mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-08-12 19:39:00 +08:00
Updated FAQ plus miscellaneous updates. (#364)
### What problem does this PR solve? ### Type of change - [x] Documentation Update
This commit is contained in:
parent
826ad6a33a
commit
ec76585777
@ -56,7 +56,7 @@
|
|||||||
## 📌 Latest Features
|
## 📌 Latest Features
|
||||||
|
|
||||||
- 2024-04-11 Support [Xinference](./docs/xinference.md) for local LLM deployment.
|
- 2024-04-11 Support [Xinference](./docs/xinference.md) for local LLM deployment.
|
||||||
- 2024-04-10 Add a new layout recognization model to the 'Laws' method.
|
- 2024-04-10 Add a new layout recognization model for analyzing Laws documentation.
|
||||||
- 2024-04-08 Support [Ollama](./docs/ollama.md) for local LLM deployment.
|
- 2024-04-08 Support [Ollama](./docs/ollama.md) for local LLM deployment.
|
||||||
- 2024-04-07 Support Chinese UI.
|
- 2024-04-07 Support Chinese UI.
|
||||||
|
|
||||||
|
14
README_ja.md
14
README_ja.md
@ -53,6 +53,13 @@
|
|||||||
- 複数の想起と融合された再ランク付け。
|
- 複数の想起と融合された再ランク付け。
|
||||||
- 直感的な API によってビジネスとの統合がシームレスに。
|
- 直感的な API によってビジネスとの統合がシームレスに。
|
||||||
|
|
||||||
|
## 📌 最新の機能
|
||||||
|
|
||||||
|
- 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。
|
||||||
|
- 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。
|
||||||
|
- 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。
|
||||||
|
- 2024-04-07 中国語インターフェースをサポートします。
|
||||||
|
|
||||||
## 🔎 システム構成
|
## 🔎 システム構成
|
||||||
|
|
||||||
<div align="center" style="margin-top:20px;margin-bottom:20px;">
|
<div align="center" style="margin-top:20px;margin-bottom:20px;">
|
||||||
@ -170,12 +177,9 @@ $ chmod +x ./entrypoint.sh
|
|||||||
$ docker compose up -d
|
$ docker compose up -d
|
||||||
```
|
```
|
||||||
|
|
||||||
## 🆕 最新の新機能
|
## 📚 ドキュメンテーション
|
||||||
|
|
||||||
- 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。
|
- [FAQ](./docs/faq.md)
|
||||||
- 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。
|
|
||||||
- 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。
|
|
||||||
- 2024-04-07 中国語インターフェースをサポートします。
|
|
||||||
|
|
||||||
## 📜 ロードマップ
|
## 📜 ロードマップ
|
||||||
|
|
||||||
|
14
README_zh.md
14
README_zh.md
@ -53,6 +53,13 @@
|
|||||||
- 基于多路召回、融合重排序。
|
- 基于多路召回、融合重排序。
|
||||||
- 提供易用的 API,可以轻松集成到各类企业系统。
|
- 提供易用的 API,可以轻松集成到各类企业系统。
|
||||||
|
|
||||||
|
## 📌 新增功能
|
||||||
|
|
||||||
|
- 2024-04-11 支持用 [Xinference](./docs/xinference.md) 本地化部署大模型。
|
||||||
|
- 2024-04-10 为‘Laws’版面分析增加了底层模型。
|
||||||
|
- 2024-04-08 支持用 [Ollama](./docs/ollama.md) 本地化部署大模型。
|
||||||
|
- 2024-04-07 支持中文界面。
|
||||||
|
|
||||||
## 🔎 系统架构
|
## 🔎 系统架构
|
||||||
|
|
||||||
<div align="center" style="margin-top:20px;margin-bottom:20px;">
|
<div align="center" style="margin-top:20px;margin-bottom:20px;">
|
||||||
@ -170,12 +177,9 @@ $ chmod +x ./entrypoint.sh
|
|||||||
$ docker compose up -d
|
$ docker compose up -d
|
||||||
```
|
```
|
||||||
|
|
||||||
## 🆕 最近新特性
|
## 📚 技术文档
|
||||||
|
|
||||||
- 2024-04-11 支持用 [Xinference](./docs/xinference.md) for local LLM deployment.
|
- [FAQ](./docs/faq.md)
|
||||||
- 2024-04-10 为‘Laws’版面分析增加了模型。
|
|
||||||
- 2024-04-08 支持用 [Ollama](./docs/ollama.md) 对大模型进行本地化部署。
|
|
||||||
- 2024-04-07 支持中文界面。
|
|
||||||
|
|
||||||
## 📜 路线图
|
## 📜 路线图
|
||||||
|
|
||||||
|
18
docs/faq.md
18
docs/faq.md
@ -45,14 +45,14 @@ This feature and the related APIs are still in development. Contributions are we
|
|||||||
|
|
||||||
### How to increase the length of RAGFlow responses?
|
### How to increase the length of RAGFlow responses?
|
||||||
|
|
||||||
Adjust the **Max Tokens** slider in **Model Setting**:
|
1. Right click the desired dialog to display the **Chat Configuration** window.
|
||||||
|
2. Switch to the **Model Setting** tab and adjust the **Max Tokens** slider to get the desired length.
|
||||||

|
3. Click **OK** to confirm your change.
|
||||||
|
|
||||||
|
|
||||||
### What does Empty response mean? How to set it?
|
### What does Empty response mean? How to set it?
|
||||||
|
|
||||||
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.
|
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.
|
||||||
|
|
||||||
### Can I set the base URL for OpenAI somewhere?
|
### Can I set the base URL for OpenAI somewhere?
|
||||||
|
|
||||||
@ -70,9 +70,9 @@ You can use Ollama to deploy local LLM. See [here](https://github.com/infiniflow
|
|||||||
|
|
||||||
### How to configure RAGFlow to respond with 100% matched results, rather than utilizing LLM?
|
### How to configure RAGFlow to respond with 100% matched results, rather than utilizing LLM?
|
||||||
|
|
||||||
In Configuration, choose **Q&A** as the chunk method:
|
1. Click the **Knowledge Base** tab in the middle top of the page.
|
||||||
|
2. Right click the desired knowledge base to display the **Configuration** dialogue.
|
||||||

|
3. Choose **Q&A** as the chunk method and click **Save** to confirm your change.
|
||||||
|
|
||||||
## Debugging
|
## Debugging
|
||||||
|
|
||||||
@ -136,7 +136,7 @@ $ docker ps
|
|||||||
es:
|
es:
|
||||||
hosts: 'http://es01:9200'
|
hosts: 'http://es01:9200'
|
||||||
```
|
```
|
||||||
- - If you run RAGFlow outside of Docker, verify the ES host setting in **conf/service_conf.yml** using:
|
- If you run RAGFlow outside of Docker, verify the ES host setting in **conf/service_conf.yml** using:
|
||||||
```bash
|
```bash
|
||||||
curl http://<IP_OF_ES>:<PORT_OF_ES>
|
curl http://<IP_OF_ES>:<PORT_OF_ES>
|
||||||
```
|
```
|
||||||
@ -144,7 +144,7 @@ $ docker ps
|
|||||||
|
|
||||||
### How to handle `{"data":null,"retcode":100,"retmsg":"<NotFound '404: Not Found'>"}`?
|
### How to handle `{"data":null,"retcode":100,"retmsg":"<NotFound '404: Not Found'>"}`?
|
||||||
|
|
||||||
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.
|
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.
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
Loading…
x
Reference in New Issue
Block a user