TextCompletionClientBase Class
Base class for text completion AI services.
Create a new model by parsing and validating input data from keyword arguments.
Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.
self is explicitly positional-only to allow self as a field name.
Constructor
TextCompletionClientBase(*, ai_model_id: Annotated[str, StringConstraints(strip_whitespace=True, to_upper=None, to_lower=None, strict=None, min_length=1, max_length=None, pattern=None)], service_id: str = '')Keyword-Only Parameters
| Name | Description |
|---|---|
|
ai_model_id
Required
|
|
|
service_id
Required
|
|
Methods
| get_streaming_text_content |
This is the method that is called from the kernel to get a stream response from a text-optimized LLM. |
| get_streaming_text_contents |
Create streaming text contents, in the number specified by the settings. |
| get_text_content |
This is the method that is called from the kernel to get a response from a text-optimized LLM. |
| get_text_contents |
Create text contents, in the number specified by the settings. |
get_streaming_text_content
This is the method that is called from the kernel to get a stream response from a text-optimized LLM.
async get_streaming_text_content(prompt: str, settings: PromptExecutionSettings) -> AsyncGenerator[StreamingTextContent | None, Any]Parameters
| Name | Description |
|---|---|
|
prompt
Required
|
The prompt to send to the LLM. |
|
settings
Required
|
<xref:semantic_kernel.connectors.ai.text_completion_client_base.PromptExecutionSettings>
Settings for the request. |
Returns
| Type | Description |
|---|---|
|
A stream representing the response(s) from the LLM. |
get_streaming_text_contents
Create streaming text contents, in the number specified by the settings.
async get_streaming_text_contents(prompt: str, settings: PromptExecutionSettings) -> AsyncGenerator[list[StreamingTextContent], Any]Parameters
| Name | Description |
|---|---|
|
prompt
Required
|
The prompt to send to the LLM. |
|
settings
Required
|
<xref:semantic_kernel.connectors.ai.text_completion_client_base.PromptExecutionSettings>
Settings for the request. |
get_text_content
This is the method that is called from the kernel to get a response from a text-optimized LLM.
async get_text_content(prompt: str, settings: PromptExecutionSettings) -> TextContent | NoneParameters
| Name | Description |
|---|---|
|
prompt
Required
|
The prompt to send to the LLM. |
|
settings
Required
|
<xref:semantic_kernel.connectors.ai.text_completion_client_base.PromptExecutionSettings>
Settings for the request. |
Returns
| Type | Description |
|---|---|
|
A string or list of strings representing the response(s) from the LLM. |
get_text_contents
Create text contents, in the number specified by the settings.
async get_text_contents(prompt: str, settings: PromptExecutionSettings) -> list[TextContent]Parameters
| Name | Description |
|---|---|
|
prompt
Required
|
The prompt to send to the LLM. |
|
settings
Required
|
<xref:semantic_kernel.connectors.ai.text_completion_client_base.PromptExecutionSettings>
Settings for the request. |
Returns
| Type | Description |
|---|---|
|
A string or list of strings representing the response(s) from the LLM. |
Attributes
ai_model_id
ai_model_id: Annotated[str, StringConstraints(strip_whitespace=True, to_upper=None, to_lower=None, strict=None, min_length=1, max_length=None, pattern=None)]service_id
service_id: str