Skip to content

feat: [DevOps] Update prompt-registry specification #1031

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
sap-ai-sdk-bot wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat: [DevOps] Update prompt-registry specification #1031

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 9 additions & 3 deletions ...s/prompt-registry/src/main/java/com/sap/ai/sdk/prompt/registry/model/LLMModelDetails.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -169,7 +169,9 @@ public void setParams(@Nullable final Map<String, Object> params) {
* Set the timeout of this {@link LLMModelDetails} instance and return the same instance.
*
* @param timeout Timeout for the LLM request in seconds. This parameter is currently ignored for
* Vertex AI models. Minimum: 1 Maximum: 1200
* Vertex AI models. Values above 600s may not be honored due to infrastructure connection
* limits; in practice this primarily affects non-streaming calls where the connection may be
* idle while waiting for a response. Minimum: 1 Maximum: 1200
* @return The same instance of this {@link LLMModelDetails} class
*/
@Nonnull
Expand All @@ -180,7 +182,9 @@ public LLMModelDetails timeout(@Nullable final Integer timeout) {

/**
* Timeout for the LLM request in seconds. This parameter is currently ignored for Vertex AI
* models. minimum: 1 maximum: 1200
* models. Values above 600s may not be honored due to infrastructure connection limits; in
* practice this primarily affects non-streaming calls where the connection may be idle while
* waiting for a response. minimum: 1 maximum: 1200
*
* @return timeout The timeout of this {@link LLMModelDetails} instance.
*/
Expand All @@ -193,7 +197,9 @@ public Integer getTimeout() {
* Set the timeout of this {@link LLMModelDetails} instance.
*
* @param timeout Timeout for the LLM request in seconds. This parameter is currently ignored for
* Vertex AI models. Minimum: 1 Maximum: 1200
* Vertex AI models. Values above 600s may not be honored due to infrastructure connection
* limits; in practice this primarily affects non-streaming calls where the connection may be
* idle while waiting for a response. Minimum: 1 Maximum: 1200
*/
public void setTimeout(@Nullable final Integer timeout) {
this.timeout = timeout;
Expand Down
7 changes: 6 additions & 1 deletion ...ces/prompt-registry/src/main/java/com/sap/ai/sdk/prompt/registry/model/LlamaGuard38b.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,12 @@
import javax.annotation.Nonnull;
import javax.annotation.Nullable;

/** Filter configuration for Llama Guard 3 8B */
/**
* Filter configuration for Llama Guard 3 8B **DEPRECATED**: will be removed 2027-09-20.
*
* @deprecated
*/
@Deprecated
// CHECKSTYLE:OFF
public class LlamaGuard38b
// CHECKSTYLE:ON
Expand Down
9 changes: 8 additions & 1 deletion ...egistry/src/main/java/com/sap/ai/sdk/prompt/registry/model/LlamaGuard38bFilterConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,12 @@
import javax.annotation.Nonnull;
import javax.annotation.Nullable;

/** LlamaGuard38bFilterConfig */
/**
* Filter configuration for Llama Guard 3 8B **DEPRECATED**: will be removed 2027-09-20.
*
* @deprecated
*/
@Deprecated
// CHECKSTYLE:OFF
public class LlamaGuard38bFilterConfig implements InputFilterConfig, OutputFilterConfig
// CHECKSTYLE:ON
Expand Down Expand Up @@ -143,7 +148,9 @@ public LlamaGuard38bFilterConfig config(@Nonnull final LlamaGuard38b config) {
* Get config
*
* @return config The config of this {@link LlamaGuard38bFilterConfig} instance.
* @deprecated
*/
@Deprecated
@Nonnull
public LlamaGuard38b getConfig() {
return config;
Expand Down
7 changes: 5 additions & 2 deletions core-services/prompt-registry/src/main/resources/spec/prompt-registry.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1452,7 +1452,7 @@ components:
stream_options:
include_usage: true
timeout:
description: Timeout for the LLM request in seconds. This parameter is currently ignored for Vertex AI models.
description: Timeout for the LLM request in seconds. This parameter is currently ignored for Vertex AI models. Values above 600s may not be honored due to infrastructure connection limits; in practice this primarily affects non-streaming calls where the connection may be idle while waiting for a response.
type: integer
default: 600
minimum: 1
Expand Down Expand Up @@ -1517,7 +1517,8 @@ components:
config:
$ref: '#/components/schemas/AzureContentSafetyInput'
LlamaGuard38b:
description: Filter configuration for Llama Guard 3 8B
deprecated: true
description: 'Filter configuration for Llama Guard 3 8B **DEPRECATED**: will be removed 2027-09-20.'
type: object
additionalProperties: false
minProperties: 1
Expand Down Expand Up @@ -1551,6 +1552,8 @@ components:
code_interpreter_abuse:
type: boolean
LlamaGuard38bFilterConfig:
deprecated: true
description: 'Filter configuration for Llama Guard 3 8B **DEPRECATED**: will be removed 2027-09-20.'
type: object
required:
- type
Expand Down