View Notebook on Github

AgentOps Langchain Agent Implementation

Using AgentOps monitoring with Langchain is simple. We’ve created a LangchainCallbackHandler that will do all of the heavy lifting!

First let’s install the required packages

%pip install langchain==0.2.9
%pip install langchain_openai
%pip install -U agentops
%pip install -U python-dotenv

Then import them

import os
from langchain_openai import ChatOpenAI
from langchain.agents import tool, AgentExecutor, create_openai_tools_agent
from dotenv import load_dotenv
from langchain_core.prompts import ChatPromptTemplate

The only difference with using AgentOps is that we’ll also import this special Callback Handler

from agentops.partners.langchain_callback_handler import (
    LangchainCallbackHandler as AgentOpsLangchainCallbackHandler,
)

Next, we’ll set our API keys. There are several ways to do this, the code below is just the most foolproof way for the purposes of this notebook. It accounts for both users who use environment variables and those who just want to set the API Key here in this notebook.

Get an AgentOps API key

  1. Create an environment variable in a .env file or other method. By default, the AgentOps init() function will look for an environment variable named AGENTOPS_API_KEY. Or…

  2. Replace <your_agentops_key> below and pass in the optional api_key parameter to the AgentOps init(api_key=...) function. Remember not to commit your API key to a public repo!

load_dotenv()
AGENTOPS_API_KEY = os.environ.get("AGENTOPS_API_KEY")
OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")

This is where AgentOps comes into play. Before creating our LLM instance via Langchain, first we’ll create an instance of the AO LangchainCallbackHandler. After the handler is initialized, a session will be recorded automatically.

Pass in your API key, and optionally any tags to describe this session for easier lookup in the AO dashboard.

agentops_handler = AgentOpsLangchainCallbackHandler(
    api_key=AGENTOPS_API_KEY, default_tags=["Langchain Example"]
)

llm = ChatOpenAI(
    openai_api_key=OPENAI_API_KEY, callbacks=[agentops_handler], model="gpt-3.5-turbo"
)

# You must pass in a callback handler to record your agent
llm.callbacks = [agentops_handler]

prompt = ChatPromptTemplate.from_messages(
    [
        ("system", "You are a helpful assistant. Respond only in Spanish."),
        ("human", "{input}"),
        # Placeholders fill up a **list** of messages
        ("placeholder", "{agent_scratchpad}"),
        # ("tool_names", "find_movie")
    ]
)

You can also retrieve the session_id of the newly created session.

print("Agent Ops session ID: " + str(agentops_handler.current_session_ids))

Agents generally use tools. Let’s define a simple tool here. Tool usage is also recorded.

@tool
def find_movie(genre: str) -> str:
    """Find available movies"""
    if genre == "drama":
        return "Dune 2"
    else:
        return "Pineapple Express"


tools = [find_movie]

For each tool, you need to also add the callback handler

for t in tools:
    t.callbacks = [agentops_handler]

Add the tools to our LLM

llm_with_tools = llm.bind_tools([find_movie])

Finally, let’s create our agent! Pass in the callback handler to the agent, and all the actions will be recorded in the AO Dashboard

agent = create_openai_tools_agent(llm, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools)
agent_executor.invoke(
    {"input": "What comedies are playing?"}, config={"callback": [agentops_handler]}
)

Check your session

Finally, check your run on AgentOps

Now if we look in the AgentOps dashboard, you will see a session recorded with the LLM calls and tool usage.

Langchain v0 Example

This langchain version is out of date and support is being deprecated. You can find the example notebook here.