win4r / VideoFinder-Llama3.2-vision-OllamaLinks
VideoFinder is an advanced video analysis tool powered by multimodal AI, designed to help users easily locate and identify specific objects or people within video content. By combining the capabilities of Llama Vision model with a streamlined web interface, it enables real-time, frame-by-frame video analysis with natural language descriptions.
☆166Updated last year
Alternatives and similar repositories for VideoFinder-Llama3.2-vision-Ollama
Users that are interested in VideoFinder-Llama3.2-vision-Ollama are comparing it to the libraries listed below
Sorting:
- 文本语料转训练集工具，txt转dataset☆94Updated last year
- Sample GLM4V + ChatTTS AI assistant☆85Updated last year
- GraphRAG-Ollama-UI + GraphRAG4OpenWebUI 融合版（有gradio webui配置生成RAG索引，有fastapi提供RAG API服务）☆104Updated last year
- An common framework for voice and text interactions with LLMs☆98Updated last year
- This repo is to use chatTTS and Ollama to create local LLM audio tool.☆34Updated last year
- generate ppt with llm☆104Updated last year
- ☆273Updated 10 months ago
- 构建一个前端页面，通过flask框架实现OpenManus的前端调用。☆205Updated 7 months ago
- 视频理解：千问视频多模态模型 & Dify☆65Updated last year
- Convert files into markdown to help RAG or LLM understand, based on markitdown and MinerU, which could provide high quality pdf parser.☆131Updated 7 months ago
- AutoGen最新架构v0.4正式发布第一个稳定版本，v0.4是对AutoGen的一次从头开始的重写，目的是为构建Agent创建一个更健壮、可扩展、更易用的跨语言库，其应用接口采用分层架构设计，存在多套软件接口用以满足不同的场景需求 。☆112Updated 7 months ago
- The AI-powered PPT generation service based on ChatPPT can create presentations based on themes, requirements, or uploaded documents, sup…☆115Updated 2 months ago
- Using GPT to parse PDF☆102Updated last year
- 与 https://github.com/tonori/mem0ai-api 配合使用的非官方的 mem0ai provider.☆47Updated last year
- A function calling tool can be deployed to Cloudflare Workers with openapi schema☆101Updated last year
- 为AI带路党Pro视频准备☆276Updated 8 months ago
- 本项目主要实现使用FastAPI后端框架+CrewAI实现AI Agent复杂工作流。代码实现CrewAI的Flows功能，并支持Flow运行中间结果进行持久化存储和查询(MySQL)，支持多Flow并行(Celery是一个强大的异步任务队列/作业队列库)。☆105Updated 7 months ago
- virtualwife-llm-factory 是一个llm训练框架，用于解决虚拟角色训练入门门槛高的问题，该框架具备自动生成语料，性格塑造评估，基于国产llm微调训练等核心能力，目前还在开发，可以点个star~ 关注一下☆50Updated 5 months ago
- The tool is used for building and driving workflows specifically tailored for AI initiatives. It can be used to construct AI agents.☆160Updated last year
- 使用 FastAPI、Streamlit本地部署ChatTTS文本转语音模型，并通过 Docker Compose 进行容器化部署。☆27Updated last year
- 使用CrewAI+FastAPI搭建多Agent协作应用并对外提供API服务，同时支持gpt、国产大模型、Ollama本地大模型。☆144Updated last year
- ☆148Updated last year
- LLM voice chat project by Connect ChatTTS with Local Ollama, 连接本地部署的 Ollama 和 ChatTTS，实现和LLM的语音对话☆65Updated last year
- ☆289Updated last year
- MinerU API server☆81Updated 11 months ago
- 一个基于多模态向量模型及视觉多模态模型构建的图片搜索引擎&管理系统，实现精准的以文搜文，文搜图、以图搜图多种智能检索方式。An image search engine management system built upon multimodal vector models…☆72Updated 2 months ago
- 添加🚀流式 Web 服务到 GraphRAG，兼容 OpenAI SDK，支持可访问的实体链接🔗，支持建议问题，兼容本地嵌入模型，修复诸多问题。Add streaming web server to GraphRAG, compatible with OpenAI SD…☆260Updated 7 months ago
- GraphRAG4OpenWebUI integrates Microsoft's GraphRAG technology into Open WebUI, providing a versatile information retrieval API. It combin…☆568Updated 10 months ago
- mcp的webui界面，支持客户端连接多个sse服务端，支持 openai、deepseek、qwen等大模型，另外附上构建的 agent的 stdio和sse的简单 天气查询的完整示例☆36Updated 5 months ago
- ✨🦋 illufly - 【幻蝶】基于记忆蒸馏、资料检索的自我进化智能体☆74Updated 5 months ago