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。」"
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。」"
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.
OpenAICompatibleInputStreamPuppyChatter<S extends OpenAICompatiblePromptParameters,T extends Response>
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
the default puppychatter for openai compatible endpoints
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
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. a key that may have conflicts
the second level is a map with a real key and content
the cache implementation allows only text contents
whether a response is good, have to try a gain, or give up and failed