Skip to content

RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.

doc: udpate readme (#20347)

Jin Hai3da23a413b06
diff --git a/docs/release_notes.md b/docs/release_notes.md
index 87cc5872be..8e324f21b5 100644
--- a/docs/release_notes.md
+++ b/docs/release_notes.md
@@ -11,31 +11,29 @@ Key features, improvements and bug fixes in the latest releases.
## v1.0.0-rc1
-RAGFlow v1.0.0-rc1 is a preview release of v1.0.0. In this release, RAGFlow has been comprehensively rewritten in Go, significantly reducing system resource consumption and replacing the previously heavyweight deployment model with a lightweight one.
+RAGFlow v1.0.0-rc1 is a preview release of v1.0.0. This release marks a comprehensive rewrite of RAGFlow in Go, delivering a substantial reduction in system resource consumption and replacing the previous heavyweight deployment model with a lightweight architecture.
### Architecture changes
- **Message queue:** Migrated from Redis to NATS.
-- **Cache and checkpoints:** Kvrocks is now used for cache and checkpoint storage.
+- **Cache and checkpoints:** Kvrocks now serves as the backing store for both cache and checkpoints.
### Data upgrade
-When the RAGFlow containers start, the data upgrade process runs automatically to upgrade RAGFlow data from v0.27.2 to v1.0.0-rc1. **Once the upgrade is complete, the data cannot be rolled back to v0.27.2.**
-
+Upon container startup, RAGFlow automatically initiates the data upgrade process, migrating existing data from v0.27.2 to v1.0.0-rc1. Note that this upgrade is irreversible — once completed, data cannot be rolled back to v0.27.2.
### Upgrade prerequisites and precautions
-1. Back up your data before upgrading.
-2. Upgrade your existing deployment to v0.27.2 first.
-3. If the upgrade fails, restore the original system from your backup and submit an issue describing the problem you encountered.
+1. Back up all data prior to upgrading.
+2. Ensure your existing deployment is already on v0.27.2 before proceeding.
+3. Should the upgrade fail, restore your system from the backup and submit an issue detailing the failure.
### Compatibility
-1. **RAGFlow CLI:** Reimplemented in Go, replacing the Python version.
+1. **RAGFlow CLI:** Reimplemented in Go, replacing the previous Python version.
2. **API compatibility:** [Deprecated APIs](https://ragflow.io/docs/http_api_reference#removed-api-aliases) are no longer supported by the Go implementation.
-3. **SDK compatibility:** The Python SDK is unaffected.
+3. **SDK compatibility:** The Python SDK remains unaffected.
### Known issues
1. DeepDoc currently supports CPU environments only.
2. The local sandbox is no longer supported.
-3. GaussDB, PostgreSQL, OpenSearch, and other integrations are not yet supported.
-4. The **Team/Me** permission model is not yet supported.
+3. The **Team/Me** permission model is not yet supported.
## v0.27.2