Merge branch 'main' of github.com:deepseek-ai/awesome-deepseek-integration

This commit is contained in:
yh-xu 2024-06-26 14:27:45 +08:00
commit 04b68a8704
6 changed files with 117 additions and 4 deletions

View File

@ -45,6 +45,15 @@ English/[简体中文](https://github.com/deepseek-ai/awesome-deepseek-integrati
</tr>
</table>
### RAG framework
<table>
<tr>
<td> <img src="https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372" alt="Icon" width="64" height="auto" /> </td>
<td> <a href="https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/ragflow/README.md"> RAGFlow </a> </td>
<td> An open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data. </td>
</tr>
</table>
### IM Application Plugins
<table>

View File

@ -44,6 +44,15 @@
</tr>
</table>
### RAG 框架
<table>
<tr>
<td> <img src="https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372" alt="Icon" width="64" height="auto" /> </td>
<td> <a href="https://github.com/deepseek-ai/awesome-deepseek-integration/blob/main/docs/ragflow/README_cn.md"> RAGFlow </a> </td>
<td> 一款基于深度文档理解构建的开源 RAGRetrieval-Augmented Generation引擎。RAGFlow 可以为各种规模的企业及个人提供一套精简的 RAG 工作流程结合大语言模型LLM针对用户各类不同的复杂格式数据提供可靠的问答以及有理有据的引用。 </td>
</tr>
</table>
### 即时通讯插件
<table>

View File

@ -9,7 +9,41 @@ Continue will generate, refactor, and explain entire sections of code with LLMs.
![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/094e9dc8-03d0-493d-95fb-6129a42a35bd)
## Integrate with Deepseek API
## Integrate with DeepSeek API
<img width="1462" alt="image" src="https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/7114a8ef-c20a-4f06-91b3-2399c6b77b2d">
### Tab Completion
Please use the following config before we release official FIM support:
config.json
```json
{
"models": [],
"tabAutocompleteOptions": {
"template": "Please teach me what I should write in the `hole` tag, but without any further explanation and code backticks, i.e., as if you are directly outputting to a code editor. It can be codes or comments or strings. Don't provide existing & repetitive codes. If the provided prefix and suffix contain incomplete code and statement, your response should be able to be directly concatenated to the provided prefix and suffix. Also note that I may tell you what I'd like to write inside comments. \n{{{prefix}}}<hole></hole>{{{suffix}}}\n\nPlease be aware of the environment the hole is placed, e.g., inside strings or comments or code blocks, and please don't wrap your response in ```. You should always provide non-empty output.\n",
"useCache": true,
"maxPromptTokens": 2048
},
"tabAutocompleteModel": {
"title": "DeepSeek-V2",
"model": "deepseek-coder",
"apiKey": REDACTED,
"contextLength": 8192,
"apiBase": "https://api.deepseek.com",
"completionOptions": {
"maxTokens": 4096,
"temperature": 0,
"topP": 1,
"presencePenalty": 0,
"frequencyPenalty": 0
},
"provider": "openai",
"useLegacyCompletionsEndpoint": false
}
}
```
### Chat with model
![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/7114a8ef-c20a-4f06-91b3-2399c6b77b2d)

View File

@ -5,10 +5,43 @@
开源 IDE 插件,使用 LLM 做你的编程助手.
## UI
![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/59196087/094e9dc8-03d0-493d-95fb-6129a42a35bd)
## 配置 deepseek API
![cotinue](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/155953822/cbe11ac9-32a3-462a-b0ab-123cffaffb24)
## 接入 DeepSeek API
### Tab 补全
config.json
```json
{
"models": [],
"tabAutocompleteOptions": {
"template": "Please teach me what I should write in the `hole` tag, but without any further explanation and code backticks, i.e., as if you are directly outputting to a code editor. It can be codes or comments or strings. Don't provide existing & repetitive codes. If the provided prefix and suffix contain incomplete code and statement, your response should be able to be directly concatenated to the provided prefix and suffix. Also note that I may tell you what I'd like to write inside comments. \n{{{prefix}}}<hole></hole>{{{suffix}}}\n\nPlease be aware of the environment the hole is placed, e.g., inside strings or comments or code blocks, and please don't wrap your response in ```. You should always provide non-empty output.\n",
"useCache": true,
"maxPromptTokens": 2048
},
"tabAutocompleteModel": {
"title": "DeepSeek-V2",
"model": "deepseek-coder",
"apiKey": REDACTED,
"contextLength": 8192,
"apiBase": "https://api.deepseek.com",
"completionOptions": {
"maxTokens": 4096,
"temperature": 0,
"topP": 1,
"presencePenalty": 0,
"frequencyPenalty": 0
},
"provider": "openai",
"useLegacyCompletionsEndpoint": false
}
}
```
### 侧边栏对话窗
![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/13600976/7114a8ef-c20a-4f06-91b3-2399c6b77b2d)

14
docs/ragflow/README.md Normal file
View File

@ -0,0 +1,14 @@
<img src="https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372" alt="Icon" width="64" height="auto" />
# [RAGFlow](https://github.com/infiniflow/ragflow)
An open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding. It offers a streamlined RAG workflow for businesses of any scale, combining LLM (Large Language Models) to provide truthful question-answering capabilities, backed by well-founded citations from various complex formatted data.
## UI
![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/a69ce143-931c-4a75-b129-f6a1ddd114a2)
## Integrate with Deepseek API
![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/49dc1916-c3c2-470a-a3ea-b5877de52958)

14
docs/ragflow/README_cn.md Normal file
View File

@ -0,0 +1,14 @@
<img src="https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/77093e84-9f7c-4716-9168-bac962fa1372" alt="Icon" width="64" height="auto" />
# [RAGFlow](https://github.com/infiniflow/ragflow)
一款基于深度文档理解构建的开源 RAGRetrieval-Augmented Generation引擎。RAGFlow 可以为各种规模的企业及个人提供一套精简的 RAG 工作流程结合大语言模型LLM针对用户各类不同的复杂格式数据提供可靠的问答以及有理有据的引用。
## UI
![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/a69ce143-931c-4a75-b129-f6a1ddd114a2)
## 配置 Deepseek API
![image](https://github.com/deepseek-ai/awesome-deepseek-integration/assets/33142505/514b87e3-2eef-4dd2-b21d-88bb3f381573)