Artifacts are just data

CHANGELOG.md

@@ -11,7 +11,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Changed
 - **BREAKING**: Removed `MediaArtifact`, use `ImageArtifact` or `AudioArtifact` instead.
-- **BREAKING**: Removed `BooleanArtifact`, use `JsonArtifact` instead.
 - **BREAKING**: Removed `CsvRowArtifact`.
 - **BREAKING**: `CsvLoader`, `DataframeLoader`, and `SqlLoader` now return `list[TextArtifact]`.
 - **BREAKING**: Removed `ImageArtifact.media_type`.
@@ -20,8 +19,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - **BREAKING**: Moved `ImageArtifact.prompt` and `ImageArtifact.model` into `ImageArtifact.meta`.
 - **BREAKING**: `ImageArtifact.to_text()` now returns the base64 encoded image.
 - Updated `JsonArtifact` value converter to properly handle more types. 
-- `AudioArtifact` now subclasses `BaseArtifact` instead of `MediaArtifact`.
-- `ImageArtifact` now subclasses `BaseArtifact` instead of `MediaArtifact`.
+- `AudioArtifact` now subclasses `BlobArtifact` instead of `MediaArtifact`.
+- `ImageArtifact` now subclasses `BlobArtifact` instead of `MediaArtifact`.
 - Passing a dictionary as the value to `TextArtifact` will convert to a key-value formatted string. 
 - Removed `__add__` method from `BaseArtifact`, implemented it where necessary.
 

MIGRATION.md

@@ -36,25 +36,6 @@ audio_artifact = AudioArtifact(
 )
 ```
 
-### Removed `BooleanArtifact`
-
-`BooleanArtifact` has been removed. Use `JsonArtifact` instead.
-
-#### Before
-
-```python
-boolean_artifact = BooleanArtifact("true")
-
-print(boolean_artifact.value) # Value is True
-```
-
-#### After
-```python
-json_artifact = JsonArtifact("true")
-
-print(json_artifact.value) # Value is True
-```
-
 ### Removed `CsvRowArtifact`
 
 `CsvRowArtifact` has been removed. Use `TextArtifact` instead.

docs/griptape-framework/data/artifacts.md

@@ -5,54 +5,50 @@ search:
 
 ## Overview
 
-
-**[Artifacts](../../reference/griptape/artifacts/base_artifact.md)** are used to store data that can be provided as input to or received as output from a Language Learning Model (LLM).
+**[Artifacts](../../reference/griptape/artifacts/base_artifact.md)** are the core data structure in Griptape. They are used to encapsulate data and enhance it with metadata.
 
 ## Text
 
-[TextArtifact](../../reference/griptape/artifacts/text_artifact.md)s store textual data. They can be used to count tokens using the [token_count()](../../reference/griptape/artifacts/text_artifact.md#griptape.artifacts.text_artifact.TextArtifact.token_count) method with a tokenizer, generate a text embedding through the [generate_embedding()](../../reference/griptape/artifacts/text_artifact.md#griptape.artifacts.text_artifact.TextArtifact.generate_embedding) method, and access the embedding with the [embedding](../../reference/griptape/artifacts/text_artifact.md#griptape.artifacts.text_artifact.TextArtifact.embedding) property.
+[TextArtifact](../../reference/griptape/artifacts/text_artifact.md)s store textual data. They offer methods such as [token_count()](../../reference/griptape/artifacts/text_artifact.md#griptape.artifacts.text_artifact.TextArtifact.token_count) for counting tokens with a tokenizer, and [generate_embedding()](../../reference/griptape/artifacts/text_artifact.md#griptape.artifacts.text_artifact.TextArtifact.generate_embedding) for creating text embeddings. You can also access the embedding via the [embedding](../../reference/griptape/artifacts/text_artifact.md#griptape.artifacts.text_artifact.TextArtifact.embedding) property.
 
-[TaskMemory](../../reference/griptape/memory/task/task_memory.md) automatically stores `TextArtifacts` returned by tool activities and provides their IDs back to the LLM.
+When `TextArtifact`s are returned from Tools, they will be stored in [Task Memory](../../griptape-framework/structures/task-memory.md) if the Tool has set `off_prompt=True`.
 
-## Image
+## Blob
 
-[ImageArtifact](../../reference/griptape/artifacts/image_artifact.md)s store image data. They include binary image data and metadata such as MIME type, dimensions, and prompt and model information for images returned by [image generation drivers](../drivers/image-generation-drivers.md). They inherit functionality from [BlobArtifacts](#blob).
+[BlobArtifact](../../reference/griptape/artifacts/blob_artifact.md)s store binary large objects (blobs).
 
-## Audio
+When `BlobArtifact`s are returned from Tools, they will be stored in [Task Memory](../../griptape-framework/structures/task-memory.md) if the Tool has set `off_prompt=True`.
 
-[AudioArtifact](../../reference/griptape/artifacts/audio_artifact.md)s store audio content, including binary audio data and metadata such as format, duration, and prompt and model information for audio returned by generative models. They inherit from [BlobArtifacts](#blob).
+### Image
 
-## Action
+[ImageArtifact](../../reference/griptape/artifacts/image_artifact.md)s store image data. This includes binary image data along with metadata such as MIME type and dimensions. They are a subclass of [BlobArtifacts](#blob).
 
-[ActionArtifact](../../reference/griptape/artifacts/action_artifact.md)s represent actions taken by the LLM. Currently, the only supported action is [ToolAction](../../reference/griptape/common/actions/tool_action.md), which is used to execute a [Tool](../../griptape-framework/tools/index.md).
+### Audio
 
-## JSON
+[AudioArtifact](../../reference/griptape/artifacts/audio_artifact.md)s store audio content. This includes binary audio data and metadata such as format, and duration. They are a subclass of [BlobArtifacts](#blob).
 
-[JsonArtifact](../../reference/griptape/artifacts/json_artifact.md)s store JSON-serializable data. Any data assigned to the `value` property is converted using `json.dumps(json.loads(value))`.
-
-## Generic
+## List
 
-[GenericArtifact](../../reference/griptape/artifacts/generic_artifact.md)s act as an escape hatch for passing any type of data that does not fit into any other artifact type. While generally not recommended, they are suitable for specific scenarios. For example, see [talking to a video](../../examples/talk-to-a-video.md), which demonstrates using a `GenericArtifact` to pass a Gemini-specific video file.
+[ListArtifact](../../reference/griptape/artifacts/list_artifact.md)s store lists of Artifacts.
 
-## System Artifacts
+When `ListArtifact`s are returned from Tools, their elements will be stored in [Task Memory](../../griptape-framework/structures/task-memory.md) if the element is either a `TextArtifact` or a `BlobArtifact` and the Tool has set `off_prompt=True`.
 
-These Artifacts don't map to an LLM modality. They must be transformed in some way before they can be used as LLM input.
+## Info
 
-### Blob
+[InfoArtifact](../../reference/griptape/artifacts/info_artifact.md)s store small pieces of textual information. These are useful for conveying messages about the execution or results of an operation, such as "No results found" or "Operation completed successfully."
 
-[BlobArtifact](../../reference/griptape/artifacts/blob_artifact.md)s store binary large objects (blobs) and are used to pass unstructured data back to the LLM via [InfoArtifact](#info).
-
-`TaskMemory` automatically stores `BlobArtifacts` returned by tool activities, allowing them to be reused by other tools.
+## JSON
 
-### Info
+[JsonArtifact](../../reference/griptape/artifacts/json_artifact.md)s store JSON-serializable data. Any data assigned to the `value` property is processed using `json.dumps(json.loads(value))`.
 
-[InfoArtifact](../../reference/griptape/artifacts/info_artifact.md)s store short notifications that are passed back to the LLM without being stored in Task Memory.
+## Error
 
-### Error
+[ErrorArtifact](../../reference/griptape/artifacts/error_artifact.md)s store exception information, providing a structured way to convey errors.
 
-[ErrorArtifact](../../reference/griptape/artifacts/error_artifact.md)s store errors that are passed back to the LLM without being stored in Task Memory.
+## Action
 
-### List
+[ActionArtifact](../../reference/griptape/artifacts/action_artifact.md)s represent actions taken by an LLM. Currently, the only supported action type is [ToolAction](../../reference/griptape/common/actions/tool_action.md), which is used to execute a [Tool](../../griptape-framework/tools/index.md).
 
-[ListArtifact](../../reference/griptape/artifacts/list_artifact.md)s store lists of Artifacts that can be passed to the LLM.
+## Generic
 
+[GenericArtifact](../../reference/griptape/artifacts/generic_artifact.md)s provide a flexible way to pass data that does not fit into any other artifact category. While not generally recommended, they can be useful for specific use cases. For instance, see [talking to a video](../../examples/talk-to-a-video.md), which demonstrates using a `GenericArtifact` to pass a Gemini-specific video file.

griptape/artifacts/__init__.py

@@ -1,27 +1,25 @@
 from .base_artifact import BaseArtifact
-from .base_system_artifact import BaseSystemArtifact
-
+from .error_artifact import ErrorArtifact
+from .info_artifact import InfoArtifact
 from .text_artifact import TextArtifact
+from .json_artifact import JsonArtifact
 from .blob_artifact import BlobArtifact
+from .boolean_artifact import BooleanArtifact
+from .list_artifact import ListArtifact
 from .image_artifact import ImageArtifact
 from .audio_artifact import AudioArtifact
-from .json_artifact import JsonArtifact
 from .action_artifact import ActionArtifact
 from .generic_artifact import GenericArtifact
 
-from .error_artifact import ErrorArtifact
-from .info_artifact import InfoArtifact
-from .list_artifact import ListArtifact
-
 
 __all__ = [
     "BaseArtifact",
-    "BaseSystemArtifact",
     "ErrorArtifact",
     "InfoArtifact",
     "TextArtifact",
     "JsonArtifact",
     "BlobArtifact",
+    "BooleanArtifact",
     "ListArtifact",
     "ImageArtifact",
     "AudioArtifact",

griptape/artifacts/blob_artifact.py

@@ -28,6 +28,10 @@ class BlobArtifact(BaseArtifact):
     encoding: str = field(default="utf-8", kw_only=True)
     encoding_error_handler: str = field(default="strict", kw_only=True)
 
+    @property
+    def mime_type(self) -> str:
+        return "application/octet-stream"
+
     def to_bytes(self) -> bytes:
         return self.value
 

griptape/artifacts/boolean_artifact.py

@@ -9,17 +9,23 @@
 
 @define
 class BooleanArtifact(BaseArtifact):
+    """Stores a boolean value.
+
+    Attributes:
+        value: The boolean value.
+    """
+
     value: bool = field(converter=bool, metadata={"serializable": True})
 
     @classmethod
-    def parse_bool(cls, value: Union[str, bool]) -> BooleanArtifact:  # noqa: FBT001
-        """Convert a string literal or bool to a BooleanArtifact. The string must be either "true" or "false" with any casing."""
+    def parse_bool(cls, value: Union[str, bool]) -> BooleanArtifact:
+        """Convert a string literal or bool to a BooleanArtifact. The string must be either "true" or "false"."""
         if value is not None:
             if isinstance(value, str):
                 if value.lower() == "true":
-                    return BooleanArtifact(True)  # noqa: FBT003
+                    return BooleanArtifact(value=True)
                 elif value.lower() == "false":
-                    return BooleanArtifact(False)  # noqa: FBT003
+                    return BooleanArtifact(value=False)
             elif isinstance(value, bool):
                 return BooleanArtifact(value)
         raise ValueError(f"Cannot convert '{value}' to BooleanArtifact")
@@ -29,3 +35,6 @@ def __add__(self, other: BaseArtifact) -> BooleanArtifact:
 
     def __eq__(self, value: object) -> bool:
         return self.value is value
+
+    def to_text(self) -> str:
+        return str(self.value).lower()

griptape/artifacts/error_artifact.py

@@ -4,11 +4,11 @@
 
 from attrs import define, field
 
-from griptape.artifacts import BaseSystemArtifact
+from griptape.artifacts import BaseArtifact
 
 
 @define
-class ErrorArtifact(BaseSystemArtifact):
+class ErrorArtifact(BaseArtifact):
     """Represents an error that may want to be conveyed to the LLM.
 
     Attributes:
@@ -18,3 +18,6 @@ class ErrorArtifact(BaseSystemArtifact):
 
     value: str = field(converter=str, metadata={"serializable": True})
     exception: Optional[Exception] = field(default=None, kw_only=True, metadata={"serializable": False})
+
+    def to_text(self) -> str:
+        return self.value

griptape/artifacts/image_artifact.py

@@ -4,11 +4,11 @@
 
 from attrs import define, field
 
-from griptape.artifacts import BaseArtifact
+from griptape.artifacts import BlobArtifact
 
 
 @define
-class ImageArtifact(BaseArtifact):
+class ImageArtifact(BlobArtifact):
     """Stores image data.
 
     Attributes:

griptape/artifacts/info_artifact.py

@@ -2,11 +2,11 @@
 
 from attrs import define, field
 
-from griptape.artifacts import BaseSystemArtifact
+from griptape.artifacts import BaseArtifact
 
 
 @define
-class InfoArtifact(BaseSystemArtifact):
+class InfoArtifact(BaseArtifact):
     """Represents helpful info that can be conveyed to the LLM.
 
     For example, "No results found" or "Please try again.".
@@ -16,3 +16,6 @@ class InfoArtifact(BaseSystemArtifact):
     """
 
     value: str = field(converter=str, metadata={"serializable": True})
+
+    def to_text(self) -> str:
+        return self.value

griptape/artifacts/list_artifact.py

@@ -4,14 +4,14 @@
 
 from attrs import Attribute, define, field
 
-from griptape.artifacts import BaseArtifact, BaseSystemArtifact
+from griptape.artifacts import BaseArtifact
 
 if TYPE_CHECKING:
     from collections.abc import Sequence
 
 
 @define
-class ListArtifact(BaseSystemArtifact):
+class ListArtifact(BaseArtifact):
     value: Sequence[BaseArtifact] = field(factory=list, metadata={"serializable": True})
     item_separator: str = field(default="\n\n", kw_only=True, metadata={"serializable": True})
     validate_uniform_types: bool = field(default=False, kw_only=True, metadata={"serializable": True})

griptape/artifacts/text_artifact.py

@@ -41,11 +41,11 @@ def to_text(self) -> str:
     def to_bytes(self) -> bytes:
         return str(self.value).encode(encoding=self.encoding, errors=self.encoding_error_handler)
 
-    def generate_embedding(self, driver: BaseEmbeddingDriver) -> Optional[list[float]]:
+    def generate_embedding(self, driver: BaseEmbeddingDriver) -> list[float]:
         self._embedding.clear()
         self._embedding.extend(driver.embed_string(str(self.value)))
 
-        return self.embedding
+        return self._embedding
 
     def token_count(self, tokenizer: BaseTokenizer) -> int:
         return tokenizer.count_tokens(str(self.value))

griptape/common/prompt_stack/contents/text_message_content.py

@@ -4,7 +4,7 @@
 
 from attrs import define, field
 
-from griptape.artifacts import TextArtifact
+from griptape.artifacts import BaseArtifact, TextArtifact
 from griptape.common import BaseDeltaMessageContent, BaseMessageContent, TextDeltaMessageContent
 
 if TYPE_CHECKING:
@@ -13,7 +13,7 @@
 
 @define
 class TextMessageContent(BaseMessageContent):
-    artifact: TextArtifact = field(metadata={"serializable": True})
+    artifact: BaseArtifact = field(metadata={"serializable": True})
 
     @classmethod
     def from_deltas(cls, deltas: Sequence[BaseDeltaMessageContent]) -> TextMessageContent:

griptape/common/prompt_stack/prompt_stack.py

@@ -7,7 +7,6 @@
 from griptape.artifacts import (
     ActionArtifact,
     BaseArtifact,
-    ErrorArtifact,
     GenericArtifact,
     ImageArtifact,
     ListArtifact,
@@ -70,8 +69,6 @@ def __to_message_content(self, artifact: str | BaseArtifact) -> list[BaseMessage
             return [ImageMessageContent(artifact)]
         elif isinstance(artifact, GenericArtifact):
             return [GenericMessageContent(artifact)]
-        elif isinstance(artifact, ErrorArtifact):
-            return [TextMessageContent(TextArtifact(artifact.to_text()))]
         elif isinstance(artifact, ActionArtifact):
             action = artifact.value
             output = action.output
@@ -81,6 +78,7 @@ def __to_message_content(self, artifact: str | BaseArtifact) -> list[BaseMessage
                 return [ActionResultMessageContent(output, action=action)]
         elif isinstance(artifact, ListArtifact):
             processed_contents = [self.__to_message_content(artifact) for artifact in artifact.value]
+
             return [sub_content for processed_content in processed_contents for sub_content in processed_content]
         else:
-            raise ValueError(f"Unsupported artifact type: {type(artifact)}")
+            return [TextMessageContent(TextArtifact(artifact.to_text()))]

griptape/mixins/__init__.py

@@ -3,7 +3,7 @@
 from .actions_subtask_origin_mixin import ActionsSubtaskOriginMixin
 from .rule_mixin import RuleMixin
 from .serializable_mixin import SerializableMixin
-from .media_artifact_file_output_mixin import ArtifactFileOutputMixin
+from .artifact_file_output_mixin import ArtifactFileOutputMixin
 from .futures_executor_mixin import FuturesExecutorMixin
 from .singleton_mixin import SingletonMixin