Uses of Class
com.composum.ai.backend.base.service.GPTException

Packages that use GPTException

Package	Description
com.composum.ai.backend.base.service
com.composum.ai.backend.base.service.chat
com.composum.ai.backend.base.service.chat.impl

Uses of GPTException in com.composum.ai.backend.base.service

Subclasses of GPTException in com.composum.ai.backend.base.service

Modifier and Type	Class	Description
static class	GPTException.GPTContextLengthExceededException	{ "error": { "message": "This model's maximum context length is 4097 tokens.
static class	GPTException.GPTRetryableResponseErrorException	An exception that is thrown when the response from the GPT service is not as expected.
static class	GPTException.GPTUserNotificationException	A special exception if the user should be notified about something instead of completing the task.

Methods in com.composum.ai.backend.base.service that return GPTException

Modifier and Type	Method	Description
static GPTException	GPTException.buildException(Integer errorStatusCode, String result)

Uses of GPTException in com.composum.ai.backend.base.service.chat

Methods in com.composum.ai.backend.base.service.chat that throw GPTException

Modifier and Type	Method	Description
String	GPTContentCreationService.executePrompt(String prompt, GPTChatRequest additionalParameters)	Executes a given prompt from the user using ChatGPT.
String	GPTContentCreationService.executePromptOnText(String prompt, String text, GPTChatRequest additionalParameters)	Executes a given prompt from the user using ChatGPT, using the given text as context.
void	GPTContentCreationService.executePromptOnTextStreaming(String prompt, String text, GPTChatRequest additionalParameters, GPTCompletionCallback callback)	Executes a given prompt from the user using ChatGPT, using the given text as context.
void	GPTContentCreationService.executePromptStreaming(String prompt, GPTChatRequest additionalParameters, GPTCompletionCallback callback)	Executes a given prompt from the user using ChatGPT.
List<String>	GPTEmbeddingService.findMostRelated(String query, List<String> comparedStrings, int limit, GPTConfiguration configuration, GPTEmbeddingService.EmbeddingsCache cache)	Determines the at most limit to query semantically closest of the comparedStrings according to the embedding service.
default List<String>	GPTTranslationService.fragmentedTranslation(List<String> texts, String targetLanguage, GPTConfiguration configuration)	Translates the texts into the target language.
List<String>	GPTTranslationService.fragmentedTranslation(List<String> texts, String targetLanguage, GPTConfiguration configuration, List<GPTResponseCheck> translationChecks)	Translates the texts into the target language.
String	GPTContentCreationService.generateDescription(String text, int maxwords, GPTConfiguration configuration)	Generates a description from the given text.
List<String>	GPTContentCreationService.generateKeywords(String text, GPTConfiguration configuration)	Generates a list of keywords from the given text.
List<float[]>	GPTChatCompletionService.getEmbeddings(List<String> texts, GPTConfiguration configuration)	Calculates embeddings for the given list of texts.
List<float[]>	GPTEmbeddingService.getEmbeddings(List<String> texts, GPTConfiguration configuration, GPTEmbeddingService.EmbeddingsCache cache)	Get embeddings for the given texts.
String	GPTChatCompletionService.getSingleChatCompletion(GPTChatRequest request)	The simplest case: give some messages and get a single response.
GPTChatMessagesTemplate	GPTChatCompletionService.getTemplate(String templateName)	Retrieves a (usually cached) chat template with that name.
String	GPTChatCompletionService.shorten(String text, int maxTokens)	Helper method to shorten texts by taking out the middle if too long.
String	GPTTranslationService.singleTranslation(String text, String sourceLanguage, String targetLanguage, GPTConfiguration configuration)	Translate the text from the target to destination language, either Java locale name or language name.
void	GPTChatCompletionService.streamingChatCompletion(GPTChatRequest request, GPTCompletionCallback callback)	Give some messages and receive the streaming response via callback, to reduce waiting time.
void	GPTChatCompletionService.streamingChatCompletionWithToolCalls(GPTChatRequest request, GPTCompletionCallback callback)	Give some messages and receive the streaming response via callback, to reduce waiting time.
void	GPTTranslationService.streamingSingleTranslation(String text, String sourceLanguage, String targetLanguage, GPTConfiguration configuration, GPTCompletionCallback callback)	Translate the text from the target to destination language, either Java locale name or language name.

Constructors in com.composum.ai.backend.base.service.chat that throw GPTException

Constructor	Description
GPTChatMessagesTemplate(InputStream stream, String name)	Reads the template from the stream, which is closed afterwards.
GPTChatMessagesTemplate(ClassLoader classLoader, String name)	Reads the template from the classloader.
GPTChatMessagesTemplate(org.osgi.framework.Bundle bundle, String templateName)	Reads the template from an OSGI bundle.

Uses of GPTException in com.composum.ai.backend.base.service.chat.impl

Methods in com.composum.ai.backend.base.service.chat.impl that throw GPTException

Modifier and Type	Method	Description
void	GPTContentCreationServiceImpl.executePromptOnTextStreaming(String prompt, String text, GPTChatRequest additionalParameters, GPTCompletionCallback callback)
void	GPTContentCreationServiceImpl.executePromptStreaming(String prompt, GPTChatRequest additionalParameters, GPTCompletionCallback callback)
List<String>	GPTEmbeddingServiceImpl.findMostRelated(String query, List<String> comparedStrings, int limit, GPTConfiguration configuration, GPTEmbeddingService.EmbeddingsCache thecache)
protected List<String>	GPTTranslationServiceImpl.fragmentedTranslation(List<String> texts, String targetLanguage, GPTConfiguration configuration, AtomicInteger permittedRetries, List<GPTResponseCheck> translationChecks)
List<String>	GPTTranslationServiceImpl.fragmentedTranslation(List<String> texts, String targetLanguage, GPTConfiguration configuration, List<GPTResponseCheck> translationChecks)	We join all text fragments we have to translate into one big texts separated with separators like `%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% 573472 %%%%%%%%%%%%%%%%` and then translate that.
protected List<String>	GPTTranslationServiceImpl.fragmentedTranslationDivideAndConquer(List<String> texts, String targetLanguage, GPTConfiguration configuration, AtomicInteger permittedRetries, List<GPTResponseCheck> translationChecks)	We try to translate the whole lot of texts.
List<float[]>	GPTChatCompletionServiceImpl.getEmbeddings(List<String> texts, GPTConfiguration configuration)
List<float[]>	GPTEmbeddingServiceImpl.getEmbeddings(List<String> texts, GPTConfiguration configuration, GPTEmbeddingService.EmbeddingsCache cache)
String	GPTChatCompletionServiceImpl.getSingleChatCompletion(GPTChatRequest request)
GPTChatMessagesTemplate	GPTChatCompletionServiceImpl.getTemplate(String templateName)
void	GPTChatCompletionServiceImpl.streamingChatCompletion(GPTChatRequest request, GPTCompletionCallback callback)
void	GPTChatCompletionServiceImpl.streamingChatCompletionWithToolCalls(GPTChatRequest request, GPTCompletionCallback callback)
void	GPTTranslationServiceImpl.streamingSingleTranslation(String text, String sourceLanguage, String targetLanguage, GPTConfiguration configuration, GPTCompletionCallback callback)