writinwaters
commited on
Commit
·
31b7ac4
1
Parent(s):
a86164e
Updated FAQ plus miscellaneous updates. (#364)
Browse files### What problem does this PR solve?
### Type of change
- [x] Documentation Update
- README.md +1 -1
- README_ja.md +9 -5
- README_zh.md +9 -5
- docs/faq.md +9 -9
README.md
CHANGED
@@ -56,7 +56,7 @@
|
|
56 |
## 📌 Latest Features
|
57 |
|
58 |
- 2024-04-11 Support [Xinference](./docs/xinference.md) for local LLM deployment.
|
59 |
-
- 2024-04-10 Add a new layout recognization model
|
60 |
- 2024-04-08 Support [Ollama](./docs/ollama.md) for local LLM deployment.
|
61 |
- 2024-04-07 Support Chinese UI.
|
62 |
|
|
|
56 |
## 📌 Latest Features
|
57 |
|
58 |
- 2024-04-11 Support [Xinference](./docs/xinference.md) for local LLM deployment.
|
59 |
+
- 2024-04-10 Add a new layout recognization model for analyzing Laws documentation.
|
60 |
- 2024-04-08 Support [Ollama](./docs/ollama.md) for local LLM deployment.
|
61 |
- 2024-04-07 Support Chinese UI.
|
62 |
|
README_ja.md
CHANGED
@@ -53,6 +53,13 @@
|
|
53 |
- 複数の想起と融合された再ランク付け。
|
54 |
- 直感的な API によってビジネスとの統合がシームレスに。
|
55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
## 🔎 システム構成
|
57 |
|
58 |
<div align="center" style="margin-top:20px;margin-bottom:20px;">
|
@@ -170,12 +177,9 @@ $ chmod +x ./entrypoint.sh
|
|
170 |
$ docker compose up -d
|
171 |
```
|
172 |
|
173 |
-
##
|
174 |
|
175 |
-
-
|
176 |
-
- 2024-04-10 メソッド「Laws」に新しいレイアウト認識モデルを追加します。
|
177 |
-
- 2024-04-08 [Ollama](./docs/ollama.md) を使用した大規模モデルのローカライズされたデプロイメントをサポートします。
|
178 |
-
- 2024-04-07 中国語インターフェースをサポートします。
|
179 |
|
180 |
## 📜 ロードマップ
|
181 |
|
|
|
53 |
- 複数の想起と融合された再ランク付け。
|
54 |
- 直感的な API によってビジネスとの統合がシームレスに。
|
55 |
|
56 |
+
## 📌 最新の機能
|
57 |
+
|
58 |
+
- 2024-04-11 ローカル LLM デプロイメント用に [Xinference](./docs/xinference.md) をサポートします。
|
59 |
+
- 2024-04-10 メソッド「Laws」に新しいレイアウト認識モデルを追加します。
|
60 |
+
- 2024-04-08 [Ollama](./docs/ollama.md) を使用した大規模モデルのローカライズされたデプロイメントをサポートします。
|
61 |
+
- 2024-04-07 中国語インターフェースをサポートします。
|
62 |
+
|
63 |
## 🔎 システム構成
|
64 |
|
65 |
<div align="center" style="margin-top:20px;margin-bottom:20px;">
|
|
|
177 |
$ docker compose up -d
|
178 |
```
|
179 |
|
180 |
+
## 📚 ドキュメンテーション
|
181 |
|
182 |
+
- [FAQ](./docs/faq.md)
|
|
|
|
|
|
|
183 |
|
184 |
## 📜 ロードマップ
|
185 |
|
README_zh.md
CHANGED
@@ -53,6 +53,13 @@
|
|
53 |
- 基于多路召回、融合重排序。
|
54 |
- 提供易用的 API,可以轻松集成到各类企业系统。
|
55 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
## 🔎 系统架构
|
57 |
|
58 |
<div align="center" style="margin-top:20px;margin-bottom:20px;">
|
@@ -170,12 +177,9 @@ $ chmod +x ./entrypoint.sh
|
|
170 |
$ docker compose up -d
|
171 |
```
|
172 |
|
173 |
-
##
|
174 |
|
175 |
-
-
|
176 |
-
- 2024-04-10 为‘Laws’版面分析增加了模型。
|
177 |
-
- 2024-04-08 支持用 [Ollama](./docs/ollama.md) 对大模型进行本地化部署。
|
178 |
-
- 2024-04-07 支持中文界面。
|
179 |
|
180 |
## 📜 路线图
|
181 |
|
|
|
53 |
- 基于多路召回、融合重排序。
|
54 |
- 提供易用的 API,可以轻松集成到各类企业系统。
|
55 |
|
56 |
+
## 📌 新增功能
|
57 |
+
|
58 |
+
- 2024-04-11 支持用 [Xinference](./docs/xinference.md) 本地化部署大模型。
|
59 |
+
- 2024-04-10 为‘Laws’版面分析增加了底层模型。
|
60 |
+
- 2024-04-08 支持用 [Ollama](./docs/ollama.md) 本地化部署大模型。
|
61 |
+
- 2024-04-07 支持中文界面。
|
62 |
+
|
63 |
## 🔎 系统架构
|
64 |
|
65 |
<div align="center" style="margin-top:20px;margin-bottom:20px;">
|
|
|
177 |
$ docker compose up -d
|
178 |
```
|
179 |
|
180 |
+
## 📚 技术文档
|
181 |
|
182 |
+
- [FAQ](./docs/faq.md)
|
|
|
|
|
|
|
183 |
|
184 |
## 📜 路线图
|
185 |
|
docs/faq.md
CHANGED
@@ -45,14 +45,14 @@ This feature and the related APIs are still in development. Contributions are we
|
|
45 |
|
46 |
### How to increase the length of RAGFlow responses?
|
47 |
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
|
52 |
|
53 |
### What does Empty response mean? How to set it?
|
54 |
|
55 |
-
You limit what the system responds to what you specify in Empty response if nothing is retrieved from your knowledge base. If you do not specify anything in Empty response
|
56 |
|
57 |
### Can I set the base URL for OpenAI somewhere?
|
58 |
|
@@ -70,9 +70,9 @@ You can use Ollama to deploy local LLM. See [here](https://github.com/infiniflow
|
|
70 |
|
71 |
### How to configure RAGFlow to respond with 100% matched results, rather than utilizing LLM?
|
72 |
|
73 |
-
|
74 |
-
|
75 |
-
|
76 |
|
77 |
## Debugging
|
78 |
|
@@ -136,7 +136,7 @@ $ docker ps
|
|
136 |
es:
|
137 |
hosts: 'http://es01:9200'
|
138 |
```
|
139 |
-
-
|
140 |
```bash
|
141 |
curl http://<IP_OF_ES>:<PORT_OF_ES>
|
142 |
```
|
@@ -144,7 +144,7 @@ $ docker ps
|
|
144 |
|
145 |
### How to handle `{"data":null,"retcode":100,"retmsg":"<NotFound '404: Not Found'>"}`?
|
146 |
|
147 |
-
Your IP address or port number may be incorrect. If you are using the default configurations, enter http://<IP_OF_YOUR_MACHINE> (NOT `localhost`, NOT 9380, AND NO PORT NUMBER REQUIRED
|
148 |
|
149 |
|
150 |
|
|
|
45 |
|
46 |
### How to increase the length of RAGFlow responses?
|
47 |
|
48 |
+
1. Right click the desired dialog to display the **Chat Configuration** window.
|
49 |
+
2. Switch to the **Model Setting** tab and adjust the **Max Tokens** slider to get the desired length.
|
50 |
+
3. Click **OK** to confirm your change.
|
51 |
|
52 |
|
53 |
### What does Empty response mean? How to set it?
|
54 |
|
55 |
+
You limit what the system responds to what you specify in **Empty response** if nothing is retrieved from your knowledge base. If you do not specify anything in **Empty response**, you let your LLM improvise, giving it a chance to hallucinate.
|
56 |
|
57 |
### Can I set the base URL for OpenAI somewhere?
|
58 |
|
|
|
70 |
|
71 |
### How to configure RAGFlow to respond with 100% matched results, rather than utilizing LLM?
|
72 |
|
73 |
+
1. Click the **Knowledge Base** tab in the middle top of the page.
|
74 |
+
2. Right click the desired knowledge base to display the **Configuration** dialogue.
|
75 |
+
3. Choose **Q&A** as the chunk method and click **Save** to confirm your change.
|
76 |
|
77 |
## Debugging
|
78 |
|
|
|
136 |
es:
|
137 |
hosts: 'http://es01:9200'
|
138 |
```
|
139 |
+
- If you run RAGFlow outside of Docker, verify the ES host setting in **conf/service_conf.yml** using:
|
140 |
```bash
|
141 |
curl http://<IP_OF_ES>:<PORT_OF_ES>
|
142 |
```
|
|
|
144 |
|
145 |
### How to handle `{"data":null,"retcode":100,"retmsg":"<NotFound '404: Not Found'>"}`?
|
146 |
|
147 |
+
Your IP address or port number may be incorrect. If you are using the default configurations, enter http://<IP_OF_YOUR_MACHINE> (**NOT `localhost`, NOT 9380, AND NO PORT NUMBER REQUIRED!**) in your browser. This should work.
|
148 |
|
149 |
|
150 |
|