Model on Producthunt daily

mindcraft

Tue, 23 Sep 2025 15:29:09 +0800

mindcraft-bots/mindcraft

Mindcraft 🧠⛏️

Crafting minds for Minecraft with LLMs and Mineflayer!

[!Caution] Do not connect this bot to public servers with coding enabled. This project allows an LLM to write/execute code on your computer. The code is sandboxed, but still vulnerable to injection attacks. Code writing is disabled by default, you can enable it by setting allow_insecure_coding to true in settings.js. Ye be warned.

Requirements

Minecraft Java Edition (up to v1.21.6, recommend v1.21.1)
Node.js Installed (at least v18)
One of these: OpenAI API Key | Gemini API Key | Anthropic API Key | Replicate API Key | Hugging Face API Key | Groq API Key | Ollama Installed. | Mistral API Key | Qwen API Key [Intl.]/[cn] | Novita AI API Key | Cerebras API Key | Mercury API

Install and Run

Make sure you have the requirements above.
Clone or download this repository (big green button) ‘git clone https://github.com/mindcraft-bots/mindcraft.git'
Rename keys.example.json to keys.json and fill in your API keys (you only need one). The desired model is set in andy.json or other profiles. For other models refer to the table below.
In terminal/command prompt, run npm install from the installed directory
Start a minecraft world and open it to LAN on localhost port 55916
Run node main.js from the installed directory

If you encounter issues, check the FAQ or find support on discord. We are currently not very responsive to github issues. To run tasks please refer to Minecollab Instructions

Tasks

Bot performance can be roughly evaluated with Tasks. Tasks automatically intialize bots with a goal to aquire specific items or construct predefined buildings, and remove the bot once the goal is achieved.

To run tasks, you need python, pip, and optionally conda. You can then install dependencies with pip install -r requirements.txt.

Tasks are defined in json files in the tasks folder, and can be run with: python tasks/run_task_file.py --task_path=tasks/example_tasks.json

For full evaluations, you will need to download and install the task suite. Full instructions.

Model Customization

You can configure project details in settings.js. See file.

You can configure the agent’s name, model, and prompts in their profile like andy.json with the model field. For comprehensive details, see Model Specifications.

API	Config Variable	Example Model name	Docs
`openai`	`OPENAI_API_KEY`	`gpt-4o-mini`	docs
`google`	`GEMINI_API_KEY`	`gemini-2.0-flash`	docs
`anthropic`	`ANTHROPIC_API_KEY`	`claude-3-haiku-20240307`	docs
`xai`	`XAI_API_KEY`	`grok-2-1212`	docs
`deepseek`	`DEEPSEEK_API_KEY`	`deepseek-chat`	docs
`ollama` (local)	n/a	`ollama/sweaterdog/andy-4:micro-q8_0`	docs
`qwen`	`QWEN_API_KEY`	`qwen-max`	Intl./cn
`mistral`	`MISTRAL_API_KEY`	`mistral-large-latest`	docs
`replicate`	`REPLICATE_API_KEY`	`replicate/meta/meta-llama-3-70b-instruct`	docs
`groq` (not grok)	`GROQCLOUD_API_KEY`	`groq/mixtral-8x7b-32768`	docs
`huggingface`	`HUGGINGFACE_API_KEY`	`huggingface/mistralai/Mistral-Nemo-Instruct-2407`	docs
`novita`	`NOVITA_API_KEY`	`novita/deepseek/deepseek-r1`	docs
`openrouter`	`OPENROUTER_API_KEY`	`openrouter/anthropic/claude-3.5-sonnet`	docs
`glhf.chat`	`GHLF_API_KEY`	`glhf/hf:meta-llama/Llama-3.1-405B-Instruct`	docs
`hyperbolic`	`HYPERBOLIC_API_KEY`	`hyperbolic/deepseek-ai/DeepSeek-V3`	docs
`vllm`	n/a	`vllm/llama3`	n/a
`cerebras`	`CEREBRAS_API_KEY`	`cerebras/llama-3.3-70b`	docs
`mercury`	`MERCURY_API_KEY`	`mercury-coder-small`	docs

If you use Ollama, to install the models used by default (generation and embedding), execute the following terminal command: ollama pull sweaterdog/andy-4:micro-q8_0 && ollama pull embeddinggemma

To use Azure, you can reuse the OPENAI_API_KEY environment variable. You can get the key from the Azure portal. See azure.json for an example.

Online Servers

To connect to online servers your bot will need an official Microsoft/Minecraft account. You can use your own personal one, but will need another account if you want to connect too and play with it. To connect, change these lines in settings.js:

"host": "111.222.333.444",
"port": 55920,
"auth": "microsoft",

// rest is same...

[!Important] The bot’s name in the profile.json must exactly match the Minecraft profile name! Otherwise the bot will spam talk to itself.

To use different accounts, Mindcraft will connect with the account that the Minecraft launcher is currently using. You can switch accounts in the launcer, then run node main.js, then switch to your main account after the bot has connected.

Docker Container

If you intend to allow_insecure_coding, it is a good idea to run the app in a docker container to reduce risks of running unknown code. This is strongly recommended before connecting to remote servers.

`1`	`docker run -i -t --rm -v $(pwd):/app -w /app -p 3000-3003:3000-3003 node:latest node main.js`

or simply

`1`	`docker-compose up`

When running in docker, if you want the bot to join your local minecraft server, you have to use a special host address host.docker.internal to call your localhost from inside your docker container. Put this into your settings.js:

`1`	`"host": "host.docker.internal", // instead of "localhost", to join your local minecraft from inside the docker container`

To connect to an unsupported minecraft version, you can try to use viaproxy

Bot Profiles

Bot profiles are json files (such as andy.json) that define:

Bot backend LLMs to use for talking, coding, and embedding.
Prompts used to influence the bot’s behavior.
Examples help the bot perform tasks.

Model Specifications

LLM models can be specified simply as "model": "gpt-4o". However, you can use different models for chat, coding, and embeddings. You can pass a string or an object for these fields. A model object must specify an api, and optionally a model, url, and additional params.

"model": {
  "api": "openai",
  "model": "gpt-4o",
  "url": "https://api.openai.com/v1/",
  "params": {
    "max_tokens": 1000,
    "temperature": 1
  }
},
"code_model": {
  "api": "openai",
  "model": "gpt-4",
  "url": "https://api.openai.com/v1/"
},
"vision_model": {
  "api": "openai",
  "model": "gpt-4o",
  "url": "https://api.openai.com/v1/"
},
"embedding": {
  "api": "openai",
  "url": "https://api.openai.com/v1/",
  "model": "text-embedding-ada-002"
},
"speak_model": {
  "api": "openai",
  "url": "https://api.openai.com/v1/",
  "model": "tts-1",
  "voice": "echo"
}

model is used for chat, code_model is used for newAction coding, vision_model is used for image interpretation, and embedding is used to embed text for example selection. If code_model or vision_model is not specified, model will be used by default. Not all APIs support embeddings or vision.

All apis have default models and urls, so those fields are optional. The params field is optional and can be used to specify additional parameters for the model. It accepts any key-value pairs supported by the api. Is not supported for embedding models.

Embedding Models

Embedding models are used to embed and efficiently select relevant examples for conversation and coding.

Supported Embedding APIs: openai, google, replicate, huggingface, novita

If you try to use an unsupported model, then it will default to a simple word-overlap method. Expect reduced performance, recommend mixing APIs to ensure embedding support.

Specifying Profiles via Command Line

By default, the program will use the profiles specified in settings.js. You can specify one or more agent profiles using the --profiles argument: node main.js --profiles ./profiles/andy.json ./profiles/jill.json

Patches

Some of the node modules that we depend on have bugs in them. To add a patch, change your local node module file and run npx patch-package [package-name]

Citation:

@article{mindcraft2025,
  title = {Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning},
  author = {White*, Isadora and Nottingham*, Kolby and Maniar, Ayush and Robinson, Max and Lillemark, Hansen and Maheshwari, Mehul and Qin, Lianhui and Ammanabrolu, Prithviraj},
  journal = {arXiv preprint arXiv:2504.17950},
  year = {2025},
  url = {https://arxiv.org/abs/2504.17950},
}

rails

Sun, 07 Sep 2025 15:24:20 +0800

rails/rails

Welcome to Rails

What’s Rails?

Rails is a web-application framework that includes everything needed to create database-backed web applications according to the Model-View-Controller (MVC) pattern.

Understanding the MVC pattern is key to understanding Rails. MVC divides your application into three layers: Model, View, and Controller, each with a specific responsibility.

Model layer

The Model layer represents the domain model (such as Account, Product, Person, Post, etc.) and encapsulates the business logic specific to your application. In Rails, database-backed model classes are derived from ActiveRecord::Base. Active Record allows you to present the data from database rows as objects and embellish these data objects with business logic methods. Although most Rails models are backed by a database, models can also be ordinary Ruby classes, or Ruby classes that implement a set of interfaces as provided by the Active Model module.

View layer

The View layer is composed of “templates” that are responsible for providing appropriate representations of your application’s resources. Templates can come in a variety of formats, but most view templates are HTML with embedded Ruby code (ERB files). Views are typically rendered to generate a controller response or to generate the body of an email. In Rails, View generation is handled by Action View.

Controller layer

The Controller layer is responsible for handling incoming HTTP requests and providing a suitable response. Usually, this means returning HTML, but Rails controllers can also generate XML, JSON, PDFs, mobile-specific views, and more. Controllers load and manipulate models, and render view templates in order to generate the appropriate HTTP response. In Rails, incoming requests are routed by Action Dispatch to an appropriate controller, and controller classes are derived from ActionController::Base. Action Dispatch and Action Controller are bundled together in Action Pack.

Frameworks and libraries

Active Record, Active Model, Action Pack, and Action View can each be used independently outside Rails.

In addition to that, Rails also comes with:

Action Mailer, a library to generate and send emails
Action Mailbox, a library to receive emails within a Rails application
Active Job, a framework for declaring jobs and making them run on a variety of queuing backends
Action Cable, a framework to integrate WebSockets with a Rails application
Active Storage, a library to attach cloud and local files to Rails applications
Action Text, a library to handle rich text content
Active Support, a collection of utility classes and standard library extensions that are useful for Rails, and may also be used independently outside Rails

Getting Started

Install Rails at the command prompt if you haven’t yet:
1

$ gem install rails
At the command prompt, create a new Rails application:
1

$ rails new myapp
where “myapp” is the application name.
Change directory to myapp and start the web server:
1 2

$ cd myapp $ bin/rails server
Run with --help or -h for options.
Go to http://localhost:3000 and you’ll see the Rails bootscreen with your Rails and Ruby versions.
Follow the guidelines to start developing your application. You may find the following resources handy:

Contributing

We encourage you to contribute to Ruby on Rails! Please check out the Contributing to Ruby on Rails guide for guidelines about how to proceed. Join us!

Trying to report a possible security vulnerability in Rails? Please check out our security policy for guidelines about how to proceed.

Everyone interacting in Rails and its sub-projects’ codebases, issue trackers, chat rooms, and mailing lists is expected to follow the Rails code of conduct.

License

Ruby on Rails is released under the MIT License.

Product Hunt Daily | 2025-07-08

Tue, 08 Jul 2025 07:31:23 +0000

1. TensorBlock Forge

Tagline: One API for all AI models
Description: Forge is the fast, secure way to connect and run AI models across providers—no more fragmented tools or infrastructure headaches. Just 3 lines of code to switch. OpenAI-compatible. Privacy-first.
Website: open
Product Hunt: View on Product Hunt

Keyword: AI, model, API, machine learning, ML, deep learning, TensorBlock, Forge, OpenAI, multi-cloud, AI platform, model deployment, model management, privacy
VotesCount: 🔺705
Featured: Yes
CreatedAt: 2025-07-07 07:01 AM (UTC)

2. Stepfun Diligence Check

Tagline: AI-powered search with agent-verified citations
Description: StepFun Diligence Check tells you what’s credible — and what’s not. By tracing citations to their sources and validating them with a multi-agent system, it helps you cut through doubt and misinformation.
Website: open
Product Hunt: View on Product Hunt

Keyword: AI-powered search, citation verification, fact-checking, credibility check, source validation, misinformation detection, due diligence, research tool, agent-verified, multi-agent system
VotesCount: 🔺670
Featured: Yes
CreatedAt: 2025-07-07 07:01 AM (UTC)

3. Sara, the AI Interviewer

Tagline: Hire 10X faster. Unbiased structured interviews, 24/7.
Description: Sara is an AI teammate that conducts unbiased voice interviews in 50+ languages, reverse-engineers any job description, scores 100+ technical & behavioral signals, and delivers shareable reports in minutes — so you hire in days, not weeks.
Website: open
Product Hunt: View on Product Hunt

Keyword: AI Interviewer, AI Hiring, Structured Interviews, Unbiased Interviews, Automated Interviews, Recruitment AI, Faster Hiring, 24/7 Interviewing, Candidate Screening, Interview Scoring, AI Recruiting, Talent Acquisition, HR Tech
VotesCount: 🔺334
Featured: Yes
CreatedAt: 2025-07-07 07:01 AM (UTC)

4. Context

Tagline: The AI office suite
Description: Context is the first AI Office Suite that automates your workflow by creating documents, presentations, spreadsheets, and more using your data, tools, and style.
Website: open
Product Hunt: View on Product Hunt

Keyword: AI Office Suite, Context AI, AI productivity, Automated Documents, AI Presentations, AI Spreadsheets, Workflow Automation, AI writing tools
VotesCount: 🔺323
Featured: Yes
CreatedAt: 2025-07-07 07:01 AM (UTC)

5. Blogwald

Tagline: Structure content for llms and search engines
Description: Blogwald helps you publish authoritative content structured for how AI models and search engines rank, reason, and recommend.
Website: open
Product Hunt: View on Product Hunt

Keyword: SEO, AI content, content optimization, LLM optimization, content structure, blog writing, website content, search engine optimization, AI writing, content strategy
VotesCount: 🔺245
Featured: Yes
CreatedAt: 2025-07-07 07:01 AM (UTC)

6. Voicebun

Tagline: Build voice agents in seconds
Description: Build smart voice agents in minutes — no code needed. Automate calls, support, and scheduling with powerful AI workflows.
Website: open
Product Hunt: View on Product Hunt

Keyword: voice agent, voice automation, no-code, AI workflow, call automation, appointment scheduling, voice support
VotesCount: 🔺226
Featured: Yes
CreatedAt: 2025-07-07 07:01 AM (UTC)

7. OneNode

Tagline: Simplest backend for AI coding - Open source
Description: OneNode is the simplest backend for AI coding. The backend development doesn’t have to be complicated anymore.
Website: open
Product Hunt: View on Product Hunt

Keyword: OneNode, AI backend, open source backend, simple backend, AI coding, backend development, machine learning backend
VotesCount: 🔺204
Featured: Yes
CreatedAt: 2025-07-07 07:01 AM (UTC)

8. Jukebox

Tagline: Free alternative to Spotify collaborative playlists
Description: Never fight over the aux again! To use, create a “box” then share a link with friends so they can add songs. It’s fair, so if person A adds two songs and person B adds one, B’s song goes between A’s. Scales infinitely!
Website: open
Product Hunt: View on Product Hunt

Keyword: Collaborative playlist, music playlist, shared playlist, group playlist, aux cord alternative, music sharing, Spotify alternative, collaborative music, online jukebox, music collaboration
VotesCount: 🔺200
Featured: Yes
CreatedAt: 2025-07-07 07:01 AM (UTC)

9. DockFix

Tagline: Customize your macOS dock like never before
Description: DockFix is the ultimate Mac Dock replacement for extra customization, powerful features, and a productivity boost. Download now! This update features an exciting new workflows feature that will truly reimagine the way you use your Mac, along with much more.
Website: open
Product Hunt: View on Product Hunt

Keyword: macOS, Dock, Dock customization, Mac Dock, Dock replacement, Mac productivity, workflow, customization
VotesCount: 🔺167
Featured: Yes
CreatedAt: 2025-07-07 07:01 AM (UTC)

10. Iconize Folder

Tagline: Customize folder color & icon & text
Description: Iconize Folder is a tool that lets you easily customize folder colors, icons, and text to enhance visual appeal and improve file management efficiency.
Website: open
Product Hunt: View on Product Hunt

Keyword: Folder Icon, Customize Folder, Color Folders, Iconize, Folder Color, Change Folder Icon, Folder Customization, File Management
VotesCount: 🔺130
Featured: Yes
CreatedAt: 2025-07-07 07:01 AM (UTC)

void

Tue, 24 Jun 2025 15:30:22 +0800

voideditor/void

Welcome to Void.

Void is the open-source Cursor alternative.

Use AI agents on your codebase, checkpoint and visualize changes, and bring any model or host locally. Void sends messages directly to providers without retaining your data.

This repo contains the full sourcecode for Void. If you’re new, welcome!

🧭 Website
👋 Discord
🚙 Project Board

Contributing

To get started working on Void, check out our Project Board! You can also see HOW_TO_CONTRIBUTE.
Feel free to attend a casual weekly meeting in our Discord channel!

Reference

Void is a fork of the vscode repository. For a guide to the codebase, see VOID_CODEBASE_GUIDE.

Support

You can always reach us in our Discord server or contact us via email: hello@voideditor.com.

ComfyUI-LTXVideo

Wed, 14 May 2025 15:29:28 +0800

Lightricks/ComfyUI-LTXVideo

ComfyUI-LTXVideo

ComfyUI-LTXVideo is a collection of custom nodes for ComfyUI, designed to provide useful tools for working with the LTXV model. The model itself is supported in the core ComfyUI code. The main LTXVideo repository can be found here.

⭐ 06.05.2025 – LTXVideo 13B 0.9.7 Release ⭐

🚀 What’s New in LTXVideo 13B 0.9.7

LTXV 13B 0.9.7 Delivers cinematic-quality videos at unprecedented speed.
👉 Download here
LTXV 13B Quantized 0.9.7 Offers reduced memory requirements and even faster inference speeds. Ideal for consumer-grade GPUs (e.g., NVIDIA 4090, 5090). Delivers outstanding quality with improved performance.
Important: In order to run the quantized version please install LTXVideo-Q8-Kernels package and use dedicated flow below. Loading the model in Comfy with LoadCheckpoint node won’t work.
👉 Download here
🧩 Example ComfyUI flow available in the Example Workflows section.
Latent Upscaling Models Enables inference across multiple scales by upscaling latent tensors without decoding/encoding. Multiscale inference delivers high-quality results in a fraction of the time compared to similar models.
Important: Make sure you put the models below in models/upscale_models folder.
👉 Spatial upscaling: Download here.
👉 Temporal upscaling: Download here.
🧩 Example ComfyUI flow available in the Example Workflows section.

Technical Updates

New simplified flows and nodes
1.1. Simplified image to video: Download here.
1.2. Simplified image to video with extension: Download here.
1.3. Simplified image to video with keyframes: Download here.

17.04.2025 ⭐ LTXVideo 0.9.6 Release ⭐

LTXVideo 0.9.6 introduces:

LTXV 0.9.6 – higher quality, faster, great for final output. Download from here.
LTXV 0.9.6 Distilled – our fastest model yet (only 8 steps for generation), lighter, great for rapid iteration. Download from here.

Technical Updates

We introduce the STGGuiderAdvanced node, which applies different CFG and STG parameters at various diffusion steps. All flows have been updated to use this node and are designed to provide optimal parameters for the best quality. See the Example Workflows section.

5.03.2025 ⭐ LTXVideo 0.9.5 Release ⭐

LTXVideo 0.9.5 introduces:

Improved quality with reduced artifacts.
Support for higher resolution and longer sequences.
Frame and sequence conditioning (beyond the first frame).
Enhanced prompt understanding.
Commercial license availability.

Technical Updates

Since LTXVideo is now fully supported in the ComfyUI core, we have removed the custom model implementation. Instead, we provide updated workflows to showcase the new features:

Frame Conditioning – Enables interpolation between given frames.
Sequence Conditioning – Allows motion interpolation from a given frame sequence, enabling video extension from the beginning, end, or middle of the original video.
Prompt Enhancer – A new node that helps generate prompts optimized for the best model performance. See the Example Workflows section for more details.

LTXTricks Update

The LTXTricks code has been integrated into this repository (in the /tricks folder) and will be maintained here. The original repo is no longer maintained, but all existing workflows should continue to function as expected.

22.12.2024

Fixed a bug which caused the model to produce artifacts on short negative prompts when using a native CLIP Loader node.

19.12.2024 ⭐ Update ⭐

Improved model - removes “strobing texture” artifacts and generates better motion. Download from here.
STG support
Integrated image degradation system for improved motion generation.
Additional initial latent optional input to chain latents for high res generation.
Image captioning in image to video flow.

Installation

Installation via ComfyUI-Manager is preferred. Simply search for ComfyUI-LTXVideo in the list of nodes and follow installation instructions.

Manual installation

Install ComfyUI
Clone this repository to custom-nodes folder in your ComfyUI installation directory.
Install the required packages:

`1`	`cd custom_nodes/ComfyUI-LTXVideo && pip install -r requirements.txt`

For portable ComfyUI installations, run

`1`	`.\python_embeded\python.exe -m pip install -r .\ComfyUI\custom_nodes\ComfyUI-LTXVideo\requirements.txt`

Models

Download ltx-video-2b-v0.9.1.safetensors from Hugging Face and place it under models/checkpoints.
Install one of the t5 text encoders, for example google_t5-v1_1-xxl_encoderonly. You can install it using ComfyUI Model Manager.

Example workflows

Note that to run the example workflows, you need to have some additional custom nodes, like ComfyUI-VideoHelperSuite and others, installed. You can do it by pressing “Install Missing Custom Nodes” button in ComfyUI Manager.

Easy to use multi scale generation workflows

🧩 Image to video
🧩 Image to video with keyframes
🧩 Image to video with duration extension
🧩 Image to video 8b quantized

Inversion

Flow Edit

🧩 Download workflow

RF Edit

🧩 Download workflow

Awesome-Dify-Workflow

Fri, 18 Apr 2025 15:28:32 +0800

svcvit/Awesome-Dify-Workflow

Awesome-Dify-Workflow 🚀

Share & Discover Useful Dify Workflows! For personal use & learning.

English | 中文

分享一些好用的 Dify 工作流程，自用、学习两相宜，请使用 Dify 0.13.0 及以上版本导入。已支持多 任务并行、会话变量、表单、echart渲染 相关特性。Agent节点为1.0版本之后功能，请尽可能使用最新版DIFY导入。

所有的 Workflow 基本都可以免费使用，更多 Workflow 收集整理中……

分享群

开了一个分享群，有兴趣可以加入，如果你有关于 workflow 的问题也可以一起讨论。（2025/04/17 更新）

主群都超200了，加群主好友，备注 dify，拉你到人多一些的群。不过微信风控，有时候加不上，可以稍后再试。
当然，也可以加新群，目前人少一点，基本1-2天左右一个群就能满200.

视频教程

最近计划更新一个DIFY使用系列教程，基本上有手就会，里面包含很多我个人使用过程中的一些理解，相信不管你是新手小白，还是企业用户，都会有所收货。

名称	视频	文字摘要版
01课 - DIFY的本地化部署与启动	https://www.youtube.com/watch?v=6LnHVay289w	https://blog.vcvit.me/2025/04/09/01-dify-local-deployment-and-startup/
02课 - DIFY模型配置	https://www.youtube.com/watch?v=4I2DgPR3qDA	https://blog.vcvit.me/2025/04/10/02-dify-model-configuration/
03课 - chatflow和workfow的区别	https://www.youtube.com/watch?v=quEA_7LVWA8	https://blog.vcvit.me/2025/04/11/03-dify-workflow-vs-chatflow/

常见问题

这里总结了一些群里常见的问题，不定期更新，内容不会很多，希望对你有帮助。

AI 流程平台对比——Dify、Fastgpt、Ragflow

dify 有没有国内的镜像源配置呀?

A：我一般把所有image，前面的链接加上 dockerpull.org

sandbox 如何安装pandas这些第三方库？

A：打开 /docker/volumes/sandbox/dependencies/python-requirements.txt 填入需要安装的依赖，重启sandbox即可。

定时任务可以如何处理？我希望定时执行某个流程。

A：可以参考项目 https://github.com/leochen-g/dify-schedule

节点间传递string数据，提示超限制，如何处理

A：修改 .env 中的一段： CODE_MAX_STRING_LENGTH: 1000000 TEMPLATE_TRANSFORM_MAX_LENGTH: 1000000 重启容器

拿到图片URL后能在聊天窗口显示吗，试了下markdown但什么都没显示出来。

A：你的做法是对的，只是你的图片不支持跨域，所以没渲染出来

请教一个问题，知识库上传大文件提出报错，修改配置文件后，还是无法上传大文件，如下是配置文件中修改上传文件地方；

A:nginx 也要改；在.env里面；搜 nginx，应该能找到

知识库永久排队问题

A：修改 .env 中的一段：LOG_FILE=/app/logs/server.log；重启容器

在哪里可以自学Dify?

A：可以参考 https://dify101.com

Dify生成图表有什么好方案？

A：Dify自带了一些绘图功能，包括柱状图、曲线图等。也可以自己写一个Echarts插件，从数据库读取数据并画图。

Dify知识库上传PDF乱码怎么办？

A：可以使用工具将PDF转换成Markdown格式再上传。

DuckDuckGo 翻译现在是不可用了吗

A：应该是服务器挂了代理，但是dify是启在docker里面的，没挂。

探索 Dify 的官方示例应用全部是英文，怎么切换成中文？

A：点击右上角，头像，设置，语言，先切换成其它语言，再切换成中文，即可。

管理员密码忘记了怎么搞？

A：执行下面的指令：docker exec -it docker-api-1 flask reset-password

SANDBOX

sandbox 运行pandas，numpy>2.0，matplotlib，scikit-learn 代码老报错，可以使用我开发的另外一个简单版dify-sandbox-py，这些依赖已经测试可以使用。

DIFY 1.0 插件

dify_plugin_collection 仓库存放着 DIFY 的官方市场插件安装包，方便离线用户自由选择，不定期更新。

如果你希望开发插件，我有2个插件的源码 google翻译、对话Agent 希望可以给你参考。

模型

你可以使用最近火热的deepseek-R1，硅基流动提供免费2000万Tokens，如果使用邀请注册，你和我都会获赠免费2000万token的额度：https://cloud.siliconflow.cn/i/MwADckCi
如果你希望体验 OpenAI 或 Anthropic 的模型，可以使用我搭建的服务 CoffBox 的服务配置方式参考如何在Dify中使用CoffBox的服务这个方式仅供个人使用，如果你需要大规模使用，openrouter会是个更好的选择。

参考截图

所有 DSL 都为工作流模式，可以方便的发布为工具后，嵌入 ChatBot 流程。工作流会包含基础的输入、条件判断、变量聚合器、输出等内容。

DSL 目录

你可以参考下面每个 yml 的描述，找到你需要的 Workflow，然后在 DSL 文件夹中找到对应的文件，复制文件的 URL，导入自己的 Dify 账号即可。

2025-04-17更新

文件	描述	来源
`sanic-web`	这是一个使用DIFY作为服务层的数据库问答项目，项目有独立的web交互界面，请访问 https://github.com/apconw/sanic-web 查看详情。项目完成度很高，按照文档一步步操作即可启动。使用ollama的qwen和deepseek模型，即可获得不错的效果。	sanic-web

2025-04-16更新

文件	描述	来源
`MCP-amap.yml`	使用MCP Agent 策略进行MCP工具的调用示例，MCP使用高德地图提供的在线服务，你可以先注册一个开发者账号，申请一个免费的Key。替换下图中马赛克部分这里还有一个官方示例Dify MCP 插件指南：一键连接 Zapier，轻松调用 7000+ App 工具	@svcvit

2025-04-07更新

文件	描述	来源
`图文知识库`	如果你希望检索知识库后，是图配文的效果，你需要在知识库里加上图片的远程连接即可。可参考本示例，包含一个markdown文件。	@svcvit

2025-03-21更新

文件	描述	来源
`Demo-tod_agent.yml`	使用dify 1.0 的Agent节点，针对对话场景优化的Agent策略，例如：多轮对话、上下文理解、信息收集等。https://marketplace.dify.ai/plugins/svcvit/agent	@svcvit

2025-02-24更新

文件	描述	来源
`Deep Researcher On Dify .yml`	Deep Researcher 工作流复现方案	@AdamPlatin123

2025-02-17更新

文件	描述	来源
`Agent工具调用.yml`	使用dify 1.0 的Agent节点，使用FC调用不同的工具，进行回复。	@svcvit

2025-01-23更新

文件	描述	来源
`旅行Demo.yml`	使用dify 1.0 的Agent节点，演示旅行信息收集，Tool调用，对话历史上下文存储。将对话消息存入对话变量，纳入Agent的思考上下文。	@svcvit

2025-01-21更新

文件	描述	来源
`春联生成器.yml`	春联生成工具，注意字体需要电脑有，可以按需修改字体。	微信群@Junjie.M
`春联生成器 (“福”到了版本).yml`		微信群@Junjie.M
`完蛋！我被LLM包围了！ .yml`	【完蛋！我被LLM包围了！】借鉴了：https://github.com/modelscope/modelscope/tree/master/examples/apps/llm_riddles	微信群@Junjie.M

2024-12-05更新

文件	描述	来源
`File_read.yml`	使用sandbox读取文件并解析，需要使用dify-sandbox-py，挂在上传目录，这是一个pandas读取csv的示例，具体方法参考右侧来源链接	@svcvit
`runLLMCode.yml`	使用LLM生成的Code，再通过sandbox去执行。因为code节点无法直接引用LLM的代码，所以通过HTTP请求的方式执行，这里有一个分析csv的示例。	@svcvit
`数据分析.7z`	数据分析的示例，可以根据需求查询数据库，生成对应的解读和图表。示例中包括流程文件和flask的服务。	微信群：简单&平凡@

2024-11-29更新

文件	描述	来源
`LanguageConsistencyChecker.yml`	三语言检查器，主要处理翻译的内容优化，它还有一个web端配套	langfixer

2024-11-22更新

文件	描述	来源
`matplotlib.yml`	使用matplotlib画图，将图片输出为base64，再通过回复渲染图片。注意，官方sandbox权限比较复杂，安装完matplotlib也无法使用，请使用dify-sandbox-py	@svcvit
`jieba.yml`	jieba 分词示例，请使用dify-sandbox-py	@svcvit

2024-11-20更新

文件	描述	来源
`json-repair.yml`	大模型输出的JSON格式不标准，少个引号，多个括号，通过这个流程修复为可解析的的JSON	@svcvit

2024-11-15更新

文件	描述	来源
`json_translate.yml`	解析JSON中的需要翻译的内容，使用迭代器进行翻译，再组合成新的JSON，保持原有JSON的结构	@svcvit

2024-11-14更新

文件	描述	来源
`腾讯云SubtitleInfo.yml`	这是一个代码相关的示例，通过腾讯云的授权信息加密，获取需要的内容信息参考。如果你需要使用代码节点，可以参考用法。	微信分享群
`chart_demo.yml`	通过回复内容渲染charts的图表内容。当然你可以可以根据sql查询数据，拼接成需要的内容	@svcvit

2024-11-12更新

文件	描述	来源
`Form表单聊天Demo.yml`	在对话框登录之后有权限访问模型	@svcvit

翻译

文件	描述	来源
`中译英.yml`	通过宝玉的 Prompt，直译->反思->意译，将中文翻译成高质量的英文。	暂无
`DuckDuckGo 翻译+LLM 二次翻译.yml`	与三步翻译类似，但是把第一步的直译变成传统翻译引擎翻译，节省 Token，提高翻译效率，同时提高翻译质量。	暂无
`translation_workflow.yml`	使用吴恩达提出 Agentic Workflow 制作的翻译工具，录入`输入语言`、`目标语言`、`国家`、`原始文本` 4 个参数，提供更细致的翻译结果	translation-agent
`宝玉的英译中优化版.yml`	宝玉的科技文章翻译优化版本，主要优化了提示词和 xml 标签	翻译 GPT 的提示词更新和优化
`全书翻译.yml`	DIFY 官方示例，切分长文本，再迭代器内翻译	DIFY 官方探索内容

工具

文件	描述	来源
`SEO Slug Generator.yml`	给自己的博文生成 url slug，参考来源于宝玉的 X	twitter
`Document_chat_template.yml`	一个通过知识库聊天的模版	Winson-030
`搜索大师.yml`	通过 SearXNG 进行搜索，再通过 jina 获取搜索内容	Winson-030
`标题党创作.yml`	一位爆款网文作家	ghostviper
`文章仿写-单图_多图自动搭配.yml`	文章仿写	ghostviper
`Text to Card Iteration.yml`	自动生成小红书这种卡片。	🔥Dify Workflow-Agent 设计交流 @Arthur
`Dify 运营一条龙.yml`	小红书、抖音、微博、B 站一条龙运营。（2024/11/21更新，主流程已经不能用了，因为图片生成那个服务问题很多，而且限制了分辨率，导致生成图完全不对了，全当看个思路。）	Dify 一键生成多尺寸 Cover 与全平台文案
`Jina Reader Jinja.yml`	一个基于 TavilySearch 和 Jina 的问答流程	🔥Dify Workflow-Agent 设计交流群分享
`llm2o1.cn.yml`	任务拆解→提取步骤→迭代步骤执行→归纳总结→输出结果	@okooo5km
`dify_course_demo.yml`	自动化生成全套教程。	dify_course
`simple-kimi.yml`	简易自制 Kimi	aws-samples
`Claude3 Code Translation.yml`	不同代码种类之间的翻译工作流	aws-samples

聊天机器人

文件	描述	来源
`根据用户的意图进行回复.yml`	根据用户的聊天内容，进行意图判定，根据意图选择不同的工作流路径进行回复，再风格化聊天机器人话术	无
`mem0ai`	一个有记忆的聊天流程，完整代码见来源链接	dify-plugin-mem0ai
`记忆测试.yml`	添加短期记忆，CoT 思维链的示例，自动问答机器人也可以主动触达，根据上下文选择最佳回复	来自微信 svcvit

代码

文件	描述	来源
`Python Coding Prompt.yml`	通过聊天对话方式生成 Python 代码	Sonnet 3.5 for Coding 😍 - System Prompt

使用方法

下载本项目至本地，导入 DLS 文件即可，当然，你可以进行必要的调整，例如模版的调整，或提示词的调整。