WIP: Example: Human in the loop over the network #58
Conversation
|
@albertpurnama is attempting to deploy a commit to the LangChain Team on Vercel. A member of the Team first needs to authorize it. |
| // Get the agent state, check whether the agent can be resumed. | ||
| const state = await agent.getState({ | ||
| configurable: { thread_id: threadId }, | ||
| }); | ||
|
|
||
| const isBeginning = | ||
| state.next.length === 0 && Object.keys(state.values).length === 0; | ||
|
|
||
| let runInput: { messages: (AIMessage | HumanMessage)[] } | Command = | ||
| new Command({ | ||
| resume: messages.findLast((m: any) => m.role === "user")?.content, | ||
| update: { | ||
| isResuming: true, // Important if you have workflows that you want to ignore when resuming | ||
| }, | ||
| }); | ||
|
|
||
| if (isBeginning) { | ||
| runInput = { | ||
| messages, | ||
| }; | ||
| } |
There was a problem hiding this comment.
there's gotta be a simpler way to do this, I simply want to check whether the current state is resumable or not, or whether it is in its end node?
I'm hoping for something like state.currentNode to get the string name of the node, if it is __end__ then I know it's not resumable. something like this exist?
There was a problem hiding this comment.
Wouldn't it just be if state.next were populated?
| @@ -0,0 +1,88 @@ | |||
| import { ChatWindow } from "@/components/ChatWindow"; | |||
There was a problem hiding this comment.
these are copied over from agents/page.tsx
| // isResuming is very useful if you want to ignore some workflow in some node | ||
| // that you want to ignore when the graph is resuming the run for the first time | ||
| // after interrupt happened | ||
| isResuming: Annotation<boolean>({ |
There was a problem hiding this comment.
If you are just want to override the last value in the state, you can just do:
isResuming: Annotation<boolean>,
...
| "calculatorAgent helps with calculations" + | ||
| "mainAgent is the main agent that handles the user's message", | ||
| ), | ||
| response: z.string().describe("Human readable response to user's message"), |
There was a problem hiding this comment.
Small potential optimization: put response first. The LLM will generate it before generating a goto value and it can help steer it to better decisions.
| const { gotoNext } = state; | ||
|
|
||
| // we're not using the object here. we ask for string feedback. | ||
| const input = await interrupt<{}, string>({}); |
There was a problem hiding this comment.
Any reason for the type params?
| }; | ||
|
|
||
| const convertLangChainMessageToVercelMessage = (message: BaseMessage) => { | ||
| if (message._getType() === "human") { |
There was a problem hiding this comment.
You can use .getType() now
| "@langchain/langgraph": "^0.2.20", | ||
| "@langchain/core": "^0.3.27", | ||
| "@langchain/langgraph": "^0.2.39", | ||
| "@langchain/langgraph-checkpoint-postgres": "^0.0.2", |
There was a problem hiding this comment.
Small nit - should we make this a peer dep?
This PR adds an example page for human in the loop process over the network
There's a couple of package updates that is required for
interruptto run one of them is@langchain/core.TODOs: