writinwaters
commited on
Commit
·
01957f5
1
Parent(s):
318a7e5
editorial updates (#525)
Browse files### What problem does this PR solve?
### Type of change
- [x] Documentation Update
- README.md +2 -1
- README_ja.md +1 -0
- README_zh.md +1 -0
- docs/faq.md +32 -16
README.md
CHANGED
|
@@ -138,9 +138,10 @@
|
|
| 138 |
* Running on http://x.x.x.x:9380
|
| 139 |
INFO:werkzeug:Press CTRL+C to quit
|
| 140 |
```
|
|
|
|
| 141 |
|
| 142 |
5. In your web browser, enter the IP address of your server and log in to RAGFlow.
|
| 143 |
-
>
|
| 144 |
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.
|
| 145 |
|
| 146 |
> See [./docs/llm_api_key_setup.md](./docs/llm_api_key_setup.md) for more information.
|
|
|
|
| 138 |
* Running on http://x.x.x.x:9380
|
| 139 |
INFO:werkzeug:Press CTRL+C to quit
|
| 140 |
```
|
| 141 |
+
> If you skip this confirmation step and directly log in to RAGFlow, your browser may prompt a `network anomaly` error because, at that moment, your RAGFlow may not be fully initialized.
|
| 142 |
|
| 143 |
5. In your web browser, enter the IP address of your server and log in to RAGFlow.
|
| 144 |
+
> With default settings, you only need to enter `http://IP_OF_YOUR_MACHINE` (**sans** port number) as the default HTTP serving port `80` can be omitted when using the default configurations.
|
| 145 |
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.
|
| 146 |
|
| 147 |
> See [./docs/llm_api_key_setup.md](./docs/llm_api_key_setup.md) for more information.
|
README_ja.md
CHANGED
|
@@ -138,6 +138,7 @@
|
|
| 138 |
* Running on http://x.x.x.x:9380
|
| 139 |
INFO:werkzeug:Press CTRL+C to quit
|
| 140 |
```
|
|
|
|
| 141 |
|
| 142 |
5. ウェブブラウザで、プロンプトに従ってサーバーの IP アドレスを入力し、RAGFlow にログインします。
|
| 143 |
> デフォルトの設定を使用する場合、デフォルトの HTTP サービングポート `80` は省略できるので、与えられたシナリオでは、`http://IP_OF_YOUR_MACHINE`(ポート番号は省略)だけを入力すればよい。
|
|
|
|
| 138 |
* Running on http://x.x.x.x:9380
|
| 139 |
INFO:werkzeug:Press CTRL+C to quit
|
| 140 |
```
|
| 141 |
+
> もし確認ステップをスキップして直接 RAGFlow にログインした場合、その時点で RAGFlow が完全に初期化されていない可能性があるため、ブラウザーがネットワーク異常エラーを表示するかもしれません。
|
| 142 |
|
| 143 |
5. ウェブブラウザで、プロンプトに従ってサーバーの IP アドレスを入力し、RAGFlow にログインします。
|
| 144 |
> デフォルトの設定を使用する場合、デフォルトの HTTP サービングポート `80` は省略できるので、与えられたシナリオでは、`http://IP_OF_YOUR_MACHINE`(ポート番号は省略)だけを入力すればよい。
|
README_zh.md
CHANGED
|
@@ -138,6 +138,7 @@
|
|
| 138 |
* Running on http://x.x.x.x:9380
|
| 139 |
INFO:werkzeug:Press CTRL+C to quit
|
| 140 |
```
|
|
|
|
| 141 |
|
| 142 |
5. 在你的浏览器中输入你的服务器对应的 IP 地址并登录 RAGFlow。
|
| 143 |
> 上面这个例子中,您只需输入 http://IP_OF_YOUR_MACHINE 即可:未改动过配置则无需输入端口(默认的 HTTP 服务端口 80)。
|
|
|
|
| 138 |
* Running on http://x.x.x.x:9380
|
| 139 |
INFO:werkzeug:Press CTRL+C to quit
|
| 140 |
```
|
| 141 |
+
> 如果您跳过这一步系统确认步骤就登录 RAGFlow,你的浏览器有可能会提示 `network anomaly` 或 `网络异常`,因为 RAGFlow 可能并未完全启动成功。
|
| 142 |
|
| 143 |
5. 在你的浏览器中输入你的服务器对应的 IP 地址并登录 RAGFlow。
|
| 144 |
> 上面这个例子中,您只需输入 http://IP_OF_YOUR_MACHINE 即可:未改动过配置则无需输入端口(默认的 HTTP 服务端口 80)。
|
docs/faq.md
CHANGED
|
@@ -68,24 +68,40 @@ $ docker compose up -d
|
|
| 68 |
curl https://hf-mirror.com
|
| 69 |
```
|
| 70 |
|
| 71 |
-
2. If your network works fine, the issue lies with the Docker network configuration.
|
|
|
|
|
|
|
| 72 |
```
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
docker build -t infiniflow/ragflow:v0.3.0 . --network host
|
| 77 |
```
|
| 78 |
|
| 79 |
-
### 2. Issues with huggingface models
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
| 84 |
-
- FileNotFoundError: [Errno 2] No such file or directory: '/root/.cache/huggingface/hub/models--InfiniFlow--deepdoc/snapshots/be0c1e50eef6047b412d1800aa89aba4d275f997/ocr.res'
|
| 85 |
-
- if your computer can access https://hf-mirror.com
|
| 86 |
-
- cd ragflow-0.3.0/docker/; docker compose down
|
| 87 |
-
- replace https://huggingface.co with https://hf-mirror.com in the ragflow-0.3.0/docker/docker-compose.yml
|
| 88 |
-
- docker compose up -d
|
| 89 |
|
| 90 |
#### 2.2. `MaxRetryError: HTTPSConnectionPool(host='hf-mirror.com', port=443)`
|
| 91 |
|
|
@@ -152,7 +168,7 @@ You will not log in to RAGFlow unless the server is fully initialized. Run `dock
|
|
| 152 |
|
| 153 |
#### 4.1 `dependency failed to start: container ragflow-mysql is unhealthy`
|
| 154 |
|
| 155 |
-
`dependency failed to start: container ragflow-mysql is unhealthy` means that your MySQL container failed to start. Try replacing `mysql:5.7.18` with `mariadb:10.5.8` in **docker-compose-base.yml
|
| 156 |
|
| 157 |
#### 4.2 `Realtime synonym is disabled, since no redis connection`
|
| 158 |
|
|
@@ -174,7 +190,7 @@ If your RAGFlow is deployed *locally*, try the following:
|
|
| 174 |
```bash
|
| 175 |
docker logs -f ragflow-server
|
| 176 |
```
|
| 177 |
-
2. Check if the **task_executor.py** process
|
| 178 |
3. Check if your RAGFlow server can access hf-mirror.com or huggingface.com.
|
| 179 |
|
| 180 |
|
|
|
|
| 68 |
curl https://hf-mirror.com
|
| 69 |
```
|
| 70 |
|
| 71 |
+
2. If your network works fine, the issue lies with the Docker network configuration. Replace the Docker building command:
|
| 72 |
+
```bash
|
| 73 |
+
docker build -t infiniflow/ragflow:vX.Y.Z.
|
| 74 |
```
|
| 75 |
+
With this:
|
| 76 |
+
```bash
|
| 77 |
+
docker build -t infiniflow/ragflow:vX.Y.Z. --network host
|
|
|
|
| 78 |
```
|
| 79 |
|
| 80 |
+
### 2. Issues with huggingface models
|
| 81 |
+
|
| 82 |
+
#### 2.1 Cannot access https://huggingface.co
|
| 83 |
+
|
| 84 |
+
A *locally* deployed RAGflow downloads OCR and embedding modules from [Huggingface website](https://huggingface.co) by default. If your machine is unable to access this site, the following error occurs and PDF parsing fails:
|
| 85 |
+
|
| 86 |
+
```
|
| 87 |
+
FileNotFoundError: [Errno 2] No such file or directory: '/root/.cache/huggingface/hub/models--InfiniFlow--deepdoc/snapshots/be0c1e50eef6047b412d1800aa89aba4d275f997/ocr.res'
|
| 88 |
+
```
|
| 89 |
+
To fix this issue, use https://hf-mirror.com instead:
|
| 90 |
+
|
| 91 |
+
1. Stop all containers and remove all related resources:
|
| 92 |
+
|
| 93 |
+
```bash
|
| 94 |
+
cd ragflow/docker/
|
| 95 |
+
docker compose down
|
| 96 |
+
```
|
| 97 |
+
|
| 98 |
+
2. Replace `https://huggingface.co` with `https://hf-mirror.com` in **ragflow/docker/docker-compose.yml**.
|
| 99 |
+
|
| 100 |
+
3. Start up the server:
|
| 101 |
|
| 102 |
+
```bash
|
| 103 |
+
docker compose up -d
|
| 104 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
|
| 106 |
#### 2.2. `MaxRetryError: HTTPSConnectionPool(host='hf-mirror.com', port=443)`
|
| 107 |
|
|
|
|
| 168 |
|
| 169 |
#### 4.1 `dependency failed to start: container ragflow-mysql is unhealthy`
|
| 170 |
|
| 171 |
+
`dependency failed to start: container ragflow-mysql is unhealthy` means that your MySQL container failed to start. Try replacing `mysql:5.7.18` with `mariadb:10.5.8` in **docker-compose-base.yml**.
|
| 172 |
|
| 173 |
#### 4.2 `Realtime synonym is disabled, since no redis connection`
|
| 174 |
|
|
|
|
| 190 |
```bash
|
| 191 |
docker logs -f ragflow-server
|
| 192 |
```
|
| 193 |
+
2. Check if the **task_executor.py** process exists.
|
| 194 |
3. Check if your RAGFlow server can access hf-mirror.com or huggingface.com.
|
| 195 |
|
| 196 |
|