diff --git a/README.md b/README.md index b261c7982..54408d041 100644 --- a/README.md +++ b/README.md @@ -1,10 +1,9 @@
-
English |
简体中文
@@ -26,27 +25,32 @@
[RAGFlow](http://demo.ragflow.io) is an open-source, Retrieval-Augmented Generation engine built on large language models (LLM), deep document understanding, and multiple recall. It offers a streamlined RAG workflow for businesses of any scale, providing truthful responses with solid citations through a generative AI knowledge management platform.
## 🌟 Key Features
-
+
### 🍭 **"Quality in, quality out"**
- - Deep document understanding-based knowledge extraction from unstructured data with complicated formats.
- - Finds "needle in a data haystack" of literally unlimited tokens.
+
+- Deep document understanding-based knowledge extraction from unstructured data with complicated formats.
+- Finds "needle in a data haystack" of literally unlimited tokens.
### 🍱 **Template-based chunking**
- - Intelligent and explainable.
- - Plenty of template options to choose from.
+
+- Intelligent and explainable.
+- Plenty of template options to choose from.
### 🌱 **Grounded citations with reduced hallucinations**
- - Visualization of text chunking to allow human intervention.
- - Quick view of the key references and traceable citations to support grounded answers.
+
+- Visualization of text chunking to allow human intervention.
+- Quick view of the key references and traceable citations to support grounded answers.
### 🍔 **Compatibility with heterogeneous data sources**
- - Supports Word, slides, excel, txt, images, scanned copies, structured data, web pages, and more.
+
+- Supports Word, slides, excel, txt, images, scanned copies, structured data, web pages, and more.
### 🛀 **Automated and effortless RAG workflow**
- - Streamlined RAG orchestration catered to both personal and large businesses.
- - Configurable LLMs as well as embedding models.
- - Multiple recall paired with fused re-ranking.
- - Intuitive APIs for seamless integration with business.
+
+- Streamlined RAG orchestration catered to both personal and large businesses.
+- Configurable LLMs as well as embedding models.
+- Multiple recall paired with fused re-ranking.
+- Intuitive APIs for seamless integration with business.
## 🔎 System Architecture
@@ -65,11 +69,11 @@
### 🚀 Start up the server
-1. Ensure `vm.max_map_count` > 65535:
+1. Ensure `vm.max_map_count` > 65535:
> To check the value of `vm.max_map_count`:
>
- > ```bash
+ > ```bash
> $ sysctl vm.max_map_count
> ```
>
@@ -92,7 +96,7 @@
$ git clone https://github.com/infiniflow/ragflow.git
```
-3. Build the pre-built Docker images and start up the server:
+3. Build the pre-built Docker images and start up the server:
```bash
$ cd ragflow/docker
@@ -102,31 +106,33 @@
> The core image is about 15 GB in size and may take a while to load.
4. Check the server status after having the server up and running:
+
```bash
$ docker logs -f ragflow-server
```
- *The following output confirms a successful launch of the system:*
+
+ _The following output confirms a successful launch of the system:_
```bash
- ____ ______ __
+ ____ ______ __
/ __ \ ____ _ ____ _ / ____// /____ _ __
/ /_/ // __ `// __ `// /_ / // __ \| | /| / /
- / _, _// /_/ // /_/ // __/ / // /_/ /| |/ |/ /
- /_/ |_| \__,_/ \__, //_/ /_/ \____/ |__/|__/
- /____/
-
+ / _, _// /_/ // /_/ // __/ / // /_/ /| |/ |/ /
+ /_/ |_| \__,_/ \__, //_/ /_/ \____/ |__/|__/
+ /____/
+
* Running on all addresses (0.0.0.0)
* Running on http://127.0.0.1:9380
* Running on http://172.22.0.5:9380
INFO:werkzeug:Press CTRL+C to quit
- ```
+ ```
5. In your web browser, enter the IP address of your server as prompted and log in to RAGFlow.
6. In [service_conf.yaml](./docker/service_conf.yaml), select the desired LLM factory in `user_default_llm` and update the `API_KEY` field with the corresponding API key.
- > See [./docs/llm_api_key_setup.md](./docs/llm_api_key_setup.md) for more information.
-
- *The show is now on!*
+ > See [./docs/llm_api_key_setup.md](./docs/llm_api_key_setup.md) for more information.
+
+ _The show is now on!_
## 🔧 Configurations
@@ -136,14 +142,14 @@ When it comes to system configurations, you will need to manage the following fi
- [service_conf.yaml](./docker/service_conf.yaml): Configures the back-end services.
- [docker-compose.yml](./docker/docker-compose.yml): The system relies on [docker-compose.yml](./docker/docker-compose.yml) to start up.
-You must ensure that changes to the [.env](./docker/.env) file are in line with what are in the [service_conf.yaml](./docker/service_conf.yaml) file.
+You must ensure that changes to the [.env](./docker/.env) file are in line with what are in the [service_conf.yaml](./docker/service_conf.yaml) file.
> The [./docker/README](./docker/README.md) file provides a detailed description of the environment settings and service configurations, and you are REQUIRED to ensure that all environment settings listed in the [./docker/README](./docker/README.md) file are aligned with the corresponding configurations in the [service_conf.yaml](./docker/service_conf.yaml) file.
To update the default serving port (80), go to [docker-compose.yml](./docker/docker-compose.yml) and change `80:80` to `
English |
简体中文
@@ -26,27 +25,32 @@
[RAGFlow](http://demo.ragflow.io) 是一款基于大型语言模型(LLM)以及深度文档理解构建的开源检索增强型生成引擎(Retrieval-Augmented Generation Engine)。RAGFlow 可以为各种规模的企业提供一套精简的 RAG 工作流程,通过生成式 AI (Generative AI)知识管理平台提供可靠的问答以及有理有据的引用。
## 🌟 主要功能
-
+
### 🍭 **"Quality in, quality out"**
- - 基于深度文档理解,能够从各类复杂格式的非结构化数据中提取真知灼见。
- - 真正在无限上下文(token)的场景下快速完成大海捞针测试。
+
+- 基于深度文档理解,能够从各类复杂格式的非结构化数据中提取真知灼见。
+- 真正在无限上下文(token)的场景下快速完成大海捞针测试。
### 🍱 **基于模板的文本切片**
- - 不仅仅是智能,更重要的是可控可解释。
- - 多种文本模板可供选择
+
+- 不仅仅是智能,更重要的是可控可解释。
+- 多种文本模板可供选择
### 🌱 **有理有据、最大程度降低幻觉(hallucination)**
- - 文本切片过程可视化,支持手动调整。
- - 有理有据:答案提供关键引用的快照并支持追根溯源。
+
+- 文本切片过程可视化,支持手动调整。
+- 有理有据:答案提供关键引用的快照并支持追根溯源。
### 🍔 **兼容各类异构数据源**
- - 支持丰富的文件类型,包括 Word 文档、PPT、excel 表格、txt 文件、图片、PDF、影印件、复印件、结构化数据, 网页等。
+
+- 支持丰富的文件类型,包括 Word 文档、PPT、excel 表格、txt 文件、图片、PDF、影印件、复印件、结构化数据, 网页等。
### 🛀 **全程无忧、自动化的 RAG 工作流**
- - 全面优化的 RAG 工作流可以支持从个人应用乃至超大型企业的各类生态系统。
- - 大语言模型 LLM 以及向量模型均支持配置。
- - 基于多路召回、融合重排序。
- - 提供易用的 API,可以轻松集成到各类企业系统。
+
+- 全面优化的 RAG 工作流可以支持从个人应用乃至超大型企业的各类生态系统。
+- 大语言模型 LLM 以及向量模型均支持配置。
+- 基于多路召回、融合重排序。
+- 提供易用的 API,可以轻松集成到各类企业系统。
## 🔎 系统架构
@@ -69,7 +73,7 @@
> 如需确认 `vm.max_map_count` 的大小:
>
- > ```bash
+ > ```bash
> $ sysctl vm.max_map_count
> ```
>
@@ -102,32 +106,38 @@
> 核心镜像文件大约 15 GB,可能需要一定时间拉取。请耐心等待。
4. 服务器启动成功后再次确认服务器状态:
+
```bash
$ docker logs -f ragflow-server
```
- *出现以下界面提示说明服务器启动成功:*
+
+ _出现以下界面提示说明服务器启动成功:_
```bash
- ____ ______ __
+ ____ ______ __
/ __ \ ____ _ ____ _ / ____// /____ _ __
/ /_/ // __ `// __ `// /_ / // __ \| | /| / /
- / _, _// /_/ // /_/ // __/ / // /_/ /| |/ |/ /
- /_/ |_| \__,_/ \__, //_/ /_/ \____/ |__/|__/
- /____/
-
+ / _, _// /_/ // /_/ // __/ / // /_/ /| |/ |/ /
+ /_/ |_| \__,_/ \__, //_/ /_/ \____/ |__/|__/
+ /____/
+
* Running on all addresses (0.0.0.0)
* Running on http://127.0.0.1:9380
* Running on http://172.22.0.5:9380
INFO:werkzeug:Press CTRL+C to quit
- ```
+ ```
5. 根据刚才的界面提示在你的浏览器中输入你的服务器对应的 IP 地址并登录 RAGFlow。
> 上面这个例子中,您只需输入 http://172.22.0.5 即可:端口 9380 已通过 Docker 端口映射被设置成 80(默认的 HTTP 服务端口)。
-7. 在 [service_conf.yaml](./docker/service_conf.yaml) 文件的 `user_default_llm` 栏配置 LLM factory,并在 `API_KEY` 栏填写和你选择的大模型相对应的 API key。
- > 详见 [./docs/llm_api_key_setup.md](./docs/llm_api_key_setup.md)。
-
- *好戏开始,接着奏乐接着舞!*
+6. 在 [service_conf.yaml](./docker/service_conf.yaml) 文件的 `user_default_llm` 栏配置 LLM factory,并在 `API_KEY` 栏填写和你选择的大模型相对应的 API key。
+ > 详见 [./docs/llm_api_key_setup.md](./docs/llm_api_key_setup.md)。
+
+ _好戏开始,接着奏乐接着舞!_
+
+ > 详见 [./docs/llm_api_key_setup.md](./docs/llm_api_key_setup.md)。
+
+ _好戏开始,接着奏乐接着舞!_
## 🔧 系统配置
@@ -137,14 +147,14 @@
- [service_conf.yaml](./docker/service_conf.yaml):配置各类后台服务。
- [docker-compose-CN.yml](./docker/docker-compose-CN.yml): 系统依赖该文件完成启动。
-请务必确保 [.env](./docker/.env) 文件中的变量设置与 [service_conf.yaml](./docker/service_conf.yaml) 文件中的配置保持一致!
+请务必确保 [.env](./docker/.env) 文件中的变量设置与 [service_conf.yaml](./docker/service_conf.yaml) 文件中的配置保持一致!
> [./docker/README](./docker/README.md) 文件提供了环境变量设置和服务配置的详细信息。请**一定要**确保 [./docker/README](./docker/README.md) 文件当中列出来的环境变量的值与 [service_conf.yaml](./docker/service_conf.yaml) 文件当中的系统配置保持一致。
如需更新默认的 HTTP 服务端口(80), 可以在 [docker-compose-CN.yml](./docker/docker-compose-CN.yml) 文件中将配置 `80:80` 改为 `
Instead of chunking the résumé, we parse the résumé into structured data. As a HR, you can dump all the résumé you have,
- the you can list all the candidates that match the qualifications just by talk with 'RagFlow'.
+ the you can list all the candidates that match the qualifications just by talk with 'RAGFlow'.
- Once registered, an account cannot be changed and can only be
- cancelled.
+ Once registered, E-mail cannot be changed.