Spring/spring-ai
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Refactor QianFan model option builder methods

Browse Source 
- Deprecate the builder methods with the prefix `with` and add the new methods
 - Update docs and references
This commit is contained in:
Ilayaperumal Gopinathan
2024-12-17 01:38:04 +00:00
committed by Mark Pollack
parent 071b897951
commit 18bc0cff25
16 changed files with 205 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/chat/qianfan-chat.adoc
View File

@@ -124,8 +124,8 @@ ChatResponse response = chatClient.call(
new Prompt(
"Generate the names of 5 famous pirates.",
QianFanChatOptions.builder()
.withModel(QianFanApi.ChatModel.ERNIE_Speed_8K.getValue())
.withTemperature(0.5)
.model(QianFanApi.ChatModel.ERNIE_Speed_8K.getValue())
.temperature(0.5)
.build()
));
----
@@ -208,9 +208,9 @@ Next, create a `QianFanChatModel` and use it for text generations:
var qianFanApi = new QianFanApi(System.getenv("QIANFAN_API_KEY"), System.getenv("QIANFAN_SECRET_KEY"));
var chatClient = new QianFanChatModel(this.qianFanApi, QianFanChatOptions.builder()
.withModel(QianFanApi.ChatModel.ERNIE_Speed_8K.getValue())
.withTemperature(0.4)
.withMaxTokens(200)
.model(QianFanApi.ChatModel.ERNIE_Speed_8K.getValue())
.temperature(0.4)
.maxTokens(200)
.build());
ChatResponse response = this.chatClient.call(

9
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/embeddings/qianfan-embeddings.adoc
View File

@@ -120,7 +120,7 @@ For example to override the default model name for a specific request:
EmbeddingResponse embeddingResponse = embeddingClient.call(
new EmbeddingRequest(List.of("Hello World", "World is big and salvation is near"),
QianFanEmbeddingOptions.builder()
.withModel("Different-Embedding-Model-Deployment-Name")
.model("Different-Embedding-Model-Deployment-Name")
.build()));
----
@@ -188,10 +188,9 @@ Next, create an `QianFanEmbeddingModel` instance and use it to compute the simil
----
var qianFanApi = new QianFanApi(System.getenv("MINIMAX_API_KEY"), System.getenv("QIANFAN_SECRET_KEY"));
var embeddingClient = new QianFanEmbeddingModel(qianFanApi)
.withDefaultOptions(QianFanChatOptions.build()
.withModel("bge_large_en")
.build());
var embeddingClient = new QianFanEmbeddingModel(api, MetadataMode.EMBED, QianFanEmbeddingOptions.builder()
.model("bge_large_en")
.build());
EmbeddingResponse embeddingResponse = this.embeddingClient
.embedForResponse(List.of("Hello World", "World is big and salvation is near"));

6
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/image/qianfan-image.adoc
View File

@@ -110,9 +110,9 @@ For example to override the QianFan specific options such as quality and the num
ImageResponse response = qianFanImageModel.call(
new ImagePrompt("A light cream colored mini golden doodle",
QianFanImageOptions.builder()
.withN(4)
.withHeight(1024)
.withWidth(1024).build())
.N(4)
.height(1024)
.width(1024).build())
);
----