add use ollama models

pull/33/head
takatost 2024-01-12 16:45:12 +08:00
parent 31e1fac8b4
commit 82c2731f80
4 changed files with 12 additions and 0 deletions

Binary file not shown.

After

Width:  |  Height:  |  Size: 428 KiB

View File

@ -57,4 +57,10 @@ Dify supports integrating LLM and Text Embedding capabilities of large language
The integration method for Embedding models is similar to LLM, just change the model type to Text Embedding.
4. Use Ollama Models
![](../../.gitbook/assets/ollama-use-model-en.png)
Enter `Prompt Eng.` page of the App that needs to be configured, select the `llava` model under the Ollama provider, and use it after configuring the model parameters.
For more information on Ollama, please refer to: [https://github.com/jmorganca/ollama](https://github.com/jmorganca/ollama)

Binary file not shown.

After

Width:  |  Height:  |  Size: 398 KiB

View File

@ -57,4 +57,10 @@ Dify 支持接入 Ollama 部署的大型语言模型推理和 embedding 能力
Embedding 模型接入方式与 LLM 类似,只需将模型类型改为 Text Embedding 即可。
4. 使用 Ollama 模型
![](../../.gitbook/assets/ollama-use-model.png)
进入需要配置的 App 提示词编排页面,选择 Ollama 供应商下的 `llava` 模型,配置模型参数后即可使用。
如需获取 Ollama 更多信息,请参考:[https://github.com/jmorganca/ollama](https://github.com/jmorganca/ollama)