Skip to content

LangChain Agent Example

Work in Progress

This page is currently under development.

Overview

This example demonstrates how to deploy a LangChain agent using AgentCore CLI. LangChain is a popular framework for building applications with large language models (LLMs).

Prerequisites

Before starting this example, ensure you have:

  • Completed the installation steps
  • Initialized your project using agentcore-cli init
  • Basic understanding of LangChain

Project Structure

Create the following files:

Dockerfile

Docker
 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
FROM python:3.11-slim

WORKDIR /app

# Install dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy agent code
COPY app.py .

# Run the agent
CMD ["python", "app.py"]

requirements.txt

Text Only
1
2
3
4
5
6
7
langchain>=0.0.267
langchain-community>=0.0.10
langchain-core>=0.1.4
boto3>=1.28.0
fastapi>=0.104.1
uvicorn>=0.24.0
pydantic>=2.4.2

app.py

Python
1
# Example LangChain agent code will be added in a future update

Step 1: Build and Deploy

Deploy your LangChain agent:

Bash
1
agentcore-cli agent create langchain-agent --dockerfile ./Dockerfile

Step 2: Invoke the Agent

Invoke your deployed agent:

Bash
1
agentcore-cli agent invoke langchain-agent --prompt "What is the capital of France?"

LangChain Agent Features

The LangChain agent in this example includes:

  • Chain of Thought Reasoning: Solving problems step-by-step
  • Tool Usage: Accessing external tools when needed
  • Memory: Maintaining conversation context
  • Structured Output: Returning consistent response formats

Advanced Configuration

Advanced LangChain configuration options will be added in a future update.

Best Practices

Guidelines for deploying LangChain agents will be added in a future update.

Additional Resources