LangChain Runnables

A collection of practical examples demonstrating LangChain's Runnable architecture for building modular, scalable, and production-ready LLM applications.

Overview

This repository explores the core Runnable components introduced in LangChain and demonstrates how they can be combined to create flexible AI workflows.

The examples focus on:

• Sequential execution pipelines
• Parallel task execution
• Conditional routing
• Custom business logic integration
• Data transformation workflows

These concepts form the foundation of modern LangChain application development and are widely used in production AI systems.

---

Concepts Covered

RunnableSequence

Execute multiple components in sequence.

Use Cases

• Multi-step reasoning
• Data processing pipelines
• Summarization workflows
• Content generation chains

---

RunnableParallel

Run multiple tasks simultaneously and collect their outputs.

Use Cases

• Parallel prompt execution
• Multi-analysis pipelines
• Performance optimization

---

RunnablePassthrough

Pass original inputs through the chain while augmenting them with additional outputs.

Use Cases

• Context preservation
• Metadata enrichment
• Intermediate result tracking

---

RunnableLambda

Integrate custom Python logic directly into LangChain workflows.

Use Cases

• Data preprocessing
• Output transformation
• Business rule implementation

---

RunnableBranch

Route requests dynamically based on conditions.

Use Cases

• Conditional workflows
• Input classification
• Intelligent routing systems

---

Project Structure

LangChain-Runnables/
│
├── runnable_sequence.py
├── runnable_parallel.py
├── runnable_passthrough.py
├── runnable_lambda.py
├── runnable_branch.py
│
├── .env
├── requirements.txt
└── README.md

---

Technologies Used

• Python
• LangChain
• Hugging Face Inference API
• Prompt Templates
• Output Parsers
• Runnable Architecture

---

Installation

Clone the repository:

git clone https://github.com/shivharebhupendra/LangChain-Runnables.git

Move into the project directory:

cd LangChain-Runnables

Create a virtual environment:

python -m venv venv

Activate the environment:

Windows

venv\Scripts\activate

Linux / macOS

source venv/bin/activate

Install dependencies:

pip install -r requirements.txt

---

Environment Variables

Create a .env file:

HUGGINGFACEHUB_API_TOKEN=your_token_here

---

Learning Outcomes

By working through these examples, you will learn how to:

• Build modular AI pipelines
• Chain multiple LLM operations together
• Execute tasks concurrently
• Implement conditional execution paths
• Add custom Python logic to workflows
• Design scalable LangChain applications

---

Future Enhancements

This repository will be continuously updated with additional Runnable patterns and real-world AI workflow implementations, including:

• Retrieval-Augmented Generation (RAG)
• Agent Workflows
• LangGraph Integration
• Memory Systems
• Tool Calling
• Production Deployment Examples

---

Author

Bhupendra Shivhare

AI Engineer | Data Analyst | Generative AI Educator

GitHub: https://github.com/shivharebhupendra

---

⭐ If you find this repository useful, consider giving it a star and following for future updates.