exo/lm-lib
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

lm-lib fixes;

Browse Source 
git-svn-id: svn://home0/lm-lib@3609 71dcc7fd-b1f2-4e5d-bb8e-274146e81173
This commit is contained in:
(no author)
2024-12-18 18:39:04 +00:00
parent d3797e4d6d
commit 35b59043e1
4 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/main/java/de/extio/lmlib/client/textcompletion/ModelNameLoader.java
View File

@@ -39,7 +39,7 @@ class ModelNameLoader implements Runnable {
.uri(uriBuilder -> uriBuilder.path("/v1/models").build()) .uri(uriBuilder -> uriBuilder.path("/v1/models").build())
.retrieve() .retrieve()
.bodyToMono(ModelsResponse.class) .bodyToMono(ModelsResponse.class)
.retryWhen(Retry.backoff(99, Duration.ofSeconds(1)).maxBackoff(Duration.ofSeconds(10)).jitter(0.25d).doAfterRetry(rs -> LOGGER.warn("Request failed", rs.failure()))) .retryWhen(Retry.backoff(99, Duration.ofSeconds(1)).maxBackoff(Duration.ofSeconds(10)).jitter(0.25d).doAfterRetry(rs -> LOGGER.warn("Request failed " + rs.failure().getMessage())))
.block() .block()
.getData() .getData()
.stream() .stream()

2
src/main/java/de/extio/lmlib/client/textcompletion/TextCompletionClient.java
View File

@@ -241,7 +241,7 @@ public class TextCompletionClient implements Client, DisposableBean {
.bodyValue(request) .bodyValue(request)
.retrieve() .retrieve()
.bodyToMono(CompletionResponse.class) .bodyToMono(CompletionResponse.class)
.retryWhen(Retry.backoff(99, Duration.ofSeconds(1)).maxBackoff(Duration.ofSeconds(10)).jitter(0.25d).doAfterRetry(rs -> LOGGER.warn("Request failed", rs.failure()))) .retryWhen(Retry.backoff(99, Duration.ofSeconds(1)).maxBackoff(Duration.ofSeconds(10)).jitter(0.25d).doAfterRetry(rs -> LOGGER.warn("Request failed " + rs.failure().getMessage())))
.block(); .block();
} }

4
src/main/java/de/extio/lmlib/client/token/LlamaServerTokenizer.java
View File

@@ -34,7 +34,7 @@ final class LlamaServerTokenizer implements Tokenizer {
.bodyValue(request) .bodyValue(request)
.retrieve() .retrieve()
.bodyToMono(TokenizeResponse.class) .bodyToMono(TokenizeResponse.class)
.retryWhen(Retry.backoff(99, Duration.ofSeconds(1)).maxBackoff(Duration.ofSeconds(10)).jitter(0.25d).doAfterRetry(rs -> LOGGER.warn("Request failed", rs.failure()))) .retryWhen(Retry.backoff(99, Duration.ofSeconds(1)).maxBackoff(Duration.ofSeconds(10)).jitter(0.25d).doAfterRetry(rs -> LOGGER.warn("Request failed " + rs.failure().getMessage())))
.block(); .block();
return response.tokens(); return response.tokens();
} }
@@ -55,7 +55,7 @@ final class LlamaServerTokenizer implements Tokenizer {
.bodyValue(request) .bodyValue(request)
.retrieve() .retrieve()
.bodyToMono(DetokenizeResponse.class) .bodyToMono(DetokenizeResponse.class)
.retryWhen(Retry.backoff(99, Duration.ofSeconds(1)).maxBackoff(Duration.ofSeconds(10)).jitter(0.25d).doAfterRetry(rs -> LOGGER.warn("Request failed", rs.failure()))) .retryWhen(Retry.backoff(99, Duration.ofSeconds(1)).maxBackoff(Duration.ofSeconds(10)).jitter(0.25d).doAfterRetry(rs -> LOGGER.warn("Request failed " + rs.failure().getMessage())))
.block(); .block();
return response.content(); return response.content();
} }

2
src/test/resources/llama3-local.properties
View File

@@ -7,5 +7,5 @@ topP=1.0
maxContinuations=1 maxContinuations=1
modelProvider=OAI_TEXT_COMPLETION modelProvider=OAI_TEXT_COMPLETION
modelName= modelName=
url=http://localhost:5001 url=http://cruncher4:5001
apiKey= apiKey=