yujunjun/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2025-06-26 22:19:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

Obsoleted dev and dev-slim (#3930)

Browse Source 
### What problem does this PR solve?

Obsoleted dev and dev-slim
### Type of change

- [x] Documentation Update
This commit is contained in:
Zhichang Yu 2024-12-09 12:44:57 +08:00 committed by GitHub
parent 3d735dca87
commit aaec630759
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
15 changed files with 143 additions and 126 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
.github/workflows/tests.yml vendored
View File

@ -55,28 +55,29 @@ jobs:
with:
version: ">=0.8.2"
- name: Build ragflow:dev-slim
- name: Build ragflow:nightly-slim
run: |
RUNNER_WORKSPACE_PREFIX=${RUNNER_WORKSPACE_PREFIX:-$HOME}
sudo docker pull ubuntu:22.04
sudo docker build --progress=plain --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
sudo docker build --progress=plain --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
- name: Build ragflow:dev
- name: Build ragflow:nightly
run: |
sudo docker build --progress=plain --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:dev .
sudo docker build --progress=plain --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly .
- name: Start ragflow:dev-slim
- name: Start ragflow:nightly-slim
run: |
echo "RAGFLOW_IMAGE=infiniflow/ragflow:nightly-slim" >> docker/.env
sudo docker compose -f docker/docker-compose.yml up -d
- name: Stop ragflow:dev-slim
- name: Stop ragflow:nightly-slim
if: always() # always run this step even if previous steps failed
run: |
sudo docker compose -f docker/docker-compose.yml down -v
- name: Start ragflow:dev
- name: Start ragflow:nightly
run: |
echo "RAGFLOW_IMAGE=infiniflow/ragflow:dev" >> docker/.env
echo "RAGFLOW_IMAGE=infiniflow/ragflow:nightly" >> docker/.env
sudo docker compose -f docker/docker-compose.yml up -d
- name: Run sdk tests against Elasticsearch
@ -100,12 +101,12 @@ jobs:
cd sdk/python && poetry install && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
- name: Stop ragflow:dev
- name: Stop ragflow:nightly
if: always() # always run this step even if previous steps failed
run: |
sudo docker compose -f docker/docker-compose.yml down -v
- name: Start ragflow:dev
- name: Start ragflow:nightly
run: |
sudo DOC_ENGINE=infinity docker compose -f docker/docker-compose.yml up -d
@ -129,7 +130,7 @@ jobs:
done
cd sdk/python && poetry install && source .venv/bin/activate && cd test/test_frontend_api && pytest -s --tb=short get_email.py test_dataset.py
- name: Stop ragflow:dev
- name: Stop ragflow:nightly
if: always() # always run this step even if previous steps failed
run: |
sudo DOC_ENGINE=infinity docker compose -f docker/docker-compose.yml down -v

32
README.md
View File

@ -165,29 +165,25 @@ releases! 🌟
$ git clone https://github.com/infiniflow/ragflow.git
```
3. Build the pre-built Docker images and start up the server:
3. Start up the server using the pre-built Docker images:
> The command below downloads the dev version Docker image for RAGFlow slim (`dev-slim`). Note that RAGFlow slim
Docker images do not include embedding models or Python libraries and hence are approximately 1GB in size.
> The command below downloads the v0.14.1 version Docker image for RAGFlow slim (`v0.14.1-slim`). Note that RAGFlow slim
Docker images do not include embedding models or Python libraries and hence are approximately 2 GB in size.
```bash
$ cd ragflow/docker
$ docker compose -f docker-compose.yml up -d
```
> - To download a RAGFlow slim Docker image of a specific version, update the `RAGFLOW_IMAGE` variable in *
*docker/.env** to your desired version. For example, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1-slim`. After
making this change, rerun the command above to initiate the download.
> - To download the dev version of RAGFlow Docker image *including* embedding models and Python libraries, update the
`RAGFLOW_IMAGE` variable in **docker/.env** to `RAGFLOW_IMAGE=infiniflow/ragflow:dev`. After making this change,
rerun the command above to initiate the download.
> - To download a specific version of RAGFlow Docker image *including* embedding models and Python libraries, update
the `RAGFLOW_IMAGE` variable in **docker/.env** to your desired version. For example,
`RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1`. After making this change, rerun the command above to initiate the
download.
| RAGFLOW_IMAGE tag in docker/.env | size | Including embedding models and related Python packages? | comments |
| -------------------------------- | ----- | ------------------------------------------------------- | ---------------------- |
| v0.14.1 | ~9 GB | YES | stable release |
| v0.14.1-slim | ~2 GB | NO | stable release |
| v0.15.0-dev1 | ~9 GB | YES | unstable beta release |
| v0.15.0-dev1-slim | ~2 GB | NO | unstable beta release |
| nightly | ~9 GB | YES | unstable nightly build |
| nightly-slim | ~2 GB | NO | unstable nightly build |
> **NOTE:** A RAGFlow Docker image that includes embedding models and Python libraries is approximately 9GB in size
and may take significantly longer time to load.
4. Check the server status after having the server up and running:
@ -267,12 +263,12 @@ RAGFlow uses Elasticsearch by default for storing full text and vectors. To swit
## 🔧 Build a Docker image without embedding models
This image is approximately 1 GB in size and relies on external LLM and embedding services.
This image is approximately 2 GB in size and relies on external LLM and embedding services.
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
```
## 🔧 Build a Docker image including embedding models
@ -282,7 +278,7 @@ This image is approximately 9 GB in size. As it includes embedding models, it re
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build -f Dockerfile -t infiniflow/ragflow:dev .
docker build -f Dockerfile -t infiniflow/ragflow:nightly .
```
## 🔨 Launch service from source for development

28
README_id.md
View File

@ -160,7 +160,7 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
3. Bangun image Docker pre-built dan jalankan server:
> Perintah di bawah ini akan mengunduh versi dev dari Docker image RAGFlow slim (`dev-slim`). Image RAGFlow slim
> Perintah di bawah ini akan mengunduh versi v0.14.1 dari Docker image RAGFlow slim (`v0.14.1-slim`). Image RAGFlow slim
tidak termasuk model embedding atau library Python dan berukuran sekitar 1GB.
```bash
@ -168,18 +168,16 @@ Coba demo kami di [https://demo.ragflow.io](https://demo.ragflow.io).
$ docker compose -f docker-compose.yml up -d
```
> - Untuk mengunduh versi tertentu dari image Docker RAGFlow slim, perbarui variabel `RAGFlow_IMAGE` di *
*docker/.env** sesuai dengan versi yang diinginkan. Misalnya, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1-slim`.
Setelah mengubah ini, jalankan ulang perintah di atas untuk memulai unduhan.
> - Untuk mengunduh versi dev dari image Docker RAGFlow *termasuk* model embedding dan library Python, perbarui
variabel `RAGFlow_IMAGE` di **docker/.env** menjadi `RAGFLOW_IMAGE=infiniflow/ragflow:dev`. Setelah mengubah ini,
jalankan ulang perintah di atas untuk memulai unduhan.
> - Untuk mengunduh versi tertentu dari image Docker RAGFlow *termasuk* model embedding dan library Python, perbarui
variabel `RAGFlow_IMAGE` di **docker/.env** sesuai dengan versi yang diinginkan. Misalnya,
`RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1`. Setelah mengubah ini, jalankan ulang perintah di atas untuk memulai unduhan.
| RAGFLOW_IMAGE tag in docker/.env | size | Including embedding models and related Python packages? | comments |
| -------------------------------- | ----- | ------------------------------------------------------- | ---------------------- |
| v0.14.1 | ~9 GB | YES | stable release |
| v0.14.1-slim | ~2 GB | NO | stable release |
| v0.15.0-dev1 | ~9 GB | YES | unstable beta release |
| v0.15.0-dev1-slim | ~2 GB | NO | unstable beta release |
| nightly | ~9 GB | YES | unstable nightly build |
| nightly-slim | ~2 GB | NO | unstable nightly build |
> **CATATAN:** Image Docker RAGFlow yang mencakup model embedding dan library Python berukuran sekitar 9GB
dan mungkin memerlukan waktu lebih lama untuk dimuat.
4. Periksa status server setelah server aktif dan berjalan:
@ -242,12 +240,12 @@ Pembaruan konfigurasi ini memerlukan reboot semua kontainer agar efektif:
## 🔧 Membangun Docker Image tanpa Model Embedding
Image ini berukuran sekitar 1 GB dan bergantung pada aplikasi LLM eksternal dan embedding.
Image ini berukuran sekitar 2 GB dan bergantung pada aplikasi LLM eksternal dan embedding.
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
```
## 🔧 Membangun Docker Image Termasuk Model Embedding
@ -257,7 +255,7 @@ Image ini berukuran sekitar 9 GB. Karena sudah termasuk model embedding, ia hany
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build -f Dockerfile -t infiniflow/ragflow:dev .
docker build -f Dockerfile -t infiniflow/ragflow:nightly .
```
## 🔨 Menjalankan Aplikasi dari untuk Pengembangan

20
README_ja.md
View File

@ -141,18 +141,22 @@
3. ビルド済みの Docker イメージをビルドし、サーバーを起動する:
> 以下のコマンドは、RAGFlow slim（`dev-slim`）の開発版Dockerイメージをダウンロードします。RAGFlow slimのDockerイメージには、埋め込みモデルやPythonライブラリが含まれていないため、サイズは約1GBです。
> 以下のコマンドは、RAGFlow slim（`v0.14.1-slim`）の開発版Dockerイメージをダウンロードします。RAGFlow slimのDockerイメージには、埋め込みモデルやPythonライブラリが含まれていないため、サイズは約1GBです。
```bash
$ cd ragflow/docker
$ docker compose -f docker-compose.yml up -d
```
> - 特定のバージョンのRAGFlow slim Dockerイメージをダウンロードするには、**docker/.env**内の`RAGFlow_IMAGE`変数を希望のバージョンに更新します。例えば、`RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1`とします。この変更を行った後、上記のコマンドを再実行してダウンロードを開始してください。
> - RAGFlowの埋め込みモデルとPythonライブラリを含む開発版Dockerイメージをダウンロードするには、**docker/.env**内の`RAGFlow_IMAGE`変数を`RAGFLOW_IMAGE=infiniflow/ragflow:dev`に更新します。この変更を行った後、上記のコマンドを再実行してダウンロードを開始してください。
> - 特定のバージョンのRAGFlow Dockerイメージ（埋め込みモデルとPythonライブラリを含む）をダウンロードするには、**docker/.env**内の`RAGFlow_IMAGE`変数を希望のバージョンに更新します。例えば、`RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1`とします。この変更を行った後、上記のコマンドを再実行してダウンロードを開始してください。
> **NOTE:** 埋め込みモデルとPythonライブラリを含むRAGFlow Dockerイメージのサイズは約9GBであり、読み込みにかなりの時間がかかる場合があります。
| RAGFLOW_IMAGE tag in docker/.env | size | Including embedding models and related Python packages? | comments |
| -------------------------------- | ----- | ------------------------------------------------------- | ---------------------- |
| v0.14.1 | ~9 GB | YES | stable release |
| v0.14.1-slim | ~2 GB | NO | stable release |
| v0.15.0-dev1 | ~9 GB | YES | unstable beta release |
| v0.15.0-dev1-slim | ~2 GB | NO | unstable beta release |
| nightly | ~9 GB | YES | unstable nightly build |
| nightly-slim | ~2 GB | NO | unstable nightly build |
4. サーバーを立ち上げた後、サーバーの状態を確認する:
@ -228,7 +232,7 @@ RAGFlow はデフォルトで Elasticsearch を使用して全文とベクトル
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
```
## 🔧 ソースコードをコンパイルしたDockerイメージ（埋め込みモデルを含む）
@ -238,7 +242,7 @@ docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:dev-slim
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build -f Dockerfile -t infiniflow/ragflow:dev .
docker build -f Dockerfile -t infiniflow/ragflow:nightly .
```
## 🔨 ソースコードからサービスを起動する方法

22
README_ko.md
View File

@ -145,18 +145,24 @@
3. 미리 빌드된 Docker 이미지를 생성하고 서버를 시작하세요:
> 아래의 명령은 RAGFlow slim(dev-slim)의 개발 버전 Docker 이미지를 다운로드합니다. RAGFlow slim Docker 이미지에는 임베딩 모델이나 Python 라이브러리가 포함되어 있지 않으므로 크기는 약 1GB입니다.
> 아래의 명령은 RAGFlow slim(v0.14.1-slim)의 개발 버전 Docker 이미지를 다운로드합니다. RAGFlow slim Docker 이미지에는 임베딩 모델이나 Python 라이브러리가 포함되어 있지 않으므로 크기는 약 1GB입니다.
```bash
$ cd ragflow/docker
$ docker compose -f docker-compose.yml up -d
```
> - 특정 버전의 RAGFlow slim Docker 이미지를 다운로드하려면, **docker/.env**에서 `RAGFlow_IMAGE` 변수를 원하는 버전으로 업데이트하세요. 예를 들어, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1-slim`으로 설정합니다. 이 변경을 완료한 후, 위의 명령을 다시 실행하여 다운로드를 시작하세요.
> - RAGFlow의 임베딩 모델과 Python 라이브러리를 포함한 개발 버전 Docker 이미지를 다운로드하려면, **docker/.env**에서 `RAGFlow_IMAGE` 변수를 `RAGFLOW_IMAGE=infiniflow/ragflow:dev`로 업데이트하세요. 이 변경을 완료한 후, 위의 명령을 다시 실행하여 다운로드를 시작하세요.
> - 특정 버전의 RAGFlow Docker 이미지를 임베딩 모델과 Python 라이브러리를 포함하여 다운로드하려면, **docker/.env**에서 `RAGFlow_IMAGE` 변수를 원하는 버전으로 업데이트하세요. 예를 들어, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1` 로 설정합니다. 이 변경을 완료한 후, 위의 명령을 다시 실행하여 다운로드를 시작하세요.
> **NOTE:** 임베딩 모델과 Python 라이브러리를 포함한 RAGFlow Docker 이미지의 크기는 약 9GB이며, 로드하는 데 상당히 오랜 시간이 걸릴 수 있습니다.
| RAGFLOW_IMAGE tag in docker/.env | size | Including embedding models and related Python packages? | comments |
| -------------------------------- | ----- | ------------------------------------------------------- | ---------------------- |
| v0.14.1 | ~9 GB | YES | stable release |
| v0.14.1-slim | ~2 GB | NO | stable release |
| v0.15.0-dev1 | ~9 GB | YES | unstable beta release |
| v0.15.0-dev1-slim | ~2 GB | NO | unstable beta release |
| nightly | ~9 GB | YES | unstable nightly build |
| nightly-slim | ~2 GB | NO | unstable nightly build |
4. 서버가 시작된 후 서버 상태를 확인하세요:
@ -230,7 +236,7 @@ RAGFlow 는 기본적으로 Elasticsearch 를 사용하여 전체 텍스트 및
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
```
## 🔧 소스 코드로 Docker 이미지를 컴파일합니다(임베딩 모델 포함)
@ -240,7 +246,7 @@ docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:dev-slim
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build -f Dockerfile -t infiniflow/ragflow:dev .
docker build -f Dockerfile -t infiniflow/ragflow:nightly .
```
## 🔨 소스 코드로 서비스를 시작합니다.

23
README_zh.md
View File

@ -142,18 +142,23 @@
3. 进入 **docker** 文件夹，利用提前编译好的 Docker 镜像启动服务器：
> 运行以下命令会自动下载 dev 版的 RAGFlow slim Docker 镜像（`dev-slim`），该镜像并不包含 embedding 模型以及一些 Python 库，因此镜像大小约 1GB。
> 运行以下命令会自动下载 v0.14.1 版的 RAGFlow slim Docker 镜像（`v0.14.1-slim`），该镜像并不包含 embedding 模型以及一些 Python 库，因此镜像大小约 1GB。
```bash
$ cd ragflow/docker
$ docker compose -f docker-compose.yml up -d
```
> - 如果你想下载并运行特定版本的 RAGFlow slim Docker 镜像，请在 **docker/.env** 文件中找到 `RAGFLOW_IMAGE` 变量，将其改为对应版本。例如 `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1-slim`，然后再运行上述命令。
> - 如果您想安装内置 embedding 模型和 Python 库的 dev 版本的 Docker 镜像，需要将 **docker/.env** 文件中的 `RAGFLOW_IMAGE` 变量修改为： `RAGFLOW_IMAGE=infiniflow/ragflow:dev`。
> - 如果您想安装内置 embedding 模型和 Python 库的指定版本的 RAGFlow Docker 镜像，需要将 **docker/.env** 文件中的 `RAGFLOW_IMAGE` 变量修改为： `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1`。修改后，再运行上面的命令。
> **注意：** 安装内置 embedding 模型和 Python 库的指定版本的 RAGFlow Docker 镜像大小约 9 GB，可能需要更长时间下载，请耐心等待。
| RAGFLOW_IMAGE tag in docker/.env | 尺寸 | 内置 embedding 模型和相关 Python 库? | 描述 |
| -------------------------------- | ----- | ------------------------------------------------------- | ---------------------- |
| v0.14.1 | ~9 GB | YES | stable release |
| v0.14.1-slim | ~2 GB | NO | stable release |
| v0.15.0-dev1 | ~9 GB | YES | unstable beta release |
| v0.15.0-dev1-slim | ~2 GB | NO | unstable beta release |
| nightly | ~9 GB | YES | unstable nightly build |
| nightly-slim | ~2 GB | NO | unstable nightly build |
4. 服务器启动成功后再次确认服务器状态：
```bash
@ -230,12 +235,12 @@ RAGFlow 默认使用 Elasticsearch 存储文本和向量数据. 如果要切换
## 🔧 源码编译 Docker 镜像（不含 embedding 模型）
本 Docker 镜像大小约 1 GB 左右并且依赖外部的大模型和 embedding 服务。
本 Docker 镜像大小约 2 GB 左右并且依赖外部的大模型和 embedding 服务。
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
docker build --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
```
## 🔧 源码编译 Docker 镜像（包含 embedding 模型）
@ -245,7 +250,7 @@ docker build --build-arg LIGHTEN=1 --build-arg NEED_MIRROR=1 -f Dockerfile -t in
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:dev .
docker build --build-arg NEED_MIRROR=1 -f Dockerfile -t infiniflow/ragflow:nightly .
```
## 🔨 以源代码启动服务

20
docker/.env
View File

@ -80,13 +80,13 @@ REDIS_PASSWORD=infini_rag_flow
SVR_HTTP_PORT=9380
# The RAGFlow Docker image to download.
# Defaults to the dev-slim edition, which is the RAGFlow Docker image without embedding models.
RAGFLOW_IMAGE=infiniflow/ragflow:dev
# Defaults to the v0.14.1-slim edition, which is the RAGFlow Docker image without embedding models.
RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1-slim
#
# To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
# RAGFLOW_IMAGE=infiniflow/ragflow:dev
# RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1
#
# The Docker image of the dev edition includes:
# The Docker image of the v0.14.1 edition includes:
# - Built-in embedding models:
# - BAAI/bge-large-zh-v1.5
# - BAAI/bge-reranker-v2-m3
@ -107,13 +107,13 @@ RAGFLOW_IMAGE=infiniflow/ragflow:dev
# If you cannot download the RAGFlow Docker image:
#
# - For the `dev-slim` edition, uncomment either of the following:
# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:dev-slim
# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:dev-slim
# - For the `nightly-slim` edition, uncomment either of the following:
# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly-slim
# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly-slim
#
# - For the `dev` edition, uncomment either of the following:
# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:dev
# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:dev
# - For the `nightly` edition, uncomment either of the following:
# RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly
# RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly
# The local time zone.
TIMEZONE='Asia/Shanghai'

16
docker/README.md
View File

@ -75,8 +75,8 @@ The [.env](./.env) file contains important environment variables for Docker.
- `RAGFLOW-IMAGE`
The Docker image edition. Available editions:
- `infiniflow/ragflow:dev-slim` (default): The RAGFlow Docker image without embedding models.
- `infiniflow/ragflow:dev`: The RAGFlow Docker image with embedding models including:
- `infiniflow/ragflow:v0.14.1-slim` (default): The RAGFlow Docker image without embedding models.
- `infiniflow/ragflow:v0.14.1`: The RAGFlow Docker image with embedding models including:
- Built-in embedding models:
- `BAAI/bge-large-zh-v1.5`
- `BAAI/bge-reranker-v2-m3`
@ -95,12 +95,12 @@ The [.env](./.env) file contains important environment variables for Docker.
> [!TIP]
> If you cannot download the RAGFlow Docker image, try the following mirrors.
>
> - For the `dev-slim` edition:
> - `RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:dev-slim` or,
> - `RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:dev-slim`.
> - For the `dev` edition:
> - `RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:dev` or,
> - `RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:dev`.
> - For the `nightly-slim` edition:
> - `RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly-slim` or,
> - `RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly-slim`.
> - For the `nightly` edition:
> - `RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly` or,
> - `RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly`.
### Timezone

16
docs/configurations.md
View File

@ -93,8 +93,8 @@ The [.env](https://github.com/infiniflow/ragflow/blob/main/docker/.env) file con
- `RAGFLOW-IMAGE`
The Docker image edition. Available editions:
- `infiniflow/ragflow:dev-slim` (default): The RAGFlow Docker image without embedding models.
- `infiniflow/ragflow:dev`: The RAGFlow Docker image with embedding models including:
- `infiniflow/ragflow:v0.14.1-slim` (default): The RAGFlow Docker image without embedding models.
- `infiniflow/ragflow:v0.14.1`: The RAGFlow Docker image with embedding models including:
- Built-in embedding models:
- `BAAI/bge-large-zh-v1.5`
- `BAAI/bge-reranker-v2-m3`
@ -113,12 +113,12 @@ The [.env](https://github.com/infiniflow/ragflow/blob/main/docker/.env) file con
:::tip NOTE
If you cannot download the RAGFlow Docker image, try the following mirrors.
- For the `dev-slim` edition:
- `RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:dev-slim` or,
- `RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:dev-slim`.
- For the `dev` edition:
- `RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:dev` or,
- `RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:dev`.
- For the `nightly-slim` edition:
- `RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly-slim` or,
- `RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly-slim`.
- For the `nightly` edition:
- `RAGFLOW_IMAGE=swr.cn-north-4.myhuaweicloud.com/infiniflow/ragflow:nightly` or,
- `RAGFLOW_IMAGE=registry.cn-hangzhou.aliyuncs.com/infiniflow/ragflow:nightly`.
:::
### Timezone

6
docs/guides/develop/build_docker_image.mdx
View File

@ -31,7 +31,7 @@ A guide explaining how to build a RAGFlow Docker image from its source code. By
]}>
<TabItem value="without">
This image is approximately 1 GB in size and relies on external LLM and embedding services.
This image is approximately 2 GB in size and relies on external LLM and embedding services.
:::tip NOTE
While we also test RAGFlow on ARM64 platforms, we do not plan to maintain RAGFlow Docker images for ARM. However, you can build an image yourself on a `linux/arm64` or `darwin/arm64` host machine as well.
@ -40,7 +40,7 @@ While we also test RAGFlow on ARM64 platforms, we do not plan to maintain RAGFlo
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:dev-slim .
docker build --build-arg LIGHTEN=1 -f Dockerfile -t infiniflow/ragflow:nightly-slim .
```
@ -56,7 +56,7 @@ While we also test RAGFlow on ARM64 platforms, we do not plan to maintain RAGFlo
```bash
git clone https://github.com/infiniflow/ragflow.git
cd ragflow/
docker build -f Dockerfile -t infiniflow/ragflow:dev .
docker build -f Dockerfile -t infiniflow/ragflow:nightly .
```
</TabItem>

22
docs/guides/upgrade_ragflow.mdx
View File

@ -7,11 +7,11 @@ slug: /upgrade_ragflow
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
Upgrade RAGFlow to `dev-slim`/`dev` or the latest, published release.
Upgrade RAGFlow to `nightly-slim`/`nightly` or the latest, published release.
## Upgrade RAGFlow to `dev-slim`/`dev`, the most recent, tested Docker image
## Upgrade RAGFlow to `nightly-slim`/`nightly`, the most recent, tested Docker image
`dev-slim` refers to the RAGFlow Docker image *without* embedding models, while `dev` refers to the RAGFlow Docker image with embedding models. For details on their differences, see [ragflow/docker/.env](https://github.com/infiniflow/ragflow/blob/main/docker/.env).
`nightly-slim` refers to the RAGFlow Docker image *without* embedding models, while `nightly` refers to the RAGFlow Docker image with embedding models. For details on their differences, see [ragflow/docker/.env](https://github.com/infiniflow/ragflow/blob/main/docker/.env).
To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker image:
@ -24,22 +24,22 @@ To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker imag
2. Update **ragflow/docker/.env**:
<Tabs
defaultValue="dev-slim"
defaultValue="nightly-slim"
values={[
{label: 'dev-slim', value: 'dev-slim'},
{label: 'dev', value: 'dev'},
{label: 'nightly-slim', value: 'nightly-slim'},
{label: 'nightly', value: 'nightly'},
]}>
<TabItem value="dev-slim">
<TabItem value="nightly-slim">
```bash
RAGFLOW_IMAGE=infiniflow/ragflow:dev-slim
RAGFLOW_IMAGE=infiniflow/ragflow:nightly-slim
```
</TabItem>
<TabItem value="dev">
<TabItem value="nightly">
```bash
RAGFLOW_IMAGE=infiniflow/ragflow:dev
RAGFLOW_IMAGE=infiniflow/ragflow:nightly
```
</TabItem>
@ -65,7 +65,7 @@ To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker imag
2. Switch to the latest, officially published release, e.g., `v0.14.1`:
```bash
git checkout v0.14.1
git checkout -f v0.14.1
```
3. Update **ragflow/docker/.env** as follows:

21
docs/quickstart.mdx
View File

@ -177,20 +177,27 @@ This section provides instructions on setting up the RAGFlow server on Linux. If
```bash
$ git clone https://github.com/infiniflow/ragflow.git
$ cd ragflow
$ git checkout -f v0.14.1
```
3. Build the pre-built Docker images and start up the server:
3. Use the pre-built Docker images and start up the server:
> The command below downloads the dev version Docker image for RAGFlow slim (`dev-slim`). Note that RAGFlow slim Docker images do not include embedding models or Python libraries and hence are approximately 1GB in size.
> The command below downloads the v0.14.1 version Docker image for RAGFlow slim (`v0.14.1-slim`). Note that RAGFlow slim Docker images do not include embedding models or Python libraries and hence are approximately 2 GB in size.
```bash
$ cd ragflow/docker
$ docker compose -f docker-compose.yml up -d
$ docker compose -f docker/docker-compose.yml up -d
```
> - To download a RAGFlow slim Docker image of a specific version, update the `RAGFlOW_IMAGE` variable in **docker/.env** to your desired version. For example, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1-slim`. After making this change, rerun the command above to initiate the download.
> - To download the dev version of RAGFlow Docker image *including* embedding models and Python libraries, update the `RAGFlOW_IMAGE` variable in **docker/.env** to `RAGFLOW_IMAGE=infiniflow/ragflow:dev`. After making this change, rerun the command above to initiate the download.
> - To download a specific version of RAGFlow Docker image *including* embedding models and Python libraries, update the `RAGFlOW_IMAGE` variable in **docker/.env** to your desired version. For example, `RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1`. After making this change, rerun the command above to initiate the download.
| RAGFLOW_IMAGE tag in docker/.env | size | Including embedding models and related Python packages? | comments |
| -------------------------------- | ----- | ------------------------------------------------------- | ---------------------- |
| v0.14.1 | ~9 GB | YES | stable release |
| v0.14.1-slim | ~2 GB | NO | stable release |
| v0.15.0-dev1 | ~9 GB | YES | unstable beta release |
| v0.15.0-dev1-slim | ~2 GB | NO | unstable beta release |
| nightly | ~9 GB | YES | unstable nightly build |
| nightly-slim | ~2 GB | NO | unstable nightly build |
:::tip NOTE
A RAGFlow Docker image that includes embedding models and Python libraries is approximately 9GB in size and may take significantly longer time to load.

6
docs/references/faq.md
View File

@ -42,10 +42,10 @@ We officially support x86 CPU and nvidia GPU. While we also test RAGFlow on ARM6
### Which embedding models can be deployed locally?
RAGFlow offers two Docker image editions, `dev-slim` and `dev`:
RAGFlow offers two Docker image editions, `v0.14.1-slim` and `v0.14.1`:
- `infiniflow/ragflow:dev-slim` (default): The RAGFlow Docker image without embedding models.
- `infiniflow/ragflow:dev`: The RAGFlow Docker image with embedding models including:
- `infiniflow/ragflow:v0.14.1-slim` (default): The RAGFlow Docker image without embedding models.
- `infiniflow/ragflow:v0.14.1`: The RAGFlow Docker image with embedding models including:
- Built-in embedding models:
- `BAAI/bge-large-zh-v1.5`
- `BAAI/bge-reranker-v2-m3`

6
docs/release_notes.md
View File

@ -102,11 +102,11 @@ Released on September 30, 2024.
As of this release, RAGFlow offers slim editions of its Docker images to improve the experience for users with limited Internet access. A slim edition of RAGFlow's Docker image does not include built-in BGE/BCE embedding models and has a size of about 1GB; a full edition of RAGFlow is approximately 9GB and includes both built-in embedding models and embedding models that will be downloaded once you select them in the RAGFlow UI.
The default Docker image edition is `dev-slim`. The following list clarifies the differences between various editions:
The default Docker image edition is `nightly-slim`. The following list clarifies the differences between various editions:
- `dev-slim`: The slim edition of the most recent tested Docker image.
- `nightly-slim`: The slim edition of the most recent tested Docker image.
- `v0.12.0-slim`: The slim edition of the most recent **officially released** Docker image.
- `dev`: The full edition of the most recent tested Docker image.
- `nightly`: The full edition of the most recent tested Docker image.
- `v0.12.0`: The full edition of the most recent **officially released** Docker image.
See [Upgrade RAGFlow](https://ragflow.io/docs/dev/upgrade_ragflow) for instructions on upgrading.

8
helm/values.yaml
View File

@ -27,13 +27,13 @@ env:
REDIS_PASSWORD: infini_rag_flow_helm
# The RAGFlow Docker image to download.
# Defaults to the dev-slim edition, which is the RAGFlow Docker image without embedding models.
RAGFLOW_IMAGE: infiniflow/ragflow:dev-slim
# Defaults to the v0.14.1-slim edition, which is the RAGFlow Docker image without embedding models.
RAGFLOW_IMAGE: infiniflow/ragflow:v0.14.1-slim
#
# To download the RAGFlow Docker image with embedding models, uncomment the following line instead:
# RAGFLOW_IMAGE=infiniflow/ragflow:dev
# RAGFLOW_IMAGE=infiniflow/ragflow:v0.14.1
#
# The Docker image of the dev edition includes:
# The Docker image of the v0.14.1 edition includes:
# - Built-in embedding models:
# - BAAI/bge-large-zh-v1.5
# - BAAI/bge-reranker-v2-m3