Logging

Learn about using the Galileo LangChain and LangGraph logging integration to log agent traces

The Galileo LangChain integration allows you to automatically log all LangChain and LangGraph interactions with LLMs, including prompts, responses, and performance metrics. The Galileo SDK has a custom callback that is passed to LangChain or LangGraph.

GalileoCallback - Python

The Python Galileo Synchronous LangChain SDK reference.

GalileoAsyncCallback - Python

The Python Galileo Asynchronous LangChain SDK reference.

GalileoCallback - TypeScript

The TypeScript Galileo LangChain SDK reference.

Basic usage

The integration is based on the GalileoCallback class, which implements LangChain’s callback interface. To use it, create an instance of the callback and pass it to your LangChain components:

Python

from galileo.handlers.langchain import GalileoCallback
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage

# Create a callback handler
callback = GalileoCallback()

# Initialize the LLM with the callback
llm = ChatOpenAI(model="gpt-4o", temperature=0.7, callbacks=[callback])

# Create a message with the user's query
messages = [
    HumanMessage(content="What is LangChain and how is it used with OpenAI?")
]

# Make the API call
response = llm.invoke(messages)

print(response.content)

The GalileoCallback captures various LangChain events, including:

• LLM starts and completions
• Chat model interactions
• Chain executions
• Tool calls
• Retriever operations
• Agent actions

For each of these events, the callback logs relevant information to Galileo, such as:

• Input prompts and messages
• Output responses
• Model information
• Timing data
• Token usage
• Error information (if any)

The GalileoCallback automatically handles nested chains and agents, creating a hierarchical trace that reflects the structure of your LangChain application.

Python asynchronous callbacks

In Python, there are separate callbacks for synchronous and asynchronous code. If you are using the asynchronous LangChain or LangGraph API, use the GalileoAsyncCallback callback handler.

Python

import asyncio
from galileo.handlers.langchain import GalileoAsyncCallback
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage

# Create a callback handler
callback = GalileoAsyncCallback()

# Initialize the LLM with the callback
llm = ChatOpenAI(model="gpt-4o", temperature=0.7, callbacks=[callback])

# Create a message with the user's query
messages = [
    HumanMessage(content="What is LangChain and how is it used with OpenAI?")
]

async def main():
    # Make the API call
    response = await llm.ainvoke(messages)
    print(response.content)

asyncio.run(main())

Use a custom logger

When initializing the GalileoCallback, you can optionally specify a Galileo logger instance, either by creating a new logger, or by using the current logger from the Galileo context:

Python

from galileo import GalileoLogger
from galileo.handlers.langchain import GalileoCallback

# Create a custom logger
logger = GalileoLogger(project="my-project", log_stream="my-log-stream")

# Create a callback with the custom logger
callback = GalileoCallback(
    galileo_logger=logger,  # Optional custom logger
    start_new_trace=True,   # Whether to start a new trace for each chain
    flush_on_chain_end=True # Whether to flush traces when chains end
)

This is particularly useful if you want to call your LangChain code from inside a function decorated with the log decorator, or from inside an experiment.

Session and trace support

Every time you invoke a chain or an LLM call, a new session and trace is created. If you want to manually manage sessions or traces, you can do this using by passing a Galileo logger instance to the callback.

To add the chain or LLM call invocation as a new trace to an existing session, create the session first using the logger instance that was used to create the callback:

Python

from galileo import GalileoLogger
from galileo.handlers.langchain import GalileoCallback

# Create a custom logger
logger = GalileoLogger(project="my-project", log_stream="my-log-stream")

# Create a callback with the custom logger
callback = GalileoCallback(
    galileo_logger=logger
)

# Create a new session
logger.start_session(name="My new session")

To add the chain or LLM call invocation to an existing trace, ensure the trace is started, and set the start_new_trace parameter to False.

Python

from galileo import GalileoLogger
from galileo.handlers.langchain import GalileoCallback

# Create a custom logger
logger = GalileoLogger(project="my-project", log_stream="my-log-stream")

# Create a callback with the custom logger
callback = GalileoCallback(
    galileo_logger=logger,
    start_new_trace=False
)

# Create a new session
logger.start_session(name="My new session")

# Add a trace and a span
logger.start_trace("My trace")
logger.add_workflow_span("Crew workflow")

Use with LangChain chains

You can also use the callback with LangChain chains. Make sure to pass the callback to both the LLM and the chain.

Python

from galileo.handlers.langchain import GalileoAsyncCallback
from langchain_openai import ChatOpenAI
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables.config import RunnableConfig

# Create a callback handler
callback = GalileoAsyncCallback()

# Create the model
llm = ChatOpenAI(model="gpt-4o", temperature=0.7, callbacks=[callback])

# Create a prompt template
prompt = ChatPromptTemplate.from_template("Tell me a joke about {topic}")

# Assemble the chain with the prompt, LLM, and output parser
chain = prompt | llm | StrOutputParser()

# Create a configuration for the runnable
# that includes the callback handler
config = RunnableConfig(
    callbacks=[callback]
)

# Invoke the chain with a topic and configuration
response = chain.invoke({"topic": "the Roman Empire"},
                        config=config)
print(response)

Add metadata

You can add custom metadata and tags to your logs by including them in the metadata and tags parameters of a LangChain runnable configuration when invoking a chain or LLM.

Python

# Create a configuration for the runnable
# that includes the callback handler and metadata
config = RunnableConfig(
    callbacks=[callback],
    metadata={
        "user_id": "user-123",
        "session_id": "session-456",
        "custom_field": "custom value",
    },
    tags=["my-tag"],
)

# Invoke the chain with a topic and configuration
response = chain.invoke({"topic": "the Roman Empire"}, config=config)

This metadata will be attached to the logs in Galileo, making it easier to filter and analyze your data.

Best practices

1. Pass callbacks consistently: Make sure to pass the callback to all LangChain components (LLMs, chains, agents, etc.) to ensure complete logging.
2. Include meaningful metadata: Add relevant metadata to your invocations to make it easier to filter and analyze your logs.

Next steps

Basic logging components

Galileo logger

Log with full control over sessions, traces, and spans using the Galileo logger.

Log decorator

Quickly add logging to your code with the log decorator and wrapper.

Galileo context

Manage logging using the Galileo context manager.

Cookbooks

Monitor LangChain Agents with Galileo

Learn how to build and monitor a LangChain AI Agent using Galileo for tracing and observability.

Add evaluations to a multi-agent LangGraph application

Learn how to add evaluations to a multi-agent LangGraph chat bot using Galileo