dspy.ChatAdapter¶
dspy.ChatAdapter(callbacks: list[BaseCallback] | None = None, use_native_function_calling: bool = False, native_response_types: list[type[Type]] | None = None)
¶
Bases: Adapter
Parameters:
Name | Type | Description | Default |
---|---|---|---|
callbacks
|
list[BaseCallback] | None
|
List of callback functions to execute during |
None
|
use_native_function_calling
|
bool
|
Whether to enable native function calling capabilities when the LM supports it.
If True, the adapter will automatically configure function calling when input fields contain |
False
|
native_response_types
|
list[type[Type]] | None
|
List of output field types that should be handled by native LM features rather than
adapter parsing. For example, |
None
|
Source code in dspy/adapters/base.py
Functions¶
__call__(lm: LM, lm_kwargs: dict[str, Any], signature: type[Signature], demos: list[dict[str, Any]], inputs: dict[str, Any]) -> list[dict[str, Any]]
¶
Source code in dspy/adapters/chat_adapter.py
acall(lm: LM, lm_kwargs: dict[str, Any], signature: type[Signature], demos: list[dict[str, Any]], inputs: dict[str, Any]) -> list[dict[str, Any]]
async
¶
Source code in dspy/adapters/chat_adapter.py
format(signature: type[Signature], demos: list[dict[str, Any]], inputs: dict[str, Any]) -> list[dict[str, Any]]
¶
Format the input messages for the LM call.
This method converts the DSPy structured input along with few-shot examples and conversation history into multiturn messages as expected by the LM. For custom adapters, this method can be overridden to customize the formatting of the input messages.
In general we recommend the messages to have the following structure:
[
{"role": "system", "content": system_message},
# Begin few-shot examples
{"role": "user", "content": few_shot_example_1_input},
{"role": "assistant", "content": few_shot_example_1_output},
{"role": "user", "content": few_shot_example_2_input},
{"role": "assistant", "content": few_shot_example_2_output},
...
# End few-shot examples
# Begin conversation history
{"role": "user", "content": conversation_history_1_input},
{"role": "assistant", "content": conversation_history_1_output},
{"role": "user", "content": conversation_history_2_input},
{"role": "assistant", "content": conversation_history_2_output},
...
# End conversation history
{"role": "user", "content": current_input},
]
And system message should contain the field description, field structure, and task description.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
signature
|
type[Signature]
|
The DSPy signature for which to format the input messages. |
required |
demos
|
list[dict[str, Any]]
|
A list of few-shot examples. |
required |
inputs
|
dict[str, Any]
|
The input arguments to the DSPy module. |
required |
Returns:
Type | Description |
---|---|
list[dict[str, Any]]
|
A list of multiturn messages as expected by the LM. |
Source code in dspy/adapters/base.py
215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 |
|
format_assistant_message_content(signature: type[Signature], outputs: dict[str, Any], missing_field_message=None) -> str
¶
Source code in dspy/adapters/chat_adapter.py
format_conversation_history(signature: type[Signature], history_field_name: str, inputs: dict[str, Any]) -> list[dict[str, Any]]
¶
Format the conversation history.
This method formats the conversation history and the current input as multiturn messages.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
signature
|
type[Signature]
|
The DSPy signature for which to format the conversation history. |
required |
history_field_name
|
str
|
The name of the history field in the signature. |
required |
inputs
|
dict[str, Any]
|
The input arguments to the DSPy module. |
required |
Returns:
Type | Description |
---|---|
list[dict[str, Any]]
|
A list of multiturn messages. |
Source code in dspy/adapters/base.py
format_demos(signature: type[Signature], demos: list[dict[str, Any]]) -> list[dict[str, Any]]
¶
Format the few-shot examples.
This method formats the few-shot examples as multiturn messages.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
signature
|
type[Signature]
|
The DSPy signature for which to format the few-shot examples. |
required |
demos
|
list[dict[str, Any]]
|
A list of few-shot examples, each element is a dictionary with keys of the input and output fields of the signature. |
required |
Returns:
Type | Description |
---|---|
list[dict[str, Any]]
|
A list of multiturn messages. |
Source code in dspy/adapters/base.py
format_field_description(signature: type[Signature]) -> str
¶
Source code in dspy/adapters/chat_adapter.py
format_field_structure(signature: type[Signature]) -> str
¶
ChatAdapter
requires input and output fields to be in their own sections, with section header using markers
[[ ## field_name ## ]]
. An arbitrary field completed
([[ ## completed ## ]]) is added to the end of the
output fields section to indicate the end of the output fields.
Source code in dspy/adapters/chat_adapter.py
format_field_with_value(fields_with_values: dict[FieldInfoWithName, Any]) -> str
¶
Formats the values of the specified fields according to the field's DSPy type (input or output), annotation (e.g. str, int, etc.), and the type of the value itself. Joins the formatted values into a single string, which is is a multiline string if there are multiple fields.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
fields_with_values
|
dict[FieldInfoWithName, Any]
|
A dictionary mapping information about a field to its corresponding value. |
required |
Returns:
Type | Description |
---|---|
str
|
The joined formatted values of the fields, represented as a string |
Source code in dspy/adapters/chat_adapter.py
format_finetune_data(signature: type[Signature], demos: list[dict[str, Any]], inputs: dict[str, Any], outputs: dict[str, Any]) -> dict[str, list[Any]]
¶
Format the call data into finetuning data according to the OpenAI API specifications.
For the chat adapter, this means formatting the data as a list of messages, where each message is a dictionary with a "role" and "content" key. The role can be "system", "user", or "assistant". Then, the messages are wrapped in a dictionary with a "messages" key.
Source code in dspy/adapters/chat_adapter.py
format_task_description(signature: type[Signature]) -> str
¶
Source code in dspy/adapters/chat_adapter.py
format_user_message_content(signature: type[Signature], inputs: dict[str, Any], prefix: str = '', suffix: str = '', main_request: bool = False) -> str
¶
Source code in dspy/adapters/chat_adapter.py
parse(signature: type[Signature], completion: str) -> dict[str, Any]
¶
Source code in dspy/adapters/chat_adapter.py
user_message_output_requirements(signature: type[Signature]) -> str
¶
Returns a simplified format reminder for the language model.
In chat-based interactions, language models may lose track of the required output format as the conversation context grows longer. This method generates a concise reminder of the expected output structure that can be included in user messages.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
signature
|
Type[Signature]
|
The DSPy signature defining the expected input/output fields. |
required |
Returns:
Name | Type | Description |
---|---|---|
str |
str
|
A simplified description of the required output format. |
Note
This is a more lightweight version of format_field_structure
specifically designed
for inline reminders within chat messages.
Source code in dspy/adapters/chat_adapter.py
:::