LangChain with Google Gemini in Python: Your First Program Explained Line by Line

 


LangChain is an open-source Python framework that helps developers build applications powered by Large Language Models (LLMs) such as Google Gemini, OpenAI GPT, Anthropic Claude, and others. Instead of writing low-level API calls, LangChain provides reusable components for prompts, message handling, chains, document retrieval, memory, tools, and agents, making it easier to build intelligent AI applications.

Installation

## Install Required Packages

Create a Python virtual environment (recommended), then install the required packages:

pip install langchain langchain-google-genai python-dotenv

code :
The following example demonstrates the simplest way to communicate with Google's Gemini model using LangChain.

from dotenv import load_dotenv

from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_core.messages import HumanMessage

# Load environment variables
load_dotenv()

# Create the LLM
llm = ChatGoogleGenerativeAI(
    model="gemini-2.5-flash"
)

# Ask a question
response = llm.invoke(
    [HumanMessage(content="What is LangChain? Explain in two lines.")]
)

print(response.content)

What is dotenv?

API keys should never be hardcoded in your source code. Instead, they are usually stored in a .env file. The python-dotenv package reads this file and loads the values into your application's environment.

dotenv is a Python package (installed with pip install python-dotenv) that reads environment variables from a .env file.

2. from langchain_google_genai import ChatGoogleGenerativeAI

from langchain_google_genai import ChatGoogleGenerativeAI

  • langchain_google_genai is a Python module (provided by the langchain-google-genai package).

  • ChatGoogleGenerativeAI is a class inside that module.

    • 3. from langchain_core.messages import HumanMessage

    This imports the HumanMessage class.  Instead of sending a plain string:

    "What is AI?"

    LangChain represents every conversation as a collection of message objects rather than plain strings.

    Example:

    HumanMessage(content="What is AI?")

    This means:

    "This message was sent by the human user."

    There are other message types as well:

    HumanMessage(...)
AIMessage(...)
SystemMessage(...)
ToolMessage(...)

    These let LangChain keep track of who said what in a conversation.

    For example:

    messages = [
    SystemMessage(content="You are a helpful teacher."),
    HumanMessage(content="Explain Python."),
]


    StatementModuleImported ItemPurpose
    from dotenv import load_dotenvdotenvload_dotenv (function)Loads environment variables from a .env file.
    from langchain_google_genai import ChatGoogleGenerativeAIlangchain_google_genaiChatGoogleGenerativeAI (class)Creates a client for interacting with Gemini models.
    from langchain_core.messages import HumanMessagelangchain_core.messagesHumanMessage (class)Represents a message sent by the user in a conversation.


    Let's compare it against the major LangChain concepts.

    LangChain FeatureUsed?Explanation
    ✅ Model Integration✔ YesChatGoogleGenerativeAI connects LangChain to Gemini.
    ✅ Message Objects✔ YesHumanMessage is a LangChain message abstraction.
    ✅ LLM Invocation✔ Yesllm.invoke() is LangChain's standard API for calling models.
    Prompt Templates❌ NoYou're writing the prompt directly instead of using PromptTemplate.
    Chains / LCEL❌ NoNo multi-step workflow.
    Retrieval (RAG)❌ NoNo documents or vector database.
    Embeddings❌ NoNot generating embeddings.
    Vector Store❌ NoNo Chroma, FAISS, Pinecone, etc.
    Memory❌ NoNo conversation history management.
    Agents❌ NoThe model is not choosing or calling tools.
    Tools❌ NoNo calculator, search, APIs, or custom functions.
    Output Parsers❌ NoThe response is used as plain text.
    Document Loaders❌ NoNo PDFs, Word files, websites, etc.
    Callbacks / Tracing❌ NoNo monitoring or logging.


    Why not just pass a string?

    Suppose you do this:

    llm.invoke("What is Python?")

    This works because LangChain automatically treats the string as a human message.

    But imagine a conversation like this:

    User: What is Python?
AI: It is a programming language.
User: Who created it?

    If you only pass strings, how does the model know:

    • Which text came from the user?
    • Which text was generated by the AI?
    • Which text is an instruction from the system?

    It can't.

    That's why LangChain uses message objects.

    Here .............

    chain = prompt | llm

    really means

    chain = RunnableSequence(prompt, llm)

    The variable chain is just a normal Python variable. The object stored inside it is a RunnableSequence (or a closely related runnable type implemented by LangChain), not a special language feature.


    Comments

    Post a Comment

    Popular posts from this blog

    Aggregate function with spring data

    Image
    I was working on a small project. Requirement was different in term of object mapping. There is simple way to map  java object with database table. Aggregate function in query is not mapped with entity class. We don't have direct mapping attribute in JPA annotation to map aggregate function with entity class. Spring data support this using interface. In ORM query we use aggregate function e.g. count , sum etc. the output of these aggregate function cannot directly map with the Entity class. To collect the outcome of aggregate methods. We need to map using interface in java and provide the Interface class with mapping method.      public List<ITeacherReport> getTeacherReport(String teacherName); Our requirement is to count solved question per month by teacher from answer table. We have below environment configuration. Thymeleaf (for view,  this is template engine) JDK 1.8 Maven Springboot framework  MySql  for database operation Open the start....
    Read more

    Java Persistence API with Spring Data

    Image
    Let's try to build simple java application with the help of Spring Tool Suites IDE, Spring-Data connecting and MySql's relation database. You are free to choose any IDE (STS, Eclipse, Intellij etc).  We are building simple application which is storing User information into MySQL Database table. Our Requirements are simple IDE (any IDE, STS, Eclipse or Intellij) JDK 1.8 later  Maven 3.2 Create a Maven project using spring initializr   Open the Spring Initializr ( https://start.spring.io/  ).  This is the best way to start the project. Type the https://start.spring.io on url browser  The Initializr provides quick solution to place dependency and create project structure. Our requirement is JPA and MySql dependencies. below image shows the Initializr with required dependency selection: Following  pom.xml  file  will be generated having   spring-boot-starter-data  and   mysql-con...
    Read more

    Thread , Runnable and ExecutorService

    Image
      Previous approach to create a thread.  1.  Directly create an object of Thread Class after overriding the public void run() method of Thread class and call the start method to initiate the thread package com.executor; public class OldThread implements Runnable { private String task ; public OldThread() { super (); } public OldThread(String task ) { super (); this . task = task ; } @Override public void run(){ System. out .println( " Old thread runnable " + this . task ); try { Thread. sleep (2000); } catch (InterruptedException e ) { e .printStackTrace(); } System. out .println( this . task + " completed." ); } } 2. Implement the Runnable interface  and override the public void method and pass the reference of Runnable Object reference  into Thread(Runnable) constructor. call the start method to initiate the thread package com.executor; public cl...
    Read more