optimize ollama docs

pull/33/head
takatost 2024-01-12 12:20:16 +08:00
parent 63149a522f
commit 3f6e2e5019
2 changed files with 8 additions and 0 deletions

View File

@ -31,6 +31,7 @@ Dify supports integrating LLM and Text Embedding capabilities of large language
- Model Name: `llava`
- Base URL: `http://<your-ollama-endpoint-domain>:11434`
Enter the base URL where the Ollama service is accessible.
If Dify is deployed using docker, consider using the local network IP address, e.g., `http://192.168.1.100:11434` or the docker host machine IP address, e.g., `http://172.17.0.1:11434`.
For local source code deployment, use `http://localhost:11434`.
@ -38,12 +39,15 @@ Dify supports integrating LLM and Text Embedding capabilities of large language
- Model Type: Chat
- Model Context Length: 4096
The maximum context length of the model. If unsure, use the default value of 4096.
- Maximum Token Limit: 4096
The maximum number of tokens returned by the model. If there are no specific requirements for the model, this can be consistent with the model context length.
- Support for Vision: Yes
Check this option if the model supports image understanding (multimodal), like `llava`.
Click "Save" to use the model in the application after verifying that there are no errors.

View File

@ -31,6 +31,7 @@ Dify 支持接入 Ollama 部署的大型语言模型推理和 embedding 能力
- 模型名称:`llava`
- 基础 URL`http://<your-ollama-endpoint-domain>:11434`
此处需填写可访问到的 Ollama 服务地址。
若 Dify 为 docker 部署,建议填写局域网 IP 地址,如:`http://192.168.1.100:11434` 或 docker 宿主机 IP 地址,如:`http://172.17.0.1:11434`。
若为本地源码部署,可填写 `http://localhost:11434`
@ -38,12 +39,15 @@ Dify 支持接入 Ollama 部署的大型语言模型推理和 embedding 能力
- 模型类型:对话
- 模型上下文长度4096
模型的最大上下文长度,若不清楚可填写默认值 4096。
- 最大 token 上限4096
模型返回内容的最大 token 数量,若模型无特别说明,则可与模型上下文长度保持一致。
- 是否支持 Vision
当模型支持图片理解(多模态)勾选此项,如 `llava`
点击 "保存" 校验无误后即可在应用中使用该模型。