Replies: 1 comment 4 replies
-
|
Hello @samchouse! I'm here to help you with any bugs, questions, or contributions you have. Let's dive in and solve this issue together! To pass the user ID in a runnable for usage tracking when using LiteLLM, you can include the user ID in the await someRunnable.invoke(someInput, {
runName: "myRun",
tags: ["tag1", "tag2"],
metadata: {
userId: "your_user_id_here",
key: "value"
},
// ...
});Make sure to replace To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other |
Beta Was this translation helpful? Give feedback.
-
|
@dosu that didn't work, I'm also invoking through langgraph if that makes a difference but I thought config should be shared to the Runnable? |
Beta Was this translation helpful? Give feedback.
-
|
To pass the user ID in a Runnable for usage tracking when invoking through LangGraph, you should indeed be able to include it in the await someRunnable.invoke(someInput, {
metadata: { userId: "yourUserId" },
});This approach ensures that the user ID is included in the metadata for the Runnable invocation, allowing you to track usage associated with that specific user [1]. If this isn't working as expected, please ensure that the metadata is correctly propagated and that there are no overrides or issues in the configuration setup. To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other |
Beta Was this translation helpful? Give feedback.
-
|
@dosu it doesn't work: |
Beta Was this translation helpful? Give feedback.
-
|
To ensure that the user ID is correctly passed and recognized in the metadata when invoking a Runnable through LangGraph, you should use context variables. Here's how you can do it:
Here's a code example demonstrating this approach: import { setContextVariable } from "@langchain/core/context";
import { getContextVariable } from "@langchain/core/context";
import { tool } from "@langchain/core/tools";
import { BaseChatModel } from "@langchain/core/language_models/chat_models";
import { RunnableLambda } from "@langchain/core/runnables";
import { z } from "zod";
let userToPets: Record<string, string[]> = {};
const updateFavoritePets = tool(async (input) => {
const userId = getContextVariable("userId");
if (userId === undefined) {
throw new Error(`No "userId" found in current context. Remember to call "setContextVariable('userId', value)";`);
}
userToPets[userId] = input.pets;
return "update_favorite_pets called.";
}, {
name: "update_favorite_pets",
description: "add to the list of favorite pets.",
schema: z.object({
pets: z.array(z.string())
}),
});
const handleRunTimeRequestRunnable = RunnableLambda.from(async (params: {
userId: string;
query: string;
llm: BaseChatModel;
}) => {
const { userId, query, llm } = params;
if (!llm.bindTools) {
throw new Error("Language model does not support tools.");
}
setContextVariable("userId", userId);
const tools = [updateFavoritePets];
const llmWithTools = llm.bindTools(tools);
const modelResponse = await llmWithTools.invoke(query);
if (modelResponse.tool_calls.length > 0) {
return updateFavoritePets.invoke(modelResponse.tool_calls[0]);
} else {
return "No tool invoked.";
}
});
// Example invocation
await handleRunTimeRequestRunnable.invoke({
userId: "brace",
query: "my favorite animals are cats and parrots.",
llm: llm
});
console.log(userToPets);This code sets the To continue talking to Dosu, mention @dosu. Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other |
Beta Was this translation helpful? Give feedback.
-
Checked other resources
Commit to Help
Example Code
Description
I'm trying to call a a runnable and pass the user ID like I would usually in an OpenAI SDK call for usage tracking. I'm tracking through LiteLLM. How do I do that in a runnable?
System Info
{ "@langchain/anthropic": "^0.3.12", "@langchain/aws": "^0.1.3", "@langchain/community": "^0.3.27", "@langchain/core": "^0.3.37", "@langchain/deepseek": "^0.0.1", "@langchain/google-genai": "^0.1.7", "@langchain/google-vertexai": "^0.1.8", "@langchain/langgraph": "^0.2.41", "@langchain/mistralai": "^0.0.26", "@langchain/ollama": "^0.1.5", "@langchain/openai": "^0.4.2", }Beta Was this translation helpful? Give feedback.
All reactions