OpenAi最简洁的Java流式返回接入方式,只需要使用Spring Boot!轻松构建你的带有聊天记忆、画图功能的chatgpt!

源码地址:https://github.com/NiuXiangQian/chatgpt-stream

预览

模型:GPT-3.5-turbo

记忆功能

GPT-3.5-turbo本身不带有记忆功能需要每次把上下文传递过去

int currentToken = (int) (content.length() / TOKEN_CONVERSION_RATE);
        List<Message> history = userSessionUtil.getHistory(sessionId, MessageType.TEXT, (int) ((MAX_TOKEN / TOKEN_CONVERSION_RATE) - currentToken));
        log.info("history:{}", history);
        String historyDialogue = history.stream().map(e -> String.format(e.getUserType().getCode(), e.getMessage())).collect(Collectors.joining());

        String prompt = StringUtils.hasLength(historyDialogue) ? String.format("%sQ:%s\n\n", historyDialogue, content) : content;

流式返回

基于WebFlux+SSE实现

接口需要返回 text/event-stream类型

@GetMapping(value = "/completions/stream", produces = MediaType.TEXT_EVENT_STREAM_VALUE)

返回响应式数据

log.info("prompt:{}", prompt);
        return Flux.create(emitter -> {
            OpenAISubscriber subscriber = new OpenAISubscriber(emitter, sessionId, this, userMessage);
            Flux<String> openAiResponse =
                openAiWebClient.getChatResponse(sessionId, prompt, null, null, null);
            openAiResponse.subscribe(subscriber);
            emitter.onDispose(subscriber);
        });

完整代码:GitHub - NiuXiangQian/chatgpt-stream: OpenAi最简洁的Java流式返回接入方式,没有第三方依赖,只需要使用Spring Boot即可!轻松构建你的带有聊天记忆功能的chatgpt!

帮忙star噢 您的支持就是我的动力

正文到此结束
评论插件初始化中...
Loading...