基于 Langchain 和 ChatGLM、Qwen、Llama 等本地大模型搭建的知识库问答应用,支持 RAG 检索增强与 Agent 能力,可离线部署私有文档问答系统。
用 Python 把数据和 AI 算法快速封装成可上生产环境的 Web 应用,内置数据集成、可视化、任务调度和 MLOps 编排能力。
基于 ComfyUI 的全自动短视频生成引擎,串联文生图、语音合成与视频生成,一条流水线把创意直接做成短视频。
… dead code removed, including the entire leftover Streamlit-era service layer ( 1053, 1054, 1056) - CI now gates every PR on ruff, ESLint, the frontend production build a
…,以及更完善的本地 ASR / 字幕处理支持。 亮点 - 新增 --deep-optimize / Streamlit「深度优化」模式,在候选片段汇总后增加更深入的 AI 检查、边界修正和复核流程,提升片段边界与独立成段质量 - 新增 custom openai 提供商,支持自定义 LLM Model 和 LLM Base URL - 新
…4.9 improves highlight clip quality and makes the Streamlit workflow smoother for longer-running tasks. What's new - Added default-on clip boundary refinement to make hig
…s cookie-based authentication much clearer across Streamlit and CLI. Highlights - Added GLM and MiniMax as supported LLM providers - Added Vietnamese output support - Imp
Added - raglight serve --ui — launches a Streamlit chat interface alongside the REST API - --ui-port option to configure the Streamlit port (default: 8501 ) - Chat tab wi
…f you would like to execute your experiments in a StreamLit UI rather than in a notebook, you can do that with: python pip install prompttools git clone https://github.co