Config
Configuration schemas for gllm-inference.
AutoUploadConfig
Bases: BaseModel
Configuration for automatic file upload behavior.
Attributes:
| Name | Type | Description |
|---|---|---|
enabled |
bool
|
Whether automatic uploads are enabled. Defaults to True. |
max_concurrency |
int
|
Maximum number of simultaneous upload tasks. Must be at least 1. Defaults to 8. |
ClientConfig
Bases: BaseModel
Configuration for the underlying HTTP client used by an LM/EM invoker.
Attributes:
| Name | Type | Description |
|---|---|---|
lifecycle |
ClientLifecycle
|
The client ownership lifecycle. |
http_client |
Any | None
|
An externally built async HTTP client (e.g. |
manager |
ClientManager | None
|
An explicit, caller-owned manager this config's client should be
tracked by. Requires |
__eq__(other)
Compares this config to another object by identity, not field values.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
other
|
object
|
The object to compare against. |
required |
Returns:
| Name | Type | Description |
|---|---|---|
bool |
bool
|
True if |
__hash__()
Hashes this config by identity, not field values.
Returns:
| Name | Type | Description |
|---|---|---|
int |
int
|
This instance's identity hash. |
ThinkingConfig
Bases: BaseModel
Configuration for thinking behavior.
Attributes:
| Name | Type | Description |
|---|---|---|
enabled |
bool
|
Whether thinking is enabled. Defaults to False. |
kwargs |
dict[str, Any]
|
Additional thinking-related keyword arguments. Defaults to an empty dictionary. |
TruncationConfig
Bases: BaseModel
Configuration for text truncation behavior.
Attributes:
| Name | Type | Description |
|---|---|---|
max_length |
int
|
Maximum length of text content. Required. |
truncate_side |
TruncateSide | None
|
Side to truncate from when max_length is exceeded. 1. TruncateSide.RIGHT: Keep the beginning of the text, truncate from the end (default) 2. TruncateSide.LEFT: Keep the end of the text, truncate from the beginning If None, defaults to TruncateSide.RIGHT |