自行架設Dify使用的重排序模型：Text Embeddings Inference / Self-Hosting a Dify Reranking Model: Text Embeddings Inference

隨著在Dify使用的知識庫越來越多，傳統的用相似度來計算權重分數的做法已經不敷使用，而使用重排序模型來排序檢索結果順序的做法也越來越受歡迎。這次我們來架設HuggingFace推出的Text Embeddings Inference，並讓Dify能用它來做重排序吧。

As the knowledge base used in Dify grows, the traditional method of calculating weight scores based on similarity is becoming inadequate.  Using reranking models to reorder retrieval results is gaining popularity.  Let's set up HuggingFace's Text Embeddings Inference and integrate it into Dify for reranking.

雜談：用Dify跟Stable Diffuision製作投影片章節的封面照片 / Talk: Creating a Cover Image for Slide Section Using Dify and Stable Diffusion

為投影片的內容選擇合適的照片真不是一件容易的事情。於是我就試著將投影片的內容傳送給大型語言模型，請大型語言模型撰寫適合Stable Diffusion的提示詞，然後用提示詞來繪圖看看。這樣的工作流會出現什麼結果呢？

雜談：ComfyUI很好用，但結果跟WebUI不一樣 / ComfyUI Is User-Friendly, But Results Differ From WebUI

繼上次把Forge裝起來後，我還是覺得生圖的方式太沒效率了，所以轉向尋求其他工具。這次嘗試的是Dify跟ComfyUI的結合。

讓Dify使用自己管理的搜尋引擎：SearXNG / Let Dify Use My Self-Hosting Search Engine: SearXNG

我在「自行架設大型語言模式應用程式：Dify」這篇講到我用SerpAPI作為Dify的搜尋引擎，但除了使用別人提供的API之外，我們也可以用SearXNG自行架設客製化的搜尋引擎，並將它跟Dify結合一起使用。

In the article "Self-Hosting a Large Language Model Application: Dify," I mentioned using SerpAPI as the search engine for Dify. However, besides using third-party APIs, we can also utilize SearXNG to set up a customized search engine and integrate it with Dify.

用爬蟲作為Dify的知識庫：Firecrawl / Using a Web Crawler as Dify's Knowledge Base: Firecrawl

Dify的知識庫能夠取自網路資料，再搭配我們自架的Coolcrawl來取代公開服務Firecrawl，就能夠抓取內部區域網路裡面的網路資料。接下來就讓我們來看看這要怎麼實作吧。

Dify's knowledge base can draw from online data, and by combining it with our self-hosted Coolcrawl (instead of the public service Firecrawl), it can also crawl data within the intranet. Let's take a look at how to implement this.

離開抱抱臉: 讓Dify擁抱Ollama / Leaving Hugging Face: Embracing Ollama with Dify

在「自行架設大型語言模式應用程式：Dify」這篇我講到我在Dify裡面使用Hugging Face API作文字嵌入(embedding)，但啟動等待跟限速的限制降低了使用效率。這次我們把文字嵌入的工作交給自行架設的Ollama，讓我們來看看自行架設到底可以帶來什麼效益吧。

In the article "Self-Hosting a Large Language Model Application: Dify," I discussed using the Hugging Face API for text embedding within Dify. However, startup latency and rate limiting reduced efficiency. This time, we'll offload the text embedding task to a self-hosted Ollama instance. Let's explore the benefits of self-hosting.

雜談：來自架Dify v0.12.1吧！ / TALK: Let's Self-Host Dify v0.12.1!

自從上次講到想要從Dify v0.6.14升級之後，這次就來試著安裝看看吧。

雜談：是時候該來處理一下Dify的問題了 / TALK: It's Time to Address the Issues with Dify

在「自行架設大型語言模式應用程式：Dify」這篇裡面，我用Dify在筆電架設了可客製化、具備RAG的大型語言模型應用程式。但這段期間用下來還是遭遇了很多問題。以下就稍微列舉一下我遭遇的狀況。

自行架設大型語言模型應用程式：Dify / Self-Hosting a Large Language Model Application: Dify

Coze開始收費之後，Dify會是更好的替代方案嗎？事情原來沒有我自己想象中的這麼簡單！

When Coze began to charge fees, what is the next solution for Large Language Model (LLM) application? Will Dify be a better alternative? The actual situation is not as simple as I had imagined!