Skip to content

Commit

Permalink
Fix migration
Browse files Browse the repository at this point in the history
  • Loading branch information
@collindutter
collindutter committed Oct 9, 2024
1 parent 250b5f2 commit 689e4e7
Showing 1 changed file with 53 additions and 154 deletions.
207 changes: 53 additions & 154 deletions MIGRATION.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,95 +3,97 @@
This document provides instructions for migrating your codebase to accommodate breaking changes introduced in new versions of Griptape.
## 0.32.X to 0.33.X

### Removed `torch` extra from `transformers` dependency
### Removed `DataframeLoader`

The `torch` extra has been removed from the `transformers` dependency. If you require `torch`, install it separately.
`DataframeLoader` has been removed. Use `CsvLoader.parse` or build `TextArtifact`s from the dataframe instead.

#### Before
```bash
pip install griptape[drivers-prompt-huggingface-hub]

```python
DataframeLoader().load(df)
```

#### After
```bash
pip install griptape[drivers-prompt-huggingface-hub]
pip install torch
```python
# Convert the dataframe to csv bytes and parse it
CsvLoader().parse(bytes(df.to_csv(line_terminator='\r\n', index=False), encoding='utf-8'))
# Or build TextArtifacts from the dataframe
[TextArtifact(row) for row in source.to_dict(orient="records")]
```

### Removed `MediaArtifact`

`MediaArtifact` has been removed. Use `ImageArtifact` or `AudioArtifact` instead.
### `TextLoader`, `PdfLoader`, `ImageLoader`, and `AudioLoader` now take a `str | PathLike` instead of `bytes`.

#### Before

```python
image_media = MediaArtifact(
b"image_data",
media_type="image",
format="jpeg"
)

audio_media = MediaArtifact(
b"audio_data",
media_type="audio",
format="wav"
)
```
PdfLoader().load(Path("attention.pdf").read_bytes())
PdfLoader().load_collection([Path("attention.pdf").read_bytes(), Path("CoT.pdf").read_bytes()])
```

#### After
```python
image_artifact = ImageArtifact(
b"image_data",
format="jpeg"
)
PdfLoader().load("attention.pdf")
PdfLoader().load_collection([Path("attention.pdf"), "CoT.pdf"])
```

audio_artifact = AudioArtifact(
b"audio_data",
format="wav"
)
### Removed `fileutils.load_file` and `fileutils.load_files`

`griptape.utils.file_utils.load_file` and `griptape.utils.file_utils.load_files` have been removed.
You can now pass the file path directly to the Loader.

#### Before

```python
PdfLoader().load(load_file("attention.pdf").read_bytes())
PdfLoader().load_collection(list(load_files(["attention.pdf", "CoT.pdf"]).values()))
```

```python
PdfLoader().load("attention.pdf")
PdfLoader().load_collection(["attention.pdf", "CoT.pdf"])
```

### `ImageArtifact.format` is now required
### Loaders no longer chunk data

`ImageArtifact.format` is now a required parameter. Update any code that does not provide a `format` parameter.
Loaders no longer chunk the data after loading it. If you need to chunk the data, use a [Chunker](https://docs.griptape.ai/stable/griptape-framework/data/chunkers/) after loading the data.

#### Before

```python
image_artifact = ImageArtifact(
b"image_data"
chunks = PdfLoader().load("attention.pdf")
vector_store.upsert_text_artifacts(
{
"griptape": chunks,
}
)
```

#### After
```python
image_artifact = ImageArtifact(
b"image_data",
format="jpeg"
artifact = PdfLoader().load("attention.pdf")
chunks = Chunker().chunk(artifact)
vector_store.upsert_text_artifacts(
{
"griptape": chunks,
}
)
```

### Removed `CsvRowArtifact`

`CsvRowArtifact` has been removed. Use `TextArtifact` instead.
### Removed `torch` extra from `transformers` dependency

#### Before
The `torch` extra has been removed from the `transformers` dependency. If you require `torch`, install it separately.

```python
artifact = CsvRowArtifact({"name": "John", "age": 30})
print(artifact.value) # {"name": "John", "age": 30}
print(type(artifact.value)) # <class 'dict'>
#### Before
```bash
pip install griptape[drivers-prompt-huggingface-hub]
```

#### After
```python
artifact = TextArtifact("name: John\nage: 30")
print(artifact.value) # name: John\nage: 30
print(type(artifact.value)) # <class 'str'>
```bash
pip install griptape[drivers-prompt-huggingface-hub]
pip install torch
```

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]`.
Expand Down Expand Up @@ -124,34 +126,6 @@ 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
```

Renamed `GriptapeCloudKnowledgeBaseVectorStoreDriver` to `GriptapeCloudVectorStoreDriver`.

#### Before
Expand Down Expand Up @@ -188,81 +162,6 @@ driver = OpenAiChatPromptDriver(

## 0.31.X to 0.32.X

### Removed `DataframeLoader`

`DataframeLoader` has been removed. Use `CsvLoader.parse` or build `TextArtifact`s from the dataframe instead.

#### Before

```python
DataframeLoader().load(df)
```

#### After
```python
# Convert the dataframe to csv bytes and parse it
CsvLoader().parse(bytes(df.to_csv(line_terminator='\r\n', index=False), encoding='utf-8'))
# Or build TextArtifacts from the dataframe
[TextArtifact(row) for row in source.to_dict(orient="records")]
```

### `TextLoader`, `PdfLoader`, `ImageLoader`, and `AudioLoader` now take a `str | PathLike` instead of `bytes`.

#### Before
```python
PdfLoader().load(Path("attention.pdf").read_bytes())
PdfLoader().load_collection([Path("attention.pdf").read_bytes(), Path("CoT.pdf").read_bytes()])
```

#### After
```python
PdfLoader().load("attention.pdf")
PdfLoader().load_collection([Path("attention.pdf"), "CoT.pdf"])
```

### Removed `fileutils.load_file` and `fileutils.load_files`

`griptape.utils.file_utils.load_file` and `griptape.utils.file_utils.load_files` have been removed.
You can now pass the file path directly to the Loader.

#### Before

```python
PdfLoader().load(load_file("attention.pdf").read_bytes())
PdfLoader().load_collection(list(load_files(["attention.pdf", "CoT.pdf"]).values()))
```

```python
PdfLoader().load("attention.pdf")
PdfLoader().load_collection(["attention.pdf", "CoT.pdf"])
```

### Loaders no longer chunk data

Loaders no longer chunk the data after loading it. If you need to chunk the data, use a [Chunker](https://docs.griptape.ai/stable/griptape-framework/data/chunkers/) after loading the data.

#### Before

```python
chunks = PdfLoader().load("attention.pdf")
vector_store.upsert_text_artifacts(
{
"griptape": chunks,
}
)
```

#### After
```python
artifact = PdfLoader().load("attention.pdf")
chunks = Chunker().chunk(artifact)
vector_store.upsert_text_artifacts(
{
"griptape": chunks,
}
)
```

### Removed `MediaArtifact`

`MediaArtifact` has been removed. Use `ImageArtifact` or `AudioArtifact` instead.
Expand Down

0 comments on commit 689e4e7

Please sign in to comment.