "metadata": {}}
+            return {"documents": [], "meta": {}}
 
         texts_to_embed = self._prepare_texts_to_embed(documents)
 
@@ -180,4 +180,4 @@ def run(self, documents: List[Document]):
         for doc, embeddings in zip(documents, all_embeddings):
             doc.embedding = embeddings
 
-        return {"documents": documents, "metadata": metadata}
+        return {"documents": documents, "meta": metadata}

integrations/cohere/src/cohere_haystack/embedders/text_embedder.py

@@ -27,7 +27,7 @@ class CohereTextEmbedder:
     print(text_embedder.run(text_to_embed))
 
     # {'embedding': [-0.453125, 1.2236328, 2.0058594, ...]
-    # 'metadata': {'api_version': {'version': '1'}, 'billed_units': {'input_tokens': 4}}}
+    # 'meta': {'api_version': {'version': '1'}, 'billed_units': {'input_tokens': 4}}}
     ```
     """
 
@@ -101,7 +101,7 @@ def to_dict(self) -> Dict[str, Any]:
             timeout=self.timeout,
         )
 
-    @component.output_types(embedding=List[float], metadata=Dict[str, Any])
+    @component.output_types(embedding=List[float], meta=Dict[str, Any])
     def run(self, text: str):
         """Embed a string."""
         if not isinstance(text, str):
@@ -126,4 +126,4 @@ def run(self, text: str):
             )
             embedding, metadata = get_response(cohere_client, [text], self.model_name, self.input_type, self.truncate)
 
-        return {"embedding": embedding[0], "metadata": metadata}
+        return {"embedding": embedding[0], "meta": metadata}

integrations/cohere/src/cohere_haystack/generator.py

@@ -135,7 +135,7 @@ def from_dict(cls, data: Dict[str, Any]) -> "CohereGenerator":
             data["init_parameters"]["streaming_callback"] = streaming_callback
         return default_from_dict(cls, data)
 
-    @component.output_types(replies=List[str], metadata=List[Dict[str, Any]])
+    @component.output_types(replies=List[str], meta=List[Dict[str, Any]])
     def run(self, prompt: str):
         """
         Queries the LLM with the prompts to produce replies.
@@ -153,12 +153,12 @@ def run(self, prompt: str):
             metadata_dict["finish_reason"] = response.finish_reason
             metadata = [metadata_dict]
             self._check_truncated_answers(metadata)
-            return {"replies": replies, "metadata": metadata}
+            return {"replies": replies, "meta": metadata}
 
         metadata = [{"finish_reason": resp.finish_reason} for resp in cast(Generations, response)]
         replies = [resp.text for resp in response]
         self._check_truncated_answers(metadata)
-        return {"replies": replies, "metadata": metadata}
+        return {"replies": replies, "meta": metadata}
 
     def _check_truncated_answers(self, metadata: List[Dict[str, Any]]):
         """

integrations/cohere/tests/test_cohere_generators.py

@@ -119,8 +119,8 @@ def test_from_dict(self, monkeypatch):
 
     def test_check_truncated_answers(self, caplog):
         component = CohereGenerator(api_key="test-api-key")
-        metadata = [{"finish_reason": "MAX_TOKENS"}]
-        component._check_truncated_answers(metadata)
+        meta = [{"finish_reason": "MAX_TOKENS"}]
+        component._check_truncated_answers(meta)
         assert caplog.records[0].message == (
             "Responses have been truncated before reaching a natural stopping point. "
             "Increase the max_tokens parameter to allow for longer completions."
@@ -136,8 +136,8 @@ def test_cohere_generator_run(self):
         results = component.run(prompt="What's the capital of France?")
         assert len(results["replies"]) == 1
         assert "Paris" in results["replies"][0]
-        assert len(results["metadata"]) == 1
-        assert results["metadata"][0]["finish_reason"] == "COMPLETE"
+        assert len(results["meta"]) == 1
+        assert results["meta"][0]["finish_reason"] == "COMPLETE"
 
     @pytest.mark.skipif(
         not os.environ.get("COHERE_API_KEY", None),
@@ -174,6 +174,6 @@ def __call__(self, chunk):
 
         assert len(results["replies"]) == 1
         assert "Paris" in results["replies"][0]
-        assert len(results["metadata"]) == 1
-        assert results["metadata"][0]["finish_reason"] == "COMPLETE"
+        assert len(results["meta"]) == 1
+        assert results["meta"][0]["finish_reason"] == "COMPLETE"
         assert callback.responses == results["replies"][0]

integrations/cohere/tests/test_document_embedder.py

@@ -25,7 +25,7 @@ def test_init_default(self):
         assert embedder.timeout == 120
         assert embedder.batch_size == 32
         assert embedder.progress_bar is True
-        assert embedder.metadata_fields_to_embed == []
+        assert embedder.meta_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
 
     def test_init_with_parameters(self):
@@ -40,7 +40,7 @@ def test_init_with_parameters(self):
             timeout=60,
             batch_size=64,
             progress_bar=False,
-            metadata_fields_to_embed=["test_field"],
+            meta_fields_to_embed=["test_field"],
             embedding_separator="-",
         )
         assert embedder.api_key == "test-api-key"
@@ -53,7 +53,7 @@ def test_init_with_parameters(self):
         assert embedder.timeout == 60
         assert embedder.batch_size == 64
         assert embedder.progress_bar is False
-        assert embedder.metadata_fields_to_embed == ["test_field"]
+        assert embedder.meta_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == "-"
 
     def test_to_dict(self):
@@ -71,7 +71,7 @@ def test_to_dict(self):
                 "timeout": 120,
                 "batch_size": 32,
                 "progress_bar": True,
-                "metadata_fields_to_embed": [],
+                "meta_fields_to_embed": [],
                 "embedding_separator": "\n",
             },
         }
@@ -88,7 +88,7 @@ def test_to_dict_with_custom_init_parameters(self):
             timeout=60,
             batch_size=64,
             progress_bar=False,
-            metadata_fields_to_embed=["text_field"],
+            meta_fields_to_embed=["text_field"],
             embedding_separator="-",
         )
         component_dict = embedder_component.to_dict()
@@ -104,7 +104,7 @@ def test_to_dict_with_custom_init_parameters(self):
                 "timeout": 60,
                 "batch_size": 64,
                 "progress_bar": False,
-                "metadata_fields_to_embed": ["text_field"],
+                "meta_fields_to_embed": ["text_field"],
                 "embedding_separator": "-",
             },
         }
@@ -139,4 +139,4 @@ def test_run_wrong_input_format(self):
         with pytest.raises(TypeError, match="CohereDocumentEmbedder expects a list of Documents as input"):
             embedder.run(documents=[1, 2, 3])
 
-        assert embedder.run(documents=[]) == {"documents": [], "metadata": {}}
+        assert embedder.run(documents=[]) == {"documents": [], "meta": {}}

integrations/google_vertex/src/google_vertex_haystack/generators/image_generator.py

@@ -51,5 +51,5 @@ def from_dict(cls, data: Dict[str, Any]) -> "VertexAIImageGenerator":
     def run(self, prompt: str, negative_prompt: Optional[str] = None):
         negative_prompt = negative_prompt or self._kwargs.get("negative_prompt")
         res = self._model.generate_images(prompt=prompt, negative_prompt=negative_prompt, **self._kwargs)
-        images = [ByteStream(data=i._image_bytes, metadata=i.generation_parameters) for i in res.images]
+        images = [ByteStream(data=i._image_bytes, meta=i.generation_parameters) for i in res.images]
         return {"images": images}

integrations/gradient/tests/test_gradient_rag_pipelines.py

@@ -90,4 +90,4 @@ def test_gradient_embedding_retrieval_rag_pipeline(tmp_path):
         assert spyword in generated_answer.data
         assert generated_answer.query == question
         assert hasattr(generated_answer, "documents")
-        assert hasattr(generated_answer, "metadata")
+        assert hasattr(generated_answer, "meta")

integrations/instructor_embedders/instructor_embedders_haystack/instructor_document_embedder.py

@@ -67,7 +67,7 @@ def __init__(
         batch_size: int = 32,
         progress_bar: bool = True,
         normalize_embeddings: bool = False,
-        metadata_fields_to_embed: Optional[List[str]] = None,
+        meta_fields_to_embed: Optional[List[str]] = None,
         embedding_separator: str = "\n",
     ):
         """
@@ -91,7 +91,7 @@ def __init__(
         :param batch_size: Number of strings to encode at once.
         :param progress_bar: If true, displays progress bar during embedding.
         :param normalize_embeddings: If set to true, returned vectors will have the length of 1.
-        :param metadata_fields_to_embed: List of meta fields that should be embedded along with the Document content.
+        :param meta_fields_to_embed: List of meta fields that should be embedded along with the Document content.
         :param embedding_separator: Separator used to concatenate the meta fields to the Document content.
         """
 
@@ -103,7 +103,7 @@ def __init__(
         self.batch_size = batch_size
         self.progress_bar = progress_bar
         self.normalize_embeddings = normalize_embeddings
-        self.metadata_fields_to_embed = metadata_fields_to_embed or []
+        self.meta_fields_to_embed = meta_fields_to_embed or []
         self.embedding_separator = embedding_separator
 
     def to_dict(self) -> Dict[str, Any]:
@@ -119,7 +119,7 @@ def to_dict(self) -> Dict[str, Any]:
             batch_size=self.batch_size,
             progress_bar=self.progress_bar,
             normalize_embeddings=self.normalize_embeddings,
-            metadata_fields_to_embed=self.metadata_fields_to_embed,
+            meta_fields_to_embed=self.meta_fields_to_embed,
             embedding_separator=self.embedding_separator,
         )
 
@@ -160,9 +160,7 @@ def run(self, documents: List[Document]):
         texts_to_embed = []
         for doc in documents:
             meta_values_to_embed = [
-                str(doc.meta[key])
-                for key in self.metadata_fields_to_embed
-                if key in doc.meta and doc.meta[key] is not None
+                str(doc.meta[key]) for key in self.meta_fields_to_embed if key in doc.meta and doc.meta[key] is not None
             ]
             text_to_embed = [
                 self.instruction,

integrations/instructor_embedders/tests/test_instructor_document_embedder.py

@@ -20,7 +20,7 @@ def test_init_default(self):
         assert embedder.batch_size == 32
         assert embedder.progress_bar is True
         assert embedder.normalize_embeddings is False
-        assert embedder.metadata_fields_to_embed == []
+        assert embedder.meta_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
 
     def test_init_with_parameters(self):
@@ -35,7 +35,7 @@ def test_init_with_parameters(self):
             batch_size=64,
             progress_bar=False,
             normalize_embeddings=True,
-            metadata_fields_to_embed=["test_field"],
+            meta_fields_to_embed=["test_field"],
             embedding_separator=" | ",
         )
         assert embedder.model_name_or_path == "hkunlp/instructor-base"
@@ -45,7 +45,7 @@ def test_init_with_parameters(self):
         assert embedder.batch_size == 64
         assert embedder.progress_bar is False
         assert embedder.normalize_embeddings is True
-        assert embedder.metadata_fields_to_embed == ["test_field"]
+        assert embedder.meta_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == " | "
 
     def test_to_dict(self):
@@ -65,7 +65,7 @@ def test_to_dict(self):
                 "progress_bar": True,
                 "normalize_embeddings": False,
                 "embedding_separator": "\n",
-                "metadata_fields_to_embed": [],
+                "meta_fields_to_embed": [],
             },
         }
 
@@ -81,7 +81,7 @@ def test_to_dict_with_custom_init_parameters(self):
             batch_size=64,
             progress_bar=False,
             normalize_embeddings=True,
-            metadata_fields_to_embed=["test_field"],
+            meta_fields_to_embed=["test_field"],
             embedding_separator=" | ",
         )
         embedder_dict = embedder.to_dict()
@@ -95,7 +95,7 @@ def test_to_dict_with_custom_init_parameters(self):
                 "batch_size": 64,
                 "progress_bar": False,
                 "normalize_embeddings": True,
-                "metadata_fields_to_embed": ["test_field"],
+                "meta_fields_to_embed": ["test_field"],
                 "embedding_separator": " | ",
             },
         }
@@ -114,7 +114,7 @@ def test_from_dict(self):
                 "batch_size": 32,
                 "progress_bar": True,
                 "normalize_embeddings": False,
-                "metadata_fields_to_embed": [],
+                "meta_fields_to_embed": [],
                 "embedding_separator": "\n",
             },
         }
@@ -126,7 +126,7 @@ def test_from_dict(self):
         assert embedder.batch_size == 32
         assert embedder.progress_bar is True
         assert embedder.normalize_embeddings is False
-        assert embedder.metadata_fields_to_embed == []
+        assert embedder.meta_fields_to_embed == []
         assert embedder.embedding_separator == "\n"
 
     def test_from_dict_with_custom_init_parameters(self):
@@ -143,7 +143,7 @@ def test_from_dict_with_custom_init_parameters(self):
                 "batch_size": 64,
                 "progress_bar": False,
                 "normalize_embeddings": True,
-                "metadata_fields_to_embed": ["test_field"],
+                "meta_fields_to_embed": ["test_field"],
                 "embedding_separator": " | ",
             },
         }
@@ -155,7 +155,7 @@ def test_from_dict_with_custom_init_parameters(self):
         assert embedder.batch_size == 64
         assert embedder.progress_bar is False
         assert embedder.normalize_embeddings is True
-        assert embedder.metadata_fields_to_embed == ["test_field"]
+        assert embedder.meta_fields_to_embed == ["test_field"]
         assert embedder.embedding_separator == " | "
 
     @patch("instructor_embedders_haystack.instructor_document_embedder._InstructorEmbeddingBackendFactory")
@@ -223,7 +223,7 @@ def test_embed_metadata(self):
         embedder = InstructorDocumentEmbedder(
             model_name_or_path="model",
             instruction="Represent the financial document for retrieval",
-            metadata_fields_to_embed=["meta_field"],
+            meta_fields_to_embed=["meta_field"],
             embedding_separator="\n",
         )
         embedder.embedding_backend = MagicMock()