RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
docs: Add a Tongyi-Qianwen Base URL reminder to the upgrade guide. (#21166)
YanZhangfada812ff460
diff --git a/docs/administrator/migration/upgrade_from_v0_to_v1.md b/docs/administrator/migration/upgrade_from_v0_to_v1.mdindex e69a5e5b96..763f042ce9 100644--- a/docs/administrator/migration/upgrade_from_v0_to_v1.md+++ b/docs/administrator/migration/upgrade_from_v0_to_v1.md@@ -210,6 +210,8 @@ First verify that `v1.0.0-rc1` started successfully and that its migration complSign in to RAGFlow and confirm that existing data and configuration are present, then test document retrieval, a new document upload, one Chat, and one Agent run.+If you used **Tongyi-Qianwen** in the v0.x deployment, go to **User settings** **>** **Model providers** and edit the Tongyi-Qianwen instance. Reselect the **Base URL** for your region and save the instance again before verifying the models. For the China region, replace `https://dashscope.aliyuncs.com/compatible-mode/v1` with `https://dashscope.aliyuncs.com`.+If the Python deployment used Tag datasets, confirm that they are no longer treated as datasets, reconfigure their tag files in the Go backend, and verify tag extraction on a representative document.Keep the `v0.27.2` backup until the upgraded deployment has completed acceptance testing and operated successfully under normal workload.