writinwaters
commited on
Commit
Β·
e5aa7c3
1
Parent(s):
d3d8d70
0331 config (#176)
Browse files* Updated steps
* Miscellaneous updates
README.md
CHANGED
|
@@ -20,15 +20,13 @@
|
|
| 20 |
<img height="21" src="https://img.shields.io/badge/License-Apache--2.0-ffffff?style=flat-square&labelColor=d4eaf7&color=7d09f1" alt="license">
|
| 21 |
</a>
|
| 22 |
</p>
|
| 23 |
-
## π‘ What is RagFlow?
|
| 24 |
|
| 25 |
-
|
| 26 |
|
| 27 |
-
|
| 28 |
-
<img src="https://github.com/infiniflow/ragflow/assets/12318111/b24a7a5f-4d1d-4a30-90b1-7b0ec558b79d" width="1000"/>
|
| 29 |
-
</div>
|
| 30 |
|
| 31 |
## π Key Features
|
|
|
|
| 32 |
- π**Custom-build document understanding engine.** Our deep learning engine is made according to the needs of analyzing and searching various type of documents in different domain.
|
| 33 |
- For documents from different domain for different purpose, the engine applies different analyzing and search strategy.
|
| 34 |
- Easily intervene and manipulate the data proccessing procedure when things goes beyond expectation.
|
|
@@ -57,56 +55,41 @@
|
|
| 57 |
|
| 58 |
- CPU >= 2 cores
|
| 59 |
- RAM >= 8 GB
|
| 60 |
-
- Docker
|
| 61 |
-
|
| 62 |
-
|
| 63 |
-
|
| 64 |
-
>
|
| 65 |
-
|
| 66 |
-
>
|
| 67 |
-
>
|
| 68 |
-
>
|
| 69 |
-
>
|
| 70 |
-
>
|
| 71 |
-
>
|
| 72 |
-
>
|
| 73 |
-
>
|
| 74 |
-
> ```
|
| 75 |
-
>
|
| 76 |
-
>
|
| 77 |
-
>
|
| 78 |
-
>
|
| 79 |
-
> vm.max_map_count
|
| 80 |
-
>
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
|
| 85 |
-
|
| 86 |
-
1. Clone the repo:
|
| 87 |
|
| 88 |
```bash
|
| 89 |
$ git clone https://github.com/infiniflow/ragflow.git
|
| 90 |
```
|
| 91 |
|
| 92 |
-
|
| 93 |
-
|
| 94 |
-
2. **Recommended**: In **docker/service_conf.yaml**, select the desired LLM factory in `user_default_llm` and update the `API_KEY` field with your own.
|
| 95 |
|
| 96 |
-
|
| 97 |
-
> - RagFlow now supports the flowing LLM factories: OpenAI, Tongyi-Qianwen, ZHIPU-AI, and Moonshot.
|
| 98 |
|
| 99 |
-
3. You now presented with two options for building the system: Using the pre-built images or building the images from source:
|
| 100 |
-
|
| 101 |
-
```bash
|
| 102 |
-
# To use the pre-built images:
|
| 103 |
-
$ cd ragflow/docker
|
| 104 |
-
$ docker compose up -d
|
| 105 |
-
```
|
| 106 |
```bash
|
| 107 |
-
# To build the images from source:
|
| 108 |
-
$ cd ragflow/
|
| 109 |
-
$ docker build -t infiniflow/ragflow:v1.0 .
|
| 110 |
$ cd ragflow/docker
|
| 111 |
$ docker compose up -d
|
| 112 |
```
|
|
@@ -115,7 +98,7 @@
|
|
| 115 |
|
| 116 |
4. Check the server status after pulling all images and having Docker up and running:
|
| 117 |
```bash
|
| 118 |
-
$ docker logs -f
|
| 119 |
```
|
| 120 |
*The following output confirms a successful launch of the system:*
|
| 121 |
|
|
@@ -133,7 +116,8 @@
|
|
| 133 |
INFO:werkzeug:Press CTRL+C to quit
|
| 134 |
```
|
| 135 |
|
| 136 |
-
5. In your browser, enter the IP address of your server
|
|
|
|
| 137 |
|
| 138 |
|
| 139 |
## π§ Configurations
|
|
@@ -148,16 +132,27 @@ Updates to system configurations require a system reboot to take effect *docker-
|
|
| 148 |
|
| 149 |
> If you change anything in [.env](./docker/.env), please check [service_conf.yaml](./docker/service_conf.yaml) which is a configuration of the back-end service and should be consistent with [.env](./docker/.env).
|
| 150 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 151 |
## π Roadmap
|
| 152 |
|
| 153 |
-
See the [
|
| 154 |
|
| 155 |
## π Community
|
| 156 |
|
| 157 |
- [Discord](https://discord.gg/uqQ4YMDf)
|
| 158 |
- [Twitter](https://twitter.com/infiniflowai)
|
| 159 |
-
- GitHub Discussions
|
| 160 |
|
| 161 |
## π Contributing
|
| 162 |
|
| 163 |
-
|
|
|
|
| 20 |
<img height="21" src="https://img.shields.io/badge/License-Apache--2.0-ffffff?style=flat-square&labelColor=d4eaf7&color=7d09f1" alt="license">
|
| 21 |
</a>
|
| 22 |
</p>
|
|
|
|
| 23 |
|
| 24 |
+
## π‘ What is RAGFlow?
|
| 25 |
|
| 26 |
+
[RAGFlow](http://demo.ragflow.io) is a knowledge management platform built on custom-build document understanding engine and LLM, with reasoned and well-founded answers to your question. Clone this repository, you can deploy your own knowledge management platform to empower your business with AI.
|
|
|
|
|
|
|
| 27 |
|
| 28 |
## π Key Features
|
| 29 |
+
|
| 30 |
- π**Custom-build document understanding engine.** Our deep learning engine is made according to the needs of analyzing and searching various type of documents in different domain.
|
| 31 |
- For documents from different domain for different purpose, the engine applies different analyzing and search strategy.
|
| 32 |
- Easily intervene and manipulate the data proccessing procedure when things goes beyond expectation.
|
|
|
|
| 55 |
|
| 56 |
- CPU >= 2 cores
|
| 57 |
- RAM >= 8 GB
|
| 58 |
+
- Docker: If you have not installed Docker on your local machine (Windows, Mac, or Linux), see [Install Docker Engine](https://docs.docker.com/engine/install/).
|
| 59 |
+
|
| 60 |
+
### Start up the server
|
| 61 |
+
|
| 62 |
+
1. Ensure `vm.max_map_count` > 65535:
|
| 63 |
+
|
| 64 |
+
> To check the value of `vm.max_map_count`:
|
| 65 |
+
>
|
| 66 |
+
> ```bash
|
| 67 |
+
> $ sysctl vm.max_map_count
|
| 68 |
+
> ```
|
| 69 |
+
>
|
| 70 |
+
> Reset `vm.max_map_count` to a value greater than 65535 if it is not.
|
| 71 |
+
>
|
| 72 |
+
> ```bash
|
| 73 |
+
> # In this case, we set it to 262144:
|
| 74 |
+
> $ sudo sysctl -w vm.max_map_count=262144
|
| 75 |
+
> ```
|
| 76 |
+
>
|
| 77 |
+
> This change will be reset after a system reboot. To ensure your change remains permanent, add or update the `vm.max_map_count` value in **/etc/sysctl.conf** accordingly:
|
| 78 |
+
>
|
| 79 |
+
> ```bash
|
| 80 |
+
> vm.max_map_count=262144
|
| 81 |
+
> ```
|
| 82 |
+
|
| 83 |
+
2. Clone the repo:
|
|
|
|
| 84 |
|
| 85 |
```bash
|
| 86 |
$ git clone https://github.com/infiniflow/ragflow.git
|
| 87 |
```
|
| 88 |
|
|
|
|
|
|
|
|
|
|
| 89 |
|
| 90 |
+
3. Build the pre-built Docker images and start up the server:
|
|
|
|
| 91 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 92 |
```bash
|
|
|
|
|
|
|
|
|
|
| 93 |
$ cd ragflow/docker
|
| 94 |
$ docker compose up -d
|
| 95 |
```
|
|
|
|
| 98 |
|
| 99 |
4. Check the server status after pulling all images and having Docker up and running:
|
| 100 |
```bash
|
| 101 |
+
$ docker logs -f ragflow-server
|
| 102 |
```
|
| 103 |
*The following output confirms a successful launch of the system:*
|
| 104 |
|
|
|
|
| 116 |
INFO:werkzeug:Press CTRL+C to quit
|
| 117 |
```
|
| 118 |
|
| 119 |
+
5. In your web browser, enter the IP address of your server as prompted.
|
| 120 |
+
*The show is on!*
|
| 121 |
|
| 122 |
|
| 123 |
## π§ Configurations
|
|
|
|
| 132 |
|
| 133 |
> If you change anything in [.env](./docker/.env), please check [service_conf.yaml](./docker/service_conf.yaml) which is a configuration of the back-end service and should be consistent with [.env](./docker/.env).
|
| 134 |
|
| 135 |
+
## π οΈ Build from source
|
| 136 |
+
|
| 137 |
+
To build the Docker images from source:
|
| 138 |
+
|
| 139 |
+
```bash
|
| 140 |
+
$ git clone https://github.com/infiniflow/ragflow.git
|
| 141 |
+
$ cd ragflow/
|
| 142 |
+
$ docker build -t infiniflow/ragflow:v1.0 .
|
| 143 |
+
$ cd ragflow/docker
|
| 144 |
+
$ docker compose up -d
|
| 145 |
+
```
|
| 146 |
+
|
| 147 |
## π Roadmap
|
| 148 |
|
| 149 |
+
See the [RAGFlow Roadmap 2024](https://github.com/infiniflow/ragflow/issues/162)
|
| 150 |
|
| 151 |
## π Community
|
| 152 |
|
| 153 |
- [Discord](https://discord.gg/uqQ4YMDf)
|
| 154 |
- [Twitter](https://twitter.com/infiniflowai)
|
|
|
|
| 155 |
|
| 156 |
## π Contributing
|
| 157 |
|
| 158 |
+
RAGFlow flourishes via open-source collaboration. In this spirit, we embrace diverse contributions from the community. If you would like to be a part, review our [Contribution Guidelines](https://github.com/infiniflow/ragflow/blob/main/CONTRIBUTING.md) first.
|