win4r / VideoFinder-Llama3.2-vision-Ollama
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.
☆140Updated 5 months ago
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
- 文本语料转训练集工具，txt转dataset☆91Updated 11 months ago
- 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）☆105Updated 8 months ago
- Using GPT to parse PDF☆95Updated 7 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…☆248Updated 3 weeks ago
- generate ppt with llm☆89Updated last year
- Sample GLM4V + ChatTTS AI assistant☆84Updated 10 months ago
- An common framework for voice and text interactions with LLMs☆93Updated 5 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 。☆102Updated last week
- 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。☆25Updated 6 months ago
- ☆148Updated 10 months ago
- This repo is to use chatTTS and Ollama to create local LLM audio tool.☆30Updated 9 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☆47Updated 9 months ago
- 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。☆62Updated 6 months ago
- ChatTTS is a generative speech model for daily dialogue.this fork Support ollama☆43Updated 10 months ago
- ChatTTS HTTP API☆52Updated 10 months ago
- LangChain Tutorial 2 实现 AI 女友 Demo☆51Updated last year
- Convert files into markdown to help RAG or LLM understand, based on markitdown and MinerU, which could provide high quality pdf parser.☆88Updated 3 weeks ago
- ☆21Updated last month
- 🔥 Turn entire websites into LLM-ready markdown☆86Updated 11 months ago
- Unsloth框架在Windows平台微调训练Qwen2大模型，非WSL☆58Updated 10 months ago
- 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☆62Updated 8 months ago
- GraphRAG4OpenWebUI integrates Microsoft's GraphRAG technology into Open WebUI, providing a versatile information retrieval API. It combin…☆496Updated 3 months ago
- 阿里SenseVoice的fastpi封装，采用onnx发布，体积更小，附带量化模型，支持GPU。支持从URL文件进行语音识别。☆78Updated 7 months ago
- 异步语音对话组件。☆19Updated last month
- ☆37Updated last year
- 无缝集成处理和调度 Dify & Dify on WeChat，Web 可视化多用户管理/一键启动 ChatBot，简化了令人惊叹且响应迅速的 ChatBot 应用程序的创建。☆65Updated 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)。☆73Updated last week
- 基于Linly-Talker数字人改版的教育系统，包含网课总结、数字人 对话、Chatbot对话，项目可在autodl部署☆27Updated 10 months ago
- 与 https://github.com/tonori/mem0ai-api 配合使用的非官方的 mem0ai provider.☆49Updated 9 months ago
- GOT-OCR的GUI版本，提供OCR、导出PDF、批处理等功能，但不提供训练功能☆168Updated last month