diff --git a/docs.json b/docs.json index b86e89be..d40ff22f 100644 --- a/docs.json +++ b/docs.json @@ -12,6 +12,7 @@ "light": "https://assets-docs.dify.ai/2025/05/d05cfc6ebe48f725d171dc71c64a5d16.svg", "dark": "https://assets-docs.dify.ai/2025/05/c51f1cda47c1d9a4a162d7736f6e4c53.svg" }, + "navigation": { "versions": [ { @@ -289,6 +290,7 @@ "en/plugins/quick-start/develop-plugins/README", "en/plugins/quick-start/develop-plugins/initialize-development-tools", "en/plugins/quick-start/develop-plugins/tool-plugin", + "en/plugins/quick-start/develop-plugins/tool-oauth", { "group": "Model Plugin", "pages": [ @@ -389,6 +391,7 @@ "en/development/models-integration/gpustack", "en/development/models-integration/aws-bedrock-deepseek", "en/development/models-integration/truefoundry" + "en/development/models-integration/gpt-oss-local-deployment" ] }, { @@ -1048,7 +1051,8 @@ "zh-hans/development/models-integration/ollama", "zh-hans/development/models-integration/litellm", "zh-hans/development/models-integration/gpustack", - "zh-hans/development/models-integration/aws-bedrock-deepseek" + "zh-hans/development/models-integration/aws-bedrock-deepseek", + "zh-hans/development/models-integration/gpt-oss-local-deployment" ] }, { @@ -1691,7 +1695,8 @@ "ja-jp/development/models-integration/ollama", "ja-jp/development/models-integration/litellm", "ja-jp/development/models-integration/gpustack", - "ja-jp/development/models-integration/aws-bedrock-deepseek" + "ja-jp/development/models-integration/aws-bedrock-deepseek", + "ja-jp/development/models-integration/gpt-oss-local-deployment" ] }, { diff --git a/en/development/models-integration/gpt-oss-local-deployment.md b/en/development/models-integration/gpt-oss-local-deployment.md new file mode 100644 index 00000000..0218c9b8 --- /dev/null +++ b/en/development/models-integration/gpt-oss-local-deployment.md @@ -0,0 +1,130 @@ +--- +title: " gpt-oss Local Deployment with Ollama and Dify " +--- +# I. Introduction + +The gpt-oss series is an open-source model first released by OpenAI in August 2025. + +> gpt-oss:20b (fits systems with ~16 GB memory) +> +> gpt-oss:120b (designed for ≥ 60 GB memory) + +You can run it locally with Ollama. No cloud calls. Data stays on your machine, which helps with privacy and latency. + +Dify is an open-source platform for building AI Agents and Workflows. This guide shows how to run gpt-oss with Ollama and plug it into Dify for a private, high-performance setup. + +* * * + +# II. Environment Setup + +## Step 1: Run gpt-oss with Ollama + +1. Install Ollama + + +[Download](https://ollama.com/) and install for macOS, Windows, or Linux. If anything is unclear, see the [official docs](https://docs.dify.ai/en/development/models-integration/ollama#integrate-local-models-deployed-by-ollama). + + + +2. Pull a model + + +```Bash +# Recommended for most dev machines +ollama pull gpt-oss:20b + +# For large GPUs or multi-GPU hosts +ollama pull gpt-oss:120b +``` + +Both models are pre‑quantized in **MXFP4** , suitable for local deployment. + + + +3. Start Ollama + + +The default endpoint is http://localhost:11434. + +## Step 2: Install Dify locally + +See the [Dify docs](https://docs.dify.ai/en/getting-started/install-self-hosted/readme) for full instructions. Or follow the quick tutorial below. + +### Prerequisites + +Install [Docker](https://www.docker.com/products/docker-desktop/) and make sure Docker Engine is running. + +![1](https://raw.githubusercontent.com/NanSike/image-host/main/images/1.png) + + + +### Install steps + +```Bash +git clone https://github.com/langgenius/Dify.git +cd Dify/docker +cp .env.example .env +docker compose up -d +``` + +![2](https://raw.githubusercontent.com/NanSike/image-host/main/images/2.png) + +Open your local Dify instance and complete the initial setup. + +![3](https://raw.githubusercontent.com/NanSike/image-host/main/images/3.png) + +# III. Add the model and test chat + +1. In **Settings → Model Providers → Ollama** , click **Add Ollama model type** . + + +![4](https://raw.githubusercontent.com/NanSike/image-host/main/images/4.png) + +2. Set **Base URL** to `http://localhost:11434`, select **Model name** `gpt-oss:20b`, and fill in the required fields. + + +![5](https://raw.githubusercontent.com/NanSike/image-host/main/images/5.png) + + + +3. Create a blank template + + +![6](https://raw.githubusercontent.com/NanSike/image-host/main/images/6.png) + + + +4. Select the app or workflow type you want to build. + + +![7](https://raw.githubusercontent.com/NanSike/image-host/main/images/7.png) + +* * * + +# IV. Verification and Usage + +* On Dify’s **model testing** page, send a prompt and check that the response looks correct. + +* In a workflow, add an **LLM** node, select `gpt-oss:20b`, and connect the nodes end to end. + + +![8](https://raw.githubusercontent.com/NanSike/image-host/main/images/8.png) + +![9](https://raw.githubusercontent.com/NanSike/image-host/main/images/9.png) + +* * * + +# V. Appendix — FAQ and tips + +**Model Pull Is Slow** + +* *Configure a Docker proxy or use an image mirror to speed up downloads.* + + +**Insufficient GPU Memory** + +* *Use* *`gpt-oss:20b`*. You can enable CPU offloading, but responses will be slower.* + +**Port Access Issues** + +* *Check firewall rules, port bindings, and Docker network settings to ensure connectivity.* \ No newline at end of file diff --git a/en/development/models-integration/localai.mdx b/en/development/models-integration/localai.mdx index 407e0fa6..972d65af 100644 --- a/en/development/models-integration/localai.mdx +++ b/en/development/models-integration/localai.mdx @@ -13,7 +13,7 @@ Dify allows integration with LocalAI for local deployment of large language mode You can refer to the official [Getting Started](https://localai.io/basics/getting_started/) guide for deployment, or quickly integrate following the steps below: -(These steps are derived from [LocalAI Data query example](https://github.com/go-skynet/LocalAI/blob/master/examples/langchain-chroma/README)) +(These steps are derived from [LocalAI Data query example](https://github.com/mudler/LocalAI-examples/tree/main/langchain-chroma/README.md)) 1. First, clone the LocalAI code repository and navigate to the specified directory. diff --git a/en/guides/application-publishing/embedding-in-websites.mdx b/en/guides/application-publishing/embedding-in-websites.mdx index 1aaead4f..df03fc90 100644 --- a/en/guides/application-publishing/embedding-in-websites.mdx +++ b/en/guides/application-publishing/embedding-in-websites.mdx @@ -2,14 +2,32 @@ title: Embedding In Websites --- +Dify supports embedding your AI application into your business website, enabling you to build an AI customer‑service chatbot, knowledge‑base Q&A, and other applications with business data in just minutes. -Dify Apps can be embedded in websites using an iframe. This allows you to integrate your Dify App into your website, blog, or any other web page. +You can embed your AI application in three different ways: using an `