AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-12 17:29:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

0509 faq (#693)

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

Editorial updates only. 

### Type of change

- [x] Documentation Update
This commit is contained in:
writinwaters 2024-05-09 12:37:45 +08:00 committed by GitHub
parent 4153a36683
commit 9392b8bc8f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 10 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -58,12 +58,12 @@
## 📌 Latest Features
- 2024-05-08 Integrates LLM DeepSeek.
- 2024-05-08 Integrates LLM DeepSeek-V2.
- 2024-04-26 Adds file management.
- 2024-04-19 Supports conversation API ([detail](./docs/conversation_api.md)).
- 2024-04-16 Integrates an embedding model 'bce-embedding-base_v1' from [BCEmbedding](https://github.com/netease-youdao/BCEmbedding), and [FastEmbed](https://github.com/qdrant/fastembed), which is designed specifically for light and speedy embedding.
- 2024-04-11 Supports [Xinference](./docs/xinference.md) for local LLM deployment.
- 2024-04-10 Adds a new layout recognition model for analyzing Laws documentation.
- 2024-04-10 Adds a new layout recognition model for analyzing legal documents.
- 2024-04-08 Supports [Ollama](./docs/ollama.md) for local LLM deployment.
- 2024-04-07 Supports Chinese UI.

15
docs/faq.md
View File

@ -367,11 +367,11 @@ You can use Ollama to deploy local LLM. See [here](https://github.com/infiniflow
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.
### 7 Do I need to connect to Redis?
### 7. Do I need to connect to Redis?
No, connecting to Redis is not required.
### 8 `Error: Range of input length should be [1, 30000]`
### 8. `Error: Range of input length should be [1, 30000]`
This error occurs because there are too many chunks matching your search criteria. Try reducing the **TopN** and increasing **Similarity threshold** to fix this issue:
@ -382,14 +382,15 @@ This error occurs because there are too many chunks matching your search criteri
![topn](https://github.com/infiniflow/ragflow/assets/93570324/7ec72ab3-0dd2-4cff-af44-e2663b67b2fc)
### 9 How to upgrade RAGFlow?
### 9. How to upgrade RAGFlow?
You can upgrade RAGFlow to either the dev version or the latest version
You can upgrade RAGFlow to either the dev version or the latest version:
- Dev versions are for developers and contributors. They are published on a nightly basis and may crash because they are not fully tested. We cannot guarantee their validity and you are at your own risk trying out latest, untested features.
- The latest version is stable and reliable, and works best with RAGFlow users.
- The latest version refers to the most recent, officially published release. It is stable and works best with regular users.
Update RAGFlow to dev version:
To upgrade RAGFlow to the dev version:
1. Pull the latest source code
```bash
@ -411,7 +412,7 @@ This error occurs because there are too many chunks matching your search criteri
docker compose -f docker-compose-CN.yml up -d
```
To upgrade RAGFlow to latest version:
To upgrade RAGFlow to the latest version:
1. Update **ragflow/docker/.env** as follows:
```bash