OpenAIAssistantRunnable don't track on LangSmith

[ttessarolo]

Maybe because is still experimental but OpenAIAssistantRunnable don't seams to track on LangSmith.

[dosubot[bot]]

🤖

Hey there, @ttessarolo! Great to see you back around these parts. 👋 Hope you're doing well!

Based on the provided context, it seems that OpenAIAssistantRunnable is used to create, modify, delete, and invoke an assistant in the langchainjs codebase. This assistant can also be used as an agent and passed to the AgentExecutor class along with a set of tools for execution.

However, there is no direct interaction between OpenAIAssistantRunnable and LangSmith mentioned in the context. The OpenAIAssistantRunnable is used to create an assistant that can be used as an agent, and this agent is then passed to the AgentExecutor along with the tools for execution.

Here's a snippet of how it works:

const agent = await OpenAIAssistantRunnable.createAssistant({
  model: "gpt-3.5-turbo-1106",
  instructions: "You are a weather bot. Use the provided functions to answer questions.",
  name: "Weather Assistant",
  tools,
  asAgent: true,
});

const agentExecutor = AgentExecutor.fromAgentAndTools({
  agent,
  tools,
});

const assistantResponse = await agentExecutor.invoke({
  content: "What's the weather in San Francisco and Tokyo? And will it be warm or cold in those places?",
});

You can find this code in the langchain/src/experimental/openai_assistant/tests/openai_assistant.int.test.ts file.

If LangSmith is a specific feature or component within the langchainjs codebase, it would be helpful to have more information about its functionality and how you expect it to interact with OpenAIAssistantRunnable. This would help in providing a more accurate and helpful response.

Sources

• examples/src/agents/openai_runnable.ts
• langchain/src/experimental/openai_assistant/tests/openai_assistant.int.test.ts

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.