Reference documentation and code samples for the Google Cloud Dialogflow Cx V3 Client class ModelParameter.
Parameters to be passed to the LLM. If not set, default values will be used.
Generated from protobuf message google.cloud.dialogflow.cx.v3.Generator.ModelParameter
Namespace
Google \ Cloud \ Dialogflow \ Cx \ V3 \ GeneratorMethods
__construct
Constructor.
| Parameters | |
|---|---|
| Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ temperature |
float
The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied. Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random. |
↳ max_decode_steps |
int
The maximum number of tokens to generate. |
↳ top_p |
float
If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k. Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random. |
↳ top_k |
int
If set, the sampling process in each step is limited to the top_k tokens with highest probabilities. Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random. |
getTemperature
The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied.
Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.
| Returns | |
|---|---|
| Type | Description |
float |
|
hasTemperature
clearTemperature
setTemperature
The temperature used for sampling. Temperature sampling occurs after both topP and topK have been applied.
Valid range: [0.0, 1.0] Low temperature = less random. High temperature = more random.
| Parameter | |
|---|---|
| Name | Description |
var |
float
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getMaxDecodeSteps
The maximum number of tokens to generate.
| Returns | |
|---|---|
| Type | Description |
int |
|
hasMaxDecodeSteps
clearMaxDecodeSteps
setMaxDecodeSteps
The maximum number of tokens to generate.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getTopP
If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k.
Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.
| Returns | |
|---|---|
| Type | Description |
float |
|
hasTopP
clearTopP
setTopP
If set, only the tokens comprising the top top_p probability mass are considered. If both top_p and top_k are set, top_p will be used for further refining candidates selected with top_k.
Valid range: (0.0, 1.0]. Small topP = less random. Large topP = more random.
| Parameter | |
|---|---|
| Name | Description |
var |
float
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getTopK
If set, the sampling process in each step is limited to the top_k tokens with highest probabilities.
Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.
| Returns | |
|---|---|
| Type | Description |
int |
|
hasTopK
clearTopK
setTopK
If set, the sampling process in each step is limited to the top_k tokens with highest probabilities.
Valid range: [1, 40] or 1000+. Small topK = less random. Large topK = more random.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|