Skip to main content

OpenTelemetry instrumentation for Langchain

Project description

LangChain OpenTelemetry Integration

Overview

This integration provides support for using OpenTelemetry with the LangChain framework. It enables tracing and monitoring of applications built with LangChain.

Installation

  1. Install traceAI LangChain
pip install traceAI-langchain
  1. Install LangChain OpenAI
pip install langchain-openai

Set Environment Variables

Set up your environment variables to authenticate with FutureAGI.

import os

os.environ["FI_API_KEY"] = FI_API_KEY
os.environ["FI_SECRET_KEY"] = FI_SECRET_KEY
os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY

Quickstart

Register Tracer Provider

Set up the trace provider to establish the observability pipeline. The trace provider:

from fi_instrumentation import register
from fi_instrumentation.fi_types import ProjectType

trace_provider = register(
    project_type=ProjectType.OBSERVE,
    project_name="langchain_app",
    project_version_name="v1",  
    session_name="chat-bot"
)

Configure LangChain Instrumentation

Instrument the LangChain client to enable telemetry collection. This step ensures that all interactions with the LangChain SDK are tracked and monitored.

from traceai_langchain import LangChainInstrumentor

LangChainInstrumentor().instrument(tracer_provider=trace_provider)

Create LangChain Components

Set up your LangChain client with built-in observability.

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_template("{x} {y} {z}?").partial(x="why is", z="blue")
chain = prompt | ChatOpenAI(model_name="gpt-3.5-turbo")

def run_chain():
    try:
        result = chain.invoke({"y": "sky"})
        print(f"Response: {result}")
    except Exception as e:
        print(f"Error executing chain: {e}")

if __name__ == "__main__":
    run_chain()

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

traceai_langchain-0.1.9.tar.gz (13.3 kB view details)

Uploaded Source

Built Distribution

traceai_langchain-0.1.9-py3-none-any.whl (14.0 kB view details)

Uploaded Python 3

File details

Details for the file traceai_langchain-0.1.9.tar.gz.

File metadata

  • Download URL: traceai_langchain-0.1.9.tar.gz
  • Upload date:
  • Size: 13.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.0.0 CPython/3.13.0 Darwin/24.1.0

File hashes

Hashes for traceai_langchain-0.1.9.tar.gz
Algorithm Hash digest
SHA256 3d012c294e95b5d72f3ec7b18cce493d0b90275783af9152a44f0bd77a09b701
MD5 34075de4578c4329bf920b45ed42f988
BLAKE2b-256 3e42f7c1b5eaa236b5787c8d9375e36fb4769ef497459e75a888d982dcceebb1

See more details on using hashes here.

File details

Details for the file traceai_langchain-0.1.9-py3-none-any.whl.

File metadata

  • Download URL: traceai_langchain-0.1.9-py3-none-any.whl
  • Upload date:
  • Size: 14.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.0.0 CPython/3.13.0 Darwin/24.1.0

File hashes

Hashes for traceai_langchain-0.1.9-py3-none-any.whl
Algorithm Hash digest
SHA256 a8cb7c3ca3b9729fd382975f722bacbb10ebaa1519c55664b95aa7ae90807320
MD5 9a528cb5a9501a9673b632bfbdbbb4f6
BLAKE2b-256 da9a76f15e2ede882a80f5a707eea373a52604d2b5e3ef5074b39927d61a908a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page