Parea AI works seamlessly with LangChain. LangChain provides a callbacks system to hook into the various stages of your LLM application. With Parea’s PareaAILangchainTracer you can automatically subscribe to all exposed LangChain events.


Add the PareaAILangchainTracer as a callback when running your Langchain model/chain/agent:

pip install parea-ai langchain

First initialize Parea and the PareaAILangchainTracer. Follow these steps to get an API key.

from parea import Parea
from parea.utils.trace_integrations.langchain import PareaAILangchainTracer

p = Parea(api_key="PAREA_API_KEY") # Replace with your Parea API key

handler = PareaAILangchainTracer()

Then initialize the tracer and add it as a callback to your LangChain application.

from langchain.chat_models import ChatOpenAI
from langchain.prompts import ChatPromptTemplate

chat_model = ChatOpenAI()
prompt = ChatPromptTemplate.from_messages([
  ("system", "You are a helpful AI."),
  ("human", "{input}")
chain = prompt | chat_model

  {"input": "What is the meaning of life?"},
  config={"callbacks": [handler]}

Where to set callbacks

There are two ways callbacks can be passed - as constructor callbacks and as request callbacks.

  • Constructor callbacks are defined in the constructor of an object and apply to all calls made on that specific object. The scope is limited to the object itself.
  • Request callbacks are defined in the run() or apply() methods used for sending a request. They are applied to a specific request and all sub-requests it contains. For example, passing a handler to the method will be used for that particular request and any subsequent sub-requests triggered. Additional details here.

Below are some examples of how to set callbacks in different scenarios.

from langchain.llms import OpenAI
from langchain.utilities import SQLDatabase
from langchain_experimental.sql import SQLDatabaseChain

db = SQLDatabase.from_uri("sqlite:///Chinook.db")
llm = OpenAI(temperature=0, verbose=True)
db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)
    "How many employees are there?",

Visualizing your traces

Every time you run a LangChain component with tracing, the call hierarchy for the run is saved and can be visualized in the app on the Logs tab. You can drill down into the components inputs and outputs, parameters, response time, token usage, and other important metadata.


Evaluating a Langchain RAG application

Below is an example of how to use the PareaAILangchainTracer and Langchain to evaluate a RAG chain. The code can be found in the cookbook here.

import os
from datetime import datetime
from operator import itemgetter
from dotenv import load_dotenv
from langchain.chat_models import ChatOpenAI
from langchain.document_loaders import RecursiveUrlLoader
from langchain.document_transformers import Html2TextTransformer
from langchain.embeddings import OpenAIEmbeddings
from langchain.prompts import ChatPromptTemplate
from langchain.schema.output_parser import StrOutputParser
from langchain.text_splitter import TokenTextSplitter
from langchain.vectorstores import Chroma
from parea import Parea
from parea.utils.trace_integrations.langchain import PareaAILangchainTracer
from parea.evals.general import answer_matches_target_llm_grader_factory
from parea.evals.rag import context_query_relevancy_factory, percent_target_supported_by_context_factory
from parea.evals import EvalFuncTuple, run_evals_in_thread_and_log
from parea.schemas import Log


# Need to instantiate Parea for tracing and evals
p = Parea(api_key=os.getenv("PAREA_API_KEY"))


def format_docs(docs) -> str:
    global CONTEXT  # Declare CONTEXT as a global variable
    context = "\n\n".join(doc.page_content for doc in docs)
    CONTEXT = context
    return context

raw_documents = RecursiveUrlLoader("").load()
transformed = Html2TextTransformer().transform_documents(raw_documents)
documents = TokenTextSplitter(model_name="gpt-3.5-turbo", chunk_size=2000, chunk_overlap=200).split_documents(transformed)
retriever = Chroma.from_documents(documents, OpenAIEmbeddings()).as_retriever()

prompt = ChatPromptTemplate.from_messages(
            "You are a helpful documentation Q&A assistant, trained to answer questions from the provided context."
            "\nThe current time is {time}.\n\nRelevant documents will be retrieved in the following messages.",
        ("system", "{context}"),
        ("human", "{question}"),

model = ChatOpenAI(model="gpt-3.5-turbo-16k", temperature=0)
response_generator = prompt | model | StrOutputParser()
chain = (
    # The runnable map here routes the original inputs to a context and a question dictionary to pass to the response generator
    {"context": itemgetter("question") | retriever | format_docs, "question": itemgetter("question")}
    | response_generator

# Get started with Parea's auto evaluation metrics for RAG
    EvalFuncTuple(name="matches_target", func=answer_matches_target_llm_grader_factory(question_field="question")),
    EvalFuncTuple(name="relevancy", func=context_query_relevancy_factory(question_field="question", context_fields=["context"])),
    EvalFuncTuple(name="supported_by_context", func=percent_target_supported_by_context_factory(question_field="question", context_fields=["context"])),

def main():
    handler = PareaAILangchainTracer()
    question = "What is the population of New York City as of 2020?"
    output = chain.invoke({"question": question}, config={"callbacks": [handler]})
    # get parent trace id from the tracer
    parent_trace_id = handler.get_parent_trace_id()
    # build log component needed for evaluation metric functions
    log = Log(inputs={"question": question, "context": CONTEXT}, output=output, target="8,804,190")
    # parea provided helper function to run evaluation metrics in a thread to avoid blocking
    run_evals_in_thread_and_log(trace_id=str(parent_trace_id), log=log, eval_funcs=EVALS, verbose=True)

# ###Eval Results###
# NamedEvaluationScore(name='matches_target', score=1.0)
# NamedEvaluationScore(name='relevancy', score=0.0053)
# NamedEvaluationScore(name='supported_by_context', score=1.0)
# View trace at:{parent_trace_id}

Tracing LangChain code together with other code

If you want to observe or test LangChain code and other code together, the trace decorator plays well with that and will associate any traces, LLM calls, and LangChain logs. You can see a schematic example below:
oai_client = OpenAI()

p = Parea(api_key=os.getenv("PAREA_API_KEY"))
handler = PareaAILangchainTracer()

chain = ...

def main():
    programming_language = ("gpt-3.5-turbo", messages=[{"role": "user", "content": "Suggest one programming languages"}]).choices[0].message.content

    return chain.invoke(
        {"input": f"Write a Hello World program in {programming_language}."},
        config={"callbacks": [handler]},

The full working example can be found below: