zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-07-23 08:56:42 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: eliminate one-frame flash of title without form content in data source pages (#17214)

Browse Source
This commit is contained in:
euvre
2026-07-22 19:06:38 +08:00
committed by GitHub
parent 32ddf59ac6
commit a40d5f841b
6 changed files with 208 additions and 218 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/guides/memory/use_memory.md
View File

@@ -50,7 +50,7 @@ What is stored in the memory:
### Memory size
The default capacity allocated to the memory and the corresponding embeddings in bytes. Defaults to `5242880` (5MB).
The default capacity allocated to the memory and the corresponding embeddings in bytes. Defaults to `5242880` (5MB).
:::tip NOTE
A 1KB message with a 1024-dimension embedding occupies approximately 9KB of memory (1KB + 1024 x 8Bytes = 9KB). With a default limit of 5 MB, the system can store roughly 500 such messages.
@@ -74,7 +74,7 @@ Manually forgotten memory entries are completely excluded from the results retur
When the Memory reaches its storage limit and the automatic forgetting policy is applied, entries that were previously forgotten manually are also prioritized for removal. This allows the system to reclaim capacity more intelligently while respecting earlier user curation decisions.
## Enhance Agent context
## Enhance Agent context
Under [Retrieval](../agent/agent_component_reference/retrieval.mdx) and [Message](../agent/agent_component_reference/message.md) component settings, a new Memory invocation capability is available. In the Message component, users can configure the Agent to write selected data into a designated Memory, while the Retrieval component can be set to read from that same Memory to answer future queries. This enables a simple Q&A bot Agent to accumulate context over time and respond with richer, memory-aware answers.