All Classes and Interfaces

Class
Description
 
 
 
 
 
Used in async mode
 
 
 
a conversation message
 
 
 
 
 
 
 
 
 
 
an implementation of PuppyChatter that uses the google gemini aqa api
must be used with GeminiAqaPromptParameters and requires a fact source

usage:
PuppyChatter chatter
= new GeminiAqaPuppyChatter("{google api key}",
null
);
String sessionId=chatter.createSession();
InlinePassages inlinePassages=new InlinePassages();
inlinePassages.setPassages(List.of(
"只見在影片中網紅酷的夢不解台灣影片在國外為何比較不紅,對此,魏德聖認為影視是最容易打文化認同的,但台灣在經濟起飛的時候選擇了科技,相比之下南韓就選擇娛樂,所以會透過電視、電影的方式來達到韓式文化的行銷,魏德聖也認為對民眾來說電影就是生活跟自己比較有關係,但是台灣選擇了台積電就跟我們比較沒關係「這是我最無力感的地方。」",
"影片一曝光也引起許多網友的討論,但有許多網友表示不認同魏德聖導演的想法,網友提到韓國也是從科技業代工起來,甚至有網友認為魏德聖是在牽拖「他直接說沒受重視就好了,不用扯台積」,也有其餘網友提出電影不紅的看法「台灣電影的問題大部分是在沒辦法讓跨語種的觀眾也產生投射,也就是主題太狹窄」、「好看我會看啊~ 但國片就那樣」、「要讓台灣的電影在國外受歡迎,拜託先拍出有水準好片。」",
"2+2=4"));
GeminiAqaPromptParameters parameters=new GeminiAqaPromptParameters("user", inlinePassages);
Response response=chatter.bark(sessionId, "台灣電影在國外爲什麼不紅", parameters);
System.out.println("message="+response.getMessage());
chatter.closeSession(sessionId);
 
 
 
a fact source that connects to google drive to use this class, first, add codenote@api-project-437674419610.iam.gserviceaccount.com as a viewer to the target google drive folder and then pass the id of the folder as a parameter to the constructor
 
 
a rag handler that use google drive to extract chunks from the conversation
 
a special type of inlinepassages that use a google search to obtain passages a baseQuery can be specified as as the initial query the implementation will use the last conversation to construct additional query terms
 
a rag handler that use google search to extract chunks from the conversation
 
 
Several functionalities in the gemini package require a PuppyChatter instance, this class facilitates the initialization of that instance.
 
 
 
 
 
 
an implementation of OpenAICompatiblePromptParameters that uses an InputStream to process the response
sometimes, it may be necessary to transform the original messages, to fulfill the requirements, use this class as a bridge between the original prompts and the effective prompts
 
 
 
 
an implementation of PuppyChatter based on Open Router usage:
PuppyChatter<PromptParameters, Response> chatter=new OpenrouterPuppyChatter("open router key");
String session=chatter.createSession();
Response response=chatter.bark(session, "你好", new PromptParameters("user"));
System.out.println(response.getMessage());
chatter.closeSession(session);
when issuing prompt, a leading model:xxx can be used to specify the model to use
 
 
Parameters for configuring a prompt
 
this implementation expect the given url to be a html page
 
 
 
the response of a prompt
verify a reponse, return whether it is good, ask again, or give up
 
a simple rag handler that just return a predefined list of chunks
 
 
a rag handler that use travily to extract chunks from the conversation
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
the first level is a partial key i.e.
whether a response is good, have to try a gain, or give up and failed