Yuqiang He

javac -cp extractor/target/features-javac-extractor-1.0.0-SNAPSHOT-jar-with-dependencies.jar -Xplugin:FeaturePlugin QueueDrainObserver.java:2: 错误: 找不到符号 protected final void fastPathOrderedEmit(U value, boolean delayError, Disposable disposable) { ^ 符号: 类 U 位置: 类 QueueDrainObserver QueueDrainObserver.java:2: 错误: 找不到符号 protected final void...

finetune_XrayGLM.py 加载sat 模型时出现错误

24

finetune_XrayGLM.py文件中的第178行 model_type = 'visualglm-6b' model, args = FineTuneVisualGLMModel.from_pretrained(model_type, args) 加载sat库中的模型时报错 Downloading models https://cloud.tsinghua.edu.cn/f/348b98dffcc940b6a09d/?dl=1 into /home/dawnlab/.sat_models/visualglm-6b.zip ... /home/dawnlab/.sat_models/visualglm-6b.zip: 100%|██████████| 41.8k/41.8k [00:00

[Discussion]SQL generation based on agent game

3

### Search before asking - [X] I had searched in the [issues](https://github.com/eosphoros-ai/DB-GPT/issues?q=is%3Aissue) and found no similar feature requirement. ### Description 在工业生产系统中Langchain 和 AutoGPT 使用的 ReAct 就像是儿童木剑,无法应对复杂的场景.需要采用智能体协作方式以及对提示内容进行检索,还需训练打分模型,进行判断提示的合理性. ### Use case 现有的ReAct模式无法满足生产需求...