Refactor DeerFlow to use Gateway's LangGraph-compatible API
- Updated documentation and comments to reflect the transition from LangGraph Server to Gateway. - Changed default URLs in ChannelManager and tests to point to Gateway. - Removed references to LangGraph Server in deployment scripts and configurations. - Updated Nginx configuration to route API traffic to Gateway. - Adjusted frontend configurations to utilize Gateway's API. - Removed LangGraph service from Docker Compose files, consolidating services under Gateway. - Added regression tests to ensure Gateway integration works as expected. Co-authored-by: Copilot <copilot@github.com>
This commit is contained in:
@@ -2,7 +2,7 @@
|
||||
|
||||
Provides a pluggable channel system that connects external messaging platforms
|
||||
(Feishu/Lark, Slack, Telegram) to the DeerFlow agent via the ChannelManager,
|
||||
which uses ``langgraph-sdk`` to communicate with the underlying LangGraph Server.
|
||||
which uses ``langgraph-sdk`` to communicate with Gateway's LangGraph-compatible API.
|
||||
"""
|
||||
|
||||
from app.channels.base import Channel
|
||||
|
||||
Reference in New Issue
Block a user