What Is LangChain?

LangChain is an open-source framework for building applications powered by large language models (LLMs).

It gives you standard building blocks — prompts, models, chains, memory, tools, and retrievers — so you do not rebuild the same plumbing for every AI app.

If you are building a chatbot, a RAG system, a document Q&A tool, or an AI agent, LangChain gives you the pieces to assemble it in Python (and JavaScript).

This tutorial walks you through building your first LangChain app in Python — from installation to a working RAG system.

For organisations building AI applications, Innovative AI Solutions provides AI development and generative AI services.

What You Will Build

By the end of this tutorial, you will have built:

All in Python, all runnable locally.

Prerequisites

Step 1: Install LangChain

Create a project folder and virtual environment.

bash mkdir langchain-tutorial cd langchain-tutorial python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate Install LangChain and the OpenAI integration.

bash pip install langchain langchain-openai python-dotenv For other providers:

bash pip install langchain-google-genai # Gemini pip install langchain-anthropic # Claude

Step 2: Set Up Your API Key

Create a .env file in your project folder.

text

OPENAI_API_KEY=your_api_key_here

Load it in Python:

python from dotenv import load_dotenv load_dotenv() Never hardcode API keys in your code. Use environment variables.

Step 3: Your First LLM Call

Create step1_llm.py.

python from dotenv import load_dotenv from langchain_openai import ChatOpenAI

load_dotenv()

llm = ChatOpenAI(model="gpt-4o-mini", temperature=0.7)

response = llm.invoke("Explain what a large language model is in two sentences.") print(response.content) Run it:

bash python step1_llm.py What happened:

Step 4: Prompt Templates

Hardcoding prompts is limiting. Prompt templates let you reuse prompts with variables.

Create step2_prompt.py.

python from dotenv import load_dotenv from langchain_openai import ChatOpenAI from langchain_core.prompts import ChatPromptTemplate

load_dotenv()

llm = ChatOpenAI(model="gpt-4o-mini", temperature=0.7)

prompt = ChatPromptTemplate.from_messages([ ("system", "You are a helpful assistant that explains things simply."), ("user", "Explain {topic} in {style} style.") ])

chain = prompt | llm

response = chain.invoke({ "topic": "vector databases", "style": "conversational" })

print(response.content) What happened:

Step 5: Understanding LCEL

LCEL (LangChain Expression Language) uses the pipe operator | to chain components.

python chain = prompt | llm | parser

You can chain as many components as you need.

Adding an Output Parser

python from langchain_core.output_parsers import StrOutputParser

chain = prompt | llm | StrOutputParser() result = chain.invoke({"topic": "RAG", "style": "simple"}) print(result) # Just the string

Step 6: Build a Chatbot With Memory

LLMs are stateless. Memory lets them remember conversation.

Create step3_chatbot.py.

python from dotenv import load_dotenv from langchain_openai import ChatOpenAI from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder from langchain_core.messages import HumanMessage, AIMessage

load_dotenv()

llm = ChatOpenAI(model="gpt-4o-mini", temperature=0.7)

prompt = ChatPromptTemplate.from_messages([ ("system", "You are a friendly assistant. Keep answers short."), MessagesPlaceholder(variable_name="history"), ("user", "{input}") ])

chain = prompt | llm

history = []

def chat(user_input): response = chain.invoke({ "history": history, "input": user_input }) history.append(HumanMessage(content=user_input)) history.append(AIMessage(content=response.content)) return response.content

Test the chatbot

print(chat("Hi, my name is Abhishek.")) print(chat("What is my name?")) print(chat("What did I just ask you?")) Run it:

bash python step3_chatbot.py What happened:

Step 7: Build a RAG App

RAG (Retrieval-Augmented Generation) lets your app answer from your own documents.

Install Dependencies

bash pip install langchain-community chromadb pypdf

Create a Document

Create knowledge.txt:

text Innovative AI Solutions is a Delhi-based AI development company. We build custom AI systems including chatbots, RAG systems, and AI agents. Our pricing starts at в‚№50,000 for simple projects. We serve clients across India and internationally. Contact: info@innovativeais.com

Build the RAG App

Create step4_rag.py.

python from dotenv import load_dotenv from langchain_openai import ChatOpenAI, OpenAIEmbeddings from langchain_community.document_loaders import TextLoader from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain_community.vectorstores import Chroma from langchain_core.prompts import ChatPromptTemplate from langchain_core.output_parsers import StrOutputParser from langchain_core.runnables import RunnablePassthrough

load_dotenv()

1. Load documents

loader = TextLoader("knowledge.txt") documents = loader.load()

2. Split into chunks

splitter = RecursiveCharacterTextSplitter( chunk_size=500, chunk_overlap=50 ) chunks = splitter.split_documents(documents)

3. Create embeddings and vector store

embeddings = OpenAIEmbeddings() vectorstore = Chroma.from_documents(chunks, embeddings)

4. Create retriever

retriever = vectorstore.as_retriever(search_kwargs={"k": 2})

5. Create prompt

prompt = ChatPromptTemplate.from_messages([ ("system", "Answer the question using only the context below. " "If you don't know, say so.\n\nContext:\n{context}"), ("user", "{question}") ])

6. Create LLM

llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)

7. Build RAG chain

def format_docs(docs): return "\n\n".join(doc.page_content for doc in docs)

rag_chain = ( {"context": retriever | format_docs, "question": RunnablePassthrough()} | prompt | llm | StrOutputParser() )

8. Ask questions

questions = [ "Where is Innovative AI Solutions based?", "What services do they offer?", "What is the starting price?",

"What is the capital of France?" # Out of context

]

for q in questions: print(f"Q: {q}") print(f"A: {rag_chain.invoke(q)}\n") Run it:

bash python step4_rag.py What happened:

Step 8: Add Streaming

Streaming shows responses as they generate.

python for chunk in rag_chain.stream("What services do they offer?"): print(chunk, end="", flush=True)

Step 9: Add Conversation Memory to RAG

Combine RAG with memory for follow-up questions.

python from langchain_core.messages import HumanMessage, AIMessage

history = []

def chat_with_rag(question):

Retrieve context

docs = retriever.invoke(question) context = format_docs(docs)

Build messages

messages = [ ("system", f"Answer using this context:\n{context}") ] messages.extend(history) messages.append(("user", question))

Get response

response = llm.invoke(messages)

Update history

history.append(HumanMessage(content=question)) history.append(AIMessage(content=response.content))

return response.content

print(chat_with_rag("What services do they offer?")) print(chat_with_rag("Tell me more about the first one."))

Core LangChain Components

LangChain vs LlamaIndex

Use LangChain for general apps and agents. Use LlamaIndex for RAG-heavy apps.

Common Errors and Fixes

Best Practices

Project Structure

text langchain-tutorial/ в”њв”Ђв”Ђ .env в”њв”Ђв”Ђ knowledge.txt в”њв”Ђв”Ђ requirements.txt в”њв”Ђв”Ђ step1_llm.py в”њв”Ђв”Ђ step2_prompt.py в”њв”Ђв”Ђ step3_chatbot.py в””в”Ђв”Ђ step4_rag.py

Next Steps

India-Specific Considerations

Cost

Indian LLMs

Compliance

Decision Framework

Is LangChain Right for You?

Recommended Framework

Frequently Asked Questions

1. What is LangChain in simple words?

LangChain is a Python framework for building AI apps powered by LLMs. It gives you building blocks — prompts, chains, memory, retrievers, and agents — so you do not rebuild plumbing.

2. Do I need to know Python to use LangChain?

Yes. LangChain is a Python (and JavaScript) library. Basic Python is required.

3. Is LangChain free?

Yes. LangChain is open source. You pay for the LLM API and any managed services you use.

4. Which LLM should I use with LangChain?

OpenAI (GPT-4o mini), Google (Gemini), or Anthropic (Claude). LangChain supports all major providers.

5. What is LCEL?

LCEL (LangChain Expression Language) is the pipe-based syntax for composing components: prompt | llm | parser.

6. What is the difference between LangChain and LlamaIndex?

LangChain is general-purpose for LLM apps. LlamaIndex focuses on RAG and data. Both can be used together.

7. Can I build a chatbot with LangChain?

Yes. This tutorial shows a chatbot with memory in Step 6 and a RAG chatbot in Step 9.

8. What is RAG in LangChain?

RAG (Retrieval-Augmented Generation) retrieves relevant documents and adds them to the prompt so the LLM answers from your data.

9. How much does a LangChain app cost to run?

Low-volume apps cost ₹500–₹5,000/month for LLM API and embeddings. Vector store and hosting add ₹500–₹15,000/month.

10. What is LangGraph?

LangGraph is LangChain's framework for building stateful, multi-step agents. It extends LangChain for complex workflows.

11. What is LangSmith?

LangSmith is LangChain's platform for debugging, testing, and evaluating LLM apps.

12. How can Innovative AI Solutions help?

Innovative AI Solutions is a Delhi-based AI development company. We build LangChain apps — chatbots, RAG systems, and AI agents — with transparent pricing and full code ownership. Explore our generative AI services and AI agents.

Contact Innovative AI Solutions

Ready to build your first AI app?

We help Indian businesses design, build, and deploy LangChain applications with transparent pricing and full code ownership.

Contact Information

Innovative AI Solutions

📍 Netaji Subhash Place, Pitampura, Delhi – 110034

🌐 Website: https://innovativeais.com 📧 Email: info@innovativeais.com

рџ“ћ Phone: +91 7464 099 059 / +91 96899 67356

Business Services

•⁠⁠AI Automation •⁠⁠AI Development •⁠⁠AI Consulting

•⁠⁠Machine Learning Solutions

•⁠⁠Deep Learning Solutions

•⁠⁠Generative AI Services

•⁠⁠NLP Solutions •⁠⁠AI Agents •⁠⁠AI Chatbots •⁠⁠Voice AI •⁠⁠CRM Development

•⁠⁠Custom Software Development

•⁠⁠Website Development

•⁠⁠Mobile App Development

About the Author

Abhishek Kumar

Founder & CEO, Innovative AI Solutions

5+ years building production AI systems for Indian businesses. Based in Delhi, serving clients across India.

Ready to build your first AI app?

Innovative AI Solutions — Delhi's leading AI development company. Free consultation available.

Get Free Consultation в†’

A hands-on 2026 LangChain tutorial for beginners — install LangChain, connect an LLM, build chains, add memory, and create your first RAG app in Python.

#LangChain #Tutorial #Beginners #Python #2026 #AI #LLM #Chains #Memory #RAG #Agents #Chatbot #OpenAI #Gemini #Claude #VectorStore #PromptTemplate #India #DelhiNCRTech #AIDevelopment #MachineLearning #GenerativeAI #InnovativeAISolutions

Copyright © 2015–2026 Innovative AI Solutions. All Rights Reserved. | Privacy Policy | Terms & Conditions