摘要：
CrewAI-Multimodal-Agent https://github.com/mdwoicke/CrewAI-Multimodal-Agent # AI Crew for Reviewing Markdown Syntax ## Introduction This project is an
阅读全文
posted @ 2024-11-07 22:24
lightsong
阅读(118)
推荐(0)
摘要：
import asyncio from langchain_openai import ChatOpenAI from langchain.agents import tool from langchain_core.prompts import ChatPromptTemplate, Messag
阅读全文
posted @ 2024-11-07 22:10
lightsong
阅读(59)
推荐(0)
摘要：
Using environment variables https://www.jenkins.io/doc/pipeline/tour/environment/ pipeline { agent { label '!windows' } environment { DISABLE_AUTH = '
阅读全文
posted @ 2024-10-25 17:27
lightsong
阅读(16)
推荐(0)
摘要：
docker 镜像中的uid 在Docker镜像中，UID（用户标识符）的具体数值并不是固定的，它取决于镜像的构建方式和构建时指定的用户配置。以下是对Docker镜像中UID的详细解释： UID的分配 基础镜像：当从一个基础镜像（如Ubuntu、CentOS等）构建新的Docker镜像时，该基础镜像
阅读全文
posted @ 2024-10-24 22:04
lightsong
阅读(292)
推荐(0)
摘要：
开源监控系统Prometheus的前世今生 http://www.uml.org.cn/itil/202012101.asp https://prometheus.io/docs/introduction/overview/ info数据结构 可以存储任意信息 https://prometheus.
阅读全文
posted @ 2024-10-24 09:36
lightsong
阅读(79)
推荐(0)
摘要：
为什么需要Multi-agent framework？ Multi-agent framework（多智能体框架）之所以被需要，主要基于以下几个方面的原因： 一、突破单智能体的限制 上下文窗口大小限制：在处理长上下文（Long Context）时，单一的智能体可能会受到上下文窗口大小的限制，导致无法
阅读全文
posted @ 2024-10-20 21:21
lightsong
阅读(713)
推荐(0)
摘要：
docker compose secrets https://docs.docker.com/compose/how-tos/use-secrets/ A secret is any piece of data, such as a password, certificate, or API key
阅读全文
posted @ 2024-10-20 18:37
lightsong
阅读(241)
推荐(0)
摘要：
https://stackoverflow.com/questions/34761047/how-to-install-jenkins-plugins-from-command-line https://github.com/jenkinsci/plugin-installation-manager
阅读全文
posted @ 2024-10-17 18:44
lightsong
阅读(161)
推荐(0)
摘要：
Restricting the ability for users to create projects at the Jenkins top-level vs inside Folders https://docs.cloudbees.com/docs/cloudbees-ci-kb/latest
阅读全文
posted @ 2024-10-17 18:21
lightsong
阅读(23)
推荐(0)
摘要：
How to pass multimodal data directly to models https://python.langchain.com/v0.2/docs/how_to/multimodal_inputs/ message = HumanMessage( content=[ {"ty
阅读全文
posted @ 2024-10-16 23:29
lightsong
阅读(138)
推荐(0)
摘要：
funasr https://www.funasr.com/#/ https://github.com/modelscope/FunASR A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrai
阅读全文
posted @ 2024-10-16 22:22
lightsong
阅读(238)
推荐(0)
摘要：
Openstack deployment https://zhuanlan.zhihu.com/p/25433651#:~:text=Fuel%EF%BC%9A%20Mi 部署工具 RDO：REDHAT出品，支持Redhat、CentOS等系统。RDO基于puppet部署各个组件，支持单节点或多节点
阅读全文
posted @ 2024-10-16 21:51
lightsong
阅读(46)
推荐(0)
摘要：
EV录屏 良心软件！ 免费无水印，集视频录制与直播功能于一身的桌面录屏软件 https://www.ieway.cn/evcapture.html 无水印、无录制时长限制 基础功能无使用限制，免费使用 多种录制模式 音频采集 场景编辑 定时录制 直播推流 全屏录制 选区录制 窗口录制 只录摄像头 只
阅读全文
posted @ 2024-10-12 18:04
lightsong
阅读(179)
推荐(0)
摘要：
Dify+Ollama+llava大模型本地搭建个人AI知识库并实现远程访问 https://www.bilibili.com/video/BV1tu24YyEDh/?spm_id_from=333.337.search-card.all.click&vd_source=57e261300f39bf
阅读全文
posted @ 2024-10-09 22:11
lightsong
阅读(28)
推荐(0)
摘要：
twemproxy https://github.com/twitter/twemproxy A fast, light-weight proxy for memcached and redis twemproxy (nutcracker) twemproxy (pronounced "two-em
阅读全文
posted @ 2024-10-06 23:13
lightsong
阅读(29)
推荐(0)
摘要：
openstack hypervisor https://docs.redhat.com/en/documentation/red_hat_openstack_platform/8/html/configuration_reference_guide/section_compute-hypervis
阅读全文
posted @ 2024-10-06 13:03
lightsong
阅读(190)
推荐(0)
摘要：
TaskMatrix https://github.com/chenfei-wu/TaskMatrix TaskMatrix TaskMatrix connects ChatGPT and a series of Visual Foundation Models to enable sending
阅读全文
posted @ 2024-10-06 10:07
lightsong
阅读(52)
推荐(0)
摘要：
RAG-Multi-Modal-Generative-AI-Agent https://github.com/ganeshnehru/RAG-Multi-Modal-Generative-AI-Agent/tree/main router -> each agents. A multimodal R
阅读全文
posted @ 2024-10-05 23:25
lightsong
阅读(46)
推荐(0)
摘要：
pyttsx3 https://github.com/nateshmbhat/pyttsx3 效果太差。 pyttsx3 is a text-to-speech conversion library in Python. Unlike alternative libraries, it works
阅读全文
posted @ 2024-10-05 22:27
lightsong
阅读(264)
推荐(0)
摘要：
litellm https://github.com/BerriAI/litellm/tree/main Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure,
阅读全文
posted @ 2024-10-05 15:22
lightsong
阅读(224)
推荐(0)
摘要：
uv https://docs.astral.sh/uv/ An extremely fast Python package and project manager, written in Rust. Installing Trio's dependencies with a warm cache.
阅读全文
posted @ 2024-10-05 12:47
lightsong
阅读(299)
推荐(0)
摘要：
OS-Copilot https://github.com/OS-Copilot/OS-Copilot An self-improving embodied conversational agent seamlessly integrated into the operating system to
阅读全文
posted @ 2024-10-05 11:59
lightsong
阅读(165)
推荐(0)
摘要：
minio https://github.com/minio/minio MinIO 是在 GNU Affero 通用公共许可证 v3.0 下发布的对象存储系统。它与 Amazon S3 云存储服务兼容 API。它能够处理非结构化数据，例如照片、视频、日志文件、备份和容器图像，支持的最大对象大小为
阅读全文
posted @ 2024-10-03 22:36
lightsong
阅读(168)
推荐(0)
摘要：
agentscope https://doc.agentscope.io/en/index.html Welcome to AgentScope Tutorial AgentScope is an innovative multi-agent platform designed to empowe
阅读全文
posted @ 2024-10-03 17:49
lightsong
阅读(69)
推荐(0)
摘要：
流服务器项目 https://github.com/tiangolo/nginx-rtmp-docker https://github.com/search?q=nginx%20rtmp&type=repositories RTSP 和 RTMP原理&推拉流 https://blog.csdn.ne
阅读全文
posted @ 2024-09-30 10:21
lightsong
阅读(54)
推荐(0)
摘要：
yolov5 https://github.com/ultralytics/yolov5 对rtsp视频流的支持 https://github.com/ultralytics/yolov5/blob/master/detect.py @smart_inference_mode() def run(
阅读全文
posted @ 2024-09-30 09:17
lightsong
阅读(1009)
推荐(0)
摘要：
Top 100+ Generative AI Applications / Use Cases in 2024 https://research.aimultiple.com/generative-ai-applications/#general-generative-ai-applications
阅读全文
posted @ 2024-09-25 16:17
lightsong
阅读(86)
推荐(0)
摘要：
360智脑 https://aiot.360.cn/solutions/factory https://zhuanlan.zhihu.com/p/633755589 1、开放目标检测：自然语言输入快速完成数据标注 一些安防巡店场景下，摄像头会出现被遮挡、发生偏移、镜头对向室外等人为干扰现象，因此，3
阅读全文
posted @ 2024-09-25 10:42
lightsong
阅读(325)
推荐(0)
摘要：
LVM https://yutongbai.com/lvm.html https://zhuanlan.zhihu.com/p/671423679 Large Vision Model（简称LVM）是一种纯粹基于视觉数据进行训练和推理的大型模型，其特点在于无需涉及任何自然语言输入或输出。该模型的提出
阅读全文
posted @ 2024-09-24 19:04
lightsong
阅读(426)
推荐(0)
摘要：
llm overview https://research.aimultiple.com/llmops-tools/ integration framework is our target. Architecture -- llm-app-stack https://github.com/a16z-
阅读全文
posted @ 2024-09-22 17:56
lightsong
阅读(83)
推荐(0)
摘要：
面向真实监控场景的多模态视频理解 https://mp.weixin.qq.com/s/3iPeKtqVEKvWpOb_pqEOXA 3. 多模态异常检测 在监控视频领域，常用到多模态异常检测这一技术。传统的异常检测主要关注视频画面的大规模变化或异常行为，如打架或车祸等。随着技术进步，特别是 GPT
阅读全文
posted @ 2024-09-21 22:22
lightsong
阅读(412)
推荐(0)
摘要：
RAG OVERVIEW https://opendatascience.com/getting-started-with-multimodal-retrieval-augmented-generation/ What is RAG? RAG is an architectural framewor
阅读全文
posted @ 2024-09-21 14:28
lightsong
阅读(456)
推荐(0)
摘要：
https://chuna2.787528.xyz/88223100/p/LangChain-the-hottest-LLM-application-development-framework-for-beginners.html 以 GPT 模型为例： 1.数据滞后，现在训练的数据是到 2021 年
阅读全文
posted @ 2024-09-20 22:44
lightsong
阅读(14)
推荐(0)
摘要：
大模型的能力来源 https://arxiv.org/pdf/2402.18041 大模型合规来源 https://arxiv.org/html/2402.12193v2 大模型的罪恶检测来源 https://www.kaggle.com/datasets/odins0n/ucf-crime-dat
阅读全文
posted @ 2024-09-20 22:33
lightsong
阅读(69)
推荐(0)
摘要：
Phi-2: The surprising power of small language models https://www.microsoft.com/en-us/research/blog/phi-2-the-surprising-power-of-small-language-models
阅读全文
posted @ 2024-09-20 21:52
lightsong
阅读(83)
推荐(0)
摘要：
Pixtral 12B - the first-ever multimodal Mistral model. https://mistral.ai/news/pixtral-12b/ Pixtral 12B in short: Natively multimodal, trained with in
阅读全文
posted @ 2024-09-20 21:29
lightsong
阅读(76)
推荐(0)
摘要：
python_package https://github.com/fanqingsong/python_package Description A production ready python library template Metadata and dependency informatio
阅读全文
posted @ 2024-09-20 18:12
lightsong
阅读(36)
推荐(0)
摘要：
MoneyPrinterTurbo https://github.com/harry0703/MoneyPrinterTurbo/tree/main 利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM. FunCli
阅读全文
posted @ 2024-09-17 11:11
lightsong
阅读(77)
推荐(0)
摘要：
crewAI-examples github demo 文生图 完成读取文章，配图，发tweet。 https://github.com/wassim249/xgrow/blob/master/main.py#L23 文生图 https://github.com/coderphonui/crewai
阅读全文
posted @ 2024-09-16 23:27
lightsong
阅读(279)
推荐(0)
摘要：
autoGPT metagpt crewAI langgraph autogen camel 哪些框架适用于多模态场景？ 特点：CrewAI是一个专门用于创建多模态代理的技术，能够同时处理文本、图像和音频数据。它提供了构建多模态代理所需的工具和库，使得开发者能够更容易地集成不同模型以处理多种数据类型
阅读全文
posted @ 2024-09-16 11:08
lightsong
阅读(1143)
推荐(0)
浙公网安备 33010602011771号