Merge branch 'dev' into refactor/loaders

MIGRATION.md

@@ -1,6 +1,142 @@
 # Migration Guide
 
 This document provides instructions for migrating your codebase to accommodate breaking changes introduced in new versions of Griptape.
+## 0.31.X to 0.32.X
+
+### Removed `MediaArtifact`
+
+`MediaArtifact` has been removed. Use `ImageArtifact` or `AudioArtifact` instead.
+
+#### Before
+
+```python
+image_media = MediaArtifact(
+    b"image_data",
+    media_type="image",
+    format="jpeg"
+)
+
+audio_media = MediaArtifact(
+    b"audio_data",
+    media_type="audio",
+    format="wav"
+)
+``` 
+
+#### After
+```python
+image_artifact = ImageArtifact(
+    b"image_data",
+    format="jpeg"
+)
+
+audio_artifact = AudioArtifact(
+    b"audio_data",
+    format="wav"
+)
+```
+
+### `ImageArtifact.format` is now required
+
+`ImageArtifact.format` is now a required parameter. Update any code that does not provide a `format` parameter.
+
+#### Before
+
+```python
+image_artifact = ImageArtifact(
+    b"image_data"
+)
+```
+
+#### After
+```python
+image_artifact = ImageArtifact(
+    b"image_data",
+    format="jpeg"
+)
+```
+
+### Removed `CsvRowArtifact`
+
+`CsvRowArtifact` has been removed. Use `TextArtifact` instead.
+
+#### Before
+
+```python
+artifact = CsvRowArtifact({"name": "John", "age": 30})
+print(artifact.value) # {"name": "John", "age": 30}
+print(type(artifact.value)) # <class 'dict'>
+```
+
+#### After
+```python
+artifact = TextArtifact("name: John\nage: 30")
+print(artifact.value) # name: John\nage: 30
+print(type(artifact.value)) # <class 'str'>
+```
+
+If you require storing a dictionary as an Artifact, you can use `GenericArtifact` instead.
+
+### `CsvLoader`, `DataframeLoader`, and `SqlLoader` return types 
+
+`CsvLoader`, `DataframeLoader`, and `SqlLoader` now return a `list[TextArtifact]` instead of `list[CsvRowArtifact]`.
+
+If you require a dictionary, set a custom `formatter_fn` and then parse the text to a dictionary. 
+
+#### Before
+
+```python
+results = CsvLoader().load(Path("people.csv").read_text())
+
+print(results[0].value) # {"name": "John", "age": 30}
+print(type(results[0].value)) # <class 'dict'>
+```
+
+#### After
+```python
+results = CsvLoader().load(Path("people.csv").read_text())
+
+print(results[0].value) # name: John\nAge: 30
+print(type(results[0].value)) # <class 'str'>
+
+# Customize formatter_fn
+results = CsvLoader(formatter_fn=lambda x: json.dumps(x)).load(Path("people.csv").read_text())
+print(results[0].value) # {"name": "John", "age": 30}
+print(type(results[0].value)) # <class 'str'>
+
+dict_results = [json.loads(result.value) for result in results]
+print(dict_results[0]) # {"name": "John", "age": 30}
+print(type(dict_results[0])) # <class 'dict'>
+```
+
+### Moved `ImageArtifact.prompt` and `ImageArtifact.model` to `ImageArtifact.meta`
+
+`ImageArtifact.prompt` and `ImageArtifact.model` have been moved to `ImageArtifact.meta`.
+
+#### Before
+
+```python
+image_artifact = ImageArtifact(
+    b"image_data",
+    format="jpeg",
+    prompt="Generate an image of a cat",
+    model="DALL-E"
+)
+
+print(image_artifact.prompt, image_artifact.model) # Generate an image of a cat, DALL-E
+```
+
+#### After
+```python
+image_artifact = ImageArtifact(
+    b"image_data",
+    format="jpeg",
+    meta={"prompt": "Generate an image of a cat", "model": "DALL-E"}
+)
+
+print(image_artifact.meta["prompt"], image_artifact.meta["model"]) # Generate an image of a cat, DALL-E
+```
+
 
 ## 0.31.X to 0.32.X
 

docs/griptape-framework/structures/src/drivers_config_7.py

@@ -2,14 +2,15 @@
 
 from griptape.configs import Defaults
 from griptape.configs.drivers import DriversConfig
-from griptape.drivers import AnthropicPromptDriver
+from griptape.drivers import AnthropicPromptDriver, OpenAiEmbeddingDriver
 from griptape.structures import Agent
 
 Defaults.drivers_config = DriversConfig(
     prompt_driver=AnthropicPromptDriver(
         model="claude-3-sonnet-20240229",
         api_key=os.environ["ANTHROPIC_API_KEY"],
-    )
+    ),
+    embedding_driver=OpenAiEmbeddingDriver(),
 )
 
 

griptape/artifacts/__init__.py

@@ -5,7 +5,6 @@
 from .json_artifact import JsonArtifact
 from .blob_artifact import BlobArtifact
 from .boolean_artifact import BooleanArtifact
-from .csv_row_artifact import CsvRowArtifact
 from .list_artifact import ListArtifact
 from .image_artifact import ImageArtifact
 from .audio_artifact import AudioArtifact
@@ -21,7 +20,6 @@
     "JsonArtifact",
     "BlobArtifact",
     "BooleanArtifact",
-    "CsvRowArtifact",
     "ListArtifact",
     "ImageArtifact",
     "AudioArtifact",

griptape/artifacts/base_artifact.py

@@ -16,7 +16,7 @@
 class BaseArtifact(SerializableMixin, ABC):
     """Serves as the base class for all Artifacts.
 
-    Artifacts are used to store data that can be provided as input to, or received as output from, a language model (LLM).
+    Artifacts are used to encapsulate data and enhance it with metadata.
 
     Attributes:
         id: The unique identifier of the Artifact. Defaults to a random UUID.

griptape/artifacts/image_artifact.py

@@ -10,7 +10,7 @@ class ImageArtifact(BlobArtifact):
     """Stores image data.
 
     Attributes:
-        format: The format of the image data.
+        format: The format of the image data. Used when building the MIME type.
         width: The width of the image.
         height: The height of the image
     """

griptape/engines/extraction/csv_extraction_engine.py

@@ -6,7 +6,7 @@
 
 from attrs import Factory, define, field
 
-from griptape.artifacts import CsvRowArtifact, ListArtifact, TextArtifact
+from griptape.artifacts import ListArtifact, TextArtifact
 from griptape.common import Message, PromptStack
 from griptape.engines import BaseExtractionEngine
 from griptape.utils import J2
@@ -40,7 +40,7 @@ def extract(
             item_separator="\n",
         )
 
-    def text_to_csv_rows(self, text: str, column_names: list[str]) -> list[CsvRowArtifact]:
+    def text_to_csv_rows(self, text: str, column_names: list[str]) -> list[TextArtifact]:
         rows = []
 
         with io.StringIO(text) as f:
@@ -52,10 +52,10 @@ def text_to_csv_rows(self, text: str, column_names: list[str]) -> list[CsvRowArt
     def _extract_rec(
         self,
         artifacts: list[TextArtifact],
-        rows: list[CsvRowArtifact],
+        rows: list[TextArtifact],
         *,
         rulesets: Optional[list[Ruleset]] = None,
-    ) -> list[CsvRowArtifact]:
+    ) -> list[TextArtifact]:
         artifacts_text = self.chunk_joiner.join([a.value for a in artifacts])
         system_prompt = self.system_template_generator.render(
             column_names=self.column_names,