dspy.Image¶
dspy.Image(url: Any = None, *, download: bool = False, verify: bool = True, **data)
¶
Bases: Type
Create an Image.
Parameters¶
url: The image source. Supported values include
- ``str``: HTTP(S)/GS URL or local file path
- ``bytes``: raw image bytes
- ``PIL.Image.Image``: a PIL image instance
- ``dict`` with a single ``{"url": value}`` entry (legacy form)
- already encoded data URI
download
Whether remote URLs should be downloaded to infer their MIME type.
verify
Whether to verify SSL certificates when downloading images from URLs. Set to False for self-signed certificates. Default is True.
Any additional keyword arguments are passed to :class:pydantic.BaseModel.
Source code in .venv/lib/python3.14/site-packages/dspy/adapters/types/image.py
Functions¶
adapt_to_native_lm_feature(signature: type[Signature], field_name: str, lm: LM, lm_kwargs: dict[str, Any]) -> type[Signature]
classmethod
¶
Adapt the custom type to the native LM feature if possible.
When the LM and configuration supports the related native LM feature, e.g., native tool calling, native
reasoning, etc., we adapt the signature and lm_kwargs to enable the native LM feature.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
signature
|
type[Signature]
|
The DSPy signature for the LM call. |
required |
field_name
|
str
|
The name of the field in the signature to adapt to the native LM feature. |
required |
lm
|
LM
|
The LM instance. |
required |
lm_kwargs
|
dict[str, Any]
|
The keyword arguments for the LM call, subject to in-place updates if adaptation if required. |
required |
Returns:
| Type | Description |
|---|---|
type[Signature]
|
The adapted signature. If the custom type is not natively supported by the LM, return the original |
type[Signature]
|
signature. |
Source code in .venv/lib/python3.14/site-packages/dspy/adapters/types/base_type.py
description() -> str
classmethod
¶
extract_custom_type_from_annotation(annotation)
classmethod
¶
Extract all custom types from the annotation.
This is used to extract all custom types from the annotation of a field, while the annotation can
have arbitrary level of nesting. For example, we detect Tool is in list[dict[str, Tool]].
Source code in .venv/lib/python3.14/site-packages/dspy/adapters/types/base_type.py
format() -> list[dict[str, Any]] | str
cached
¶
Source code in .venv/lib/python3.14/site-packages/dspy/adapters/types/image.py
from_PIL(pil_image)
classmethod
¶
Source code in .venv/lib/python3.14/site-packages/dspy/adapters/types/image.py
from_file(file_path: str)
classmethod
¶
from_url(url: str, download: bool = False)
classmethod
¶
Source code in .venv/lib/python3.14/site-packages/dspy/adapters/types/image.py
is_streamable() -> bool
classmethod
¶
parse_lm_response(response: str | dict[str, Any]) -> Optional[Type]
classmethod
¶
Parse a LM response into the custom type.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
response
|
str | dict[str, Any]
|
A LM response. |
required |
Returns:
| Type | Description |
|---|---|
Optional[Type]
|
A custom type object. |
Source code in .venv/lib/python3.14/site-packages/dspy/adapters/types/base_type.py
parse_stream_chunk(chunk: ModelResponseStream) -> Optional[Type]
classmethod
¶
Parse a stream chunk into the custom type.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
chunk
|
ModelResponseStream
|
A stream chunk. |
required |
Returns:
| Type | Description |
|---|---|
Optional[Type]
|
A custom type object or None if the chunk is not for this custom type. |
Source code in .venv/lib/python3.14/site-packages/dspy/adapters/types/base_type.py
serialize_model()
¶
Source code in .venv/lib/python3.14/site-packages/dspy/adapters/types/base_type.py
:::