AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-08-10 19:18:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

v0.18.0 release notes (#7185)

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

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### Type of change

- [x] Documentation Update
This commit is contained in:
writinwaters 2025-04-23 10:41:58 +08:00 committed by GitHub
parent b44bbd11b8
commit 9a1ac8020d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 20 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/guides/dataset/enable_raptor.md
View File

@ -43,7 +43,7 @@ The system's default chat model is used to summarize clustered content. Before p
## Configurations
On the **Configuration** page of your knowledge base, the **Use RAPTOR to enhance retrieval** toggle is disabled by default.
The RAPTOR feature is disabled by default. To enable it, manually switch on the **Use RAPTOR to enhance retrieval** toggle on your knowledge base's **Configuration** page.
### Prompt
@ -71,4 +71,4 @@ The maximum number of clusters to create. Defaults to 108, with a maximum limit
### Random seed
A random seed. Click **+** button to change the seed value.
A random seed. Click the **+** button to change the seed value.

18
docs/release_notes.md
View File

@ -7,6 +7,24 @@ slug: /release_notes
Key features, improvements and bug fixes in the latest releases.
## v0.18.0
Released on April 22, 2025.
### New features
- MCP server: enables access to RAGFlow's knowledge bases via MCP.
- DeepDoc supports adopting VLM model as a processing pipeline during document layout recognition, enabling in-depth analysis of images in PDFs.
- Agent version control: all updates are continuously logged and can be rolled back to a previous version via export.
- Team collaboration: Agents can be shared with team members.
- OpenAI-compatible APIs: Agents can be called via OpenAI-compatible APIs.
- User registration control: administrators can enable or disable user registration through an environment variable.
### Improvements
- Enhanced answer referencing: Citation accuracy in generated responses is improved.
- Enhanced question-answering experience: users can now manually stop streaming output during a conversation.
## v0.17.2
Released on March 13, 2025.