You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: website/docs/configurations.md
+11-6Lines changed: 11 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -35,7 +35,7 @@ docker compose -f docker/docker-compose.yml up -d
35
35
Sets up environment for RAGFlow's dependencies: Elasticsearch/[Infinity](https://github.com/infiniflow/infinity), MySQL, MinIO, and Redis.
36
36
37
37
:::danger IMPORTANT
38
-
We do not actively maintain **docker-compose-CN-oc9.yml**, **docker-compose-gpu-CN-oc9.yml**, or **docker-compose-gpu.yml**, so use them at your own risk. However, you are welcome to file a pull request to improve any of them.
38
+
We do not actively maintain **docker-compose-CN-oc9.yml**, **docker-compose-macos.yml**, so use them at your own risk. However, you are welcome to file a pull request to improve them.
39
39
:::
40
40
41
41
## Docker environment variables
@@ -109,18 +109,23 @@ RAGFlow utilizes MinIO as its object storage solution, leveraging its scalabilit
109
109
:::tip NOTE
110
110
If you cannot download the RAGFlow Docker image, try the following mirrors.
The embedding model which text-embeddings-inference serves. Allowed values are one of `Qwen/Qwen3-Embedding-0.6B`(default), `BAAI/bge-m3`, and `BAAI/bge-small-en-v1.5`.
121
+
122
+
-`TEI_PORT`
123
+
The port used to expose the text-embeddings-inference service to the host machine, allowing **external** access to the text-embeddings-inference service running inside the Docker container. Defaults to `6380`.
124
+
120
125
### Timezone
121
126
122
-
-`TIMEZONE`
123
-
The local time zone. Defaults to `'Asia/Shanghai'`.
This image is approximately 9 GB in size. As it includes embedding models, it relies on external LLM services only.
55
-
56
-
:::danger IMPORTANT
57
-
- While we also test RAGFlow on ARM64 platforms, we do not maintain RAGFlow Docker images for ARM. However, you can build an image yourself on a `linux/arm64` or `darwin/arm64` host machine as well.
58
-
- For ARM64 platforms, please upgrade the `xgboost` version in **pyproject.toml** to `1.6.0` and ensure **unixODBC** is properly installed.
After building the infiniflow/ragflow:nightly-slim image, you are ready to launch a fully-functional RAGFlow service with all the required components, such as Elasticsearch, MySQL, MinIO, Redis, and more.
56
+
After building the infiniflow/ragflow:nightly image, you are ready to launch a fully-functional RAGFlow service with all the required components, such as Elasticsearch, MySQL, MinIO, Redis, and more.
75
57
76
58
## Example: Apple M2 Pro (Sequoia)
77
59
78
60
1. Edit Docker Compose Configuration
79
61
80
-
Open the `docker/.env` file. Find the `RAGFLOW_IMAGE` setting and change the image reference from `infiniflow/ragflow:v0.21.1-slim` to `infiniflow/ragflow:nightly-slim` to use the pre-built image.
62
+
Open the `docker/.env` file. Find the `RAGFLOW_IMAGE` setting and change the image reference from `infiniflow/ragflow:v0.21.1` to `infiniflow/ragflow:nightly` to use the pre-built image.
Copy file name to clipboardExpand all lines: website/docs/faq.mdx
+7-3Lines changed: 7 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -33,6 +33,8 @@ Each RAGFlow release is available in two editions:
33
33
-**Slim edition**: excludes built-in embedding models and is identified by a **-slim** suffix added to the version name. Example: `infiniflow/ragflow:v0.21.1-slim`
34
34
-**Full edition**: includes built-in embedding models and has no suffix added to the version name. Example: `infiniflow/ragflow:v0.21.1`
35
35
36
+
Note: Starting with `v0.22.0`, we ship only the slim edition and no longer append the **-slim** suffix to the image tag.
37
+
36
38
---
37
39
38
40
### Which embedding models can be deployed locally?
@@ -44,6 +46,8 @@ RAGFlow offers two Docker image editions, `v0.21.1-slim` and `v0.21.1`:
44
46
-`BAAI/bge-large-zh-v1.5`
45
47
-`maidalun1020/bce-embedding-base_v1`
46
48
49
+
Note: Starting with `v0.22.0`, we ship only the slim edition and no longer append the **-slim** suffix to the image tag.
50
+
47
51
---
48
52
49
53
### Where to find the version of RAGFlow? How to interpret it?
@@ -220,7 +224,7 @@ Ignore this warning and continue. All system warnings can be ignored.
Copy file name to clipboardExpand all lines: website/docs/guides/agent/agent_component_reference/retrieval.mdx
+2-3Lines changed: 2 additions & 3 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -47,7 +47,7 @@ By default, a combination of weighted keyword similarity and weighted vector cos
47
47
As a starter, you can skip this step to stay with the default retrieval method.
48
48
49
49
:::caution WARNING
50
-
Using a rerank model will *significantly* increase the system's response time. If you must use a rerank model, ensure you use a SaaS reranker; if you prefer a locally deployed rerank model, ensure you start RAGFlow with **docker-compose-gpu.yml**.
50
+
Using a rerank model will *significantly* increase the system's response time.
51
51
:::
52
52
53
53
### 5. Enable cross-language search
@@ -140,6 +140,5 @@ The global variable name for the output of the **Retrieval** component, which ca
140
140
141
141
Go through the checklist below for best performance:
142
142
143
-
- Leave the **Rerank model** field empty.
144
-
- If you must use a rerank model, ensure you use a SaaS reranker; if you prefer a locally deployed rerank model, ensure you start RAGFlow with **docker-compose-gpu.yml**.
143
+
- Leave the **Rerank model** field empty to disable rerank.
- If RAGFlow runs in Docker, the localhost is mapped within the RAGFlow Docker container as `host.docker.internal`. If Ollama runs on the same host machine, the right URL to use for Ollama would be `http://host.docker.internal:11434/' and you should check that Ollama is accessible from inside the RAGFlow container with:
Copy file name to clipboardExpand all lines: website/docs/guides/upgrade_ragflow.mdx
+9-45Lines changed: 9 additions & 45 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -7,15 +7,15 @@ slug: /upgrade_ragflow
7
7
importTabsfrom'@theme/Tabs';
8
8
importTabItemfrom'@theme/TabItem';
9
9
10
-
Upgrade RAGFlow to `nightly-slim`/`nightly` or the latest, published release.
10
+
Upgrade RAGFlow to `nightly` or the latest, published release.
11
11
12
12
:::info NOTE
13
13
Upgrading RAGFlow in itself will *not* remove your uploaded/historical data. However, be aware that `docker compose -f docker/docker-compose.yml down -v` will remove Docker container volumes, resulting in data loss.
14
14
:::
15
15
16
-
## Upgrade RAGFlow to `nightly-slim`/`nightly`, the most recent, tested Docker image
16
+
## Upgrade RAGFlow to `nightly`, the most recent, tested Docker image
17
17
18
-
`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).
18
+
`nightly` refers to the RAGFlow Docker image without embedding models.
19
19
20
20
To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker image:
21
21
@@ -27,27 +27,9 @@ To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker imag
27
27
28
28
2. Update **ragflow/docker/.env**:
29
29
30
-
<Tabs
31
-
defaultValue="nightly-slim"
32
-
values={[
33
-
{label: 'nightly-slim', value: 'nightly-slim'},
34
-
{label: 'nightly', value: 'nightly'},
35
-
]}>
36
-
<TabItemvalue="nightly-slim">
37
-
38
-
```bash
39
-
RAGFLOW_IMAGE=infiniflow/ragflow:nightly-slim
40
-
```
41
-
42
-
</TabItem>
43
-
<TabItemvalue="nightly">
44
-
45
-
```bash
46
-
RAGFLOW_IMAGE=infiniflow/ragflow:nightly
47
-
```
48
-
49
-
</TabItem>
50
-
</Tabs>
30
+
```bash
31
+
RAGFLOW_IMAGE=infiniflow/ragflow:nightly
32
+
```
51
33
52
34
3. Update RAGFlow image and restart RAGFlow:
53
35
@@ -74,27 +56,9 @@ To upgrade RAGFlow, you must upgrade **both** your code **and** your Docker imag
0 commit comments