How to Install LangChain in Python

mkdir langchain-project
cd langchain-project

mkdir langchain-project
cd langchain-project

python3 -m venv venv

python3 -m venv venv

source venv/bin/activate

source venv/bin/activate

pip install langchain langchain-core langchain-ollama python-dotenv

pip install langchain langchain-core langchain-ollama python-dotenv

python

python

import langchain
import langchain_ollama

print("Installed successfully!")

import langchain
import langchain_ollama

print("Installed successfully!")

(venv) ➜  langchain-project python
>>> import langchain
>>> import langchain_ollama
>>>
>>> print("Installed successfully!")
Installed successfully!
>>>

(venv) ➜  langchain-project python
>>> import langchain
>>> import langchain_ollama
>>>
>>> print("Installed successfully!")
Installed successfully!
>>>

from langchain_ollama import ChatOllama
from langchain_core.prompts import PromptTemplate
from langchain_core.output_parsers import StrOutputParser

# 1. Connect to local Ollama Llama3 instance
llm = ChatOllama(
    model="llama3",
    base_url="http://192.168.1.55:11434"
)

# 2. Create prompt template
prompt = PromptTemplate.from_template("Explain {topic} in simple words.")

# 3. Convert result into plain text
parser = StrOutputParser()

# 4. Build pipeline (Prompt → Model → Text)
chain = prompt | llm | parser

# 5. Run the pipeline
response = chain.invoke({"topic": "Generative AI"})
print(response)

from langchain_ollama import ChatOllama
from langchain_core.prompts import PromptTemplate
from langchain_core.output_parsers import StrOutputParser

# 1. Connect to local Ollama Llama3 instance
llm = ChatOllama(
    model="llama3",
    base_url="http://192.168.1.55:11434"
)

# 2. Create prompt template
prompt = PromptTemplate.from_template("Explain {topic} in simple words.")

# 3. Convert result into plain text
parser = StrOutputParser()

# 4. Build pipeline (Prompt → Model → Text)
chain = prompt | llm | parser

# 5. Run the pipeline
response = chain.invoke({"topic": "Generative AI"})
print(response)

(venv) ➜  python langchain_first.py
**Generative AI: The Magic of Creating New Content**

Imagine you have a super smart artist who can create new and original paintings, music, or even entire stories with just a few clicks. That's what Generative AI is all about!

**What does it do?**

Generative AI uses algorithms to generate new content that's similar to existing ones, but with its own unique twist. It's like training a machine to learn from examples and create something entirely new based on those examples.

**How does it work?**

Here are the basic steps:

1. **Training Data**: You feed the AI system with a huge amount of data, such as images, music, text, or videos.
2. **Learning Patterns**: The AI system analyzes this data to identify patterns, styles, and structures.
3. **Creating New Content**: With these learned patterns, the AI generates new content that's similar but not identical to the original data.

**Examples of Generative AI:**

1. **Artistic Images**: AI can generate stunning paintings or illustrations based on famous art styles or even create entirely new ones.
2. **Music Composition**: AI can compose music in various genres, like pop, rock, or classical.
3. **Language Generation**: AI can write short stories, articles, or even entire books with its own unique voice and style.

**Why is Generative AI important?**

1. **Creativity Expansion**: It allows humans to explore new creative possibilities and ideas that were previously unimaginable.
2. **Content Generation**: It enables fast and efficient content creation for various industries like media, advertising, or education.
3. **Personalization**: It can create customized experiences tailored to individual preferences.

In summary, Generative AI is a powerful tool that leverages machine learning to generate new and original content across various domains, pushing the boundaries of human creativity and innovation!

(venv) ➜  python langchain_first.py
**Generative AI: The Magic of Creating New Content**

Imagine you have a super smart artist who can create new and original paintings, music, or even entire stories with just a few clicks. That's what Generative AI is all about!

**What does it do?**

Generative AI uses algorithms to generate new content that's similar to existing ones, but with its own unique twist. It's like training a machine to learn from examples and create something entirely new based on those examples.

**How does it work?**

Here are the basic steps:

1. **Training Data**: You feed the AI system with a huge amount of data, such as images, music, text, or videos.
2. **Learning Patterns**: The AI system analyzes this data to identify patterns, styles, and structures.
3. **Creating New Content**: With these learned patterns, the AI generates new content that's similar but not identical to the original data.

**Examples of Generative AI:**

1. **Artistic Images**: AI can generate stunning paintings or illustrations based on famous art styles or even create entirely new ones.
2. **Music Composition**: AI can compose music in various genres, like pop, rock, or classical.
3. **Language Generation**: AI can write short stories, articles, or even entire books with its own unique voice and style.

**Why is Generative AI important?**

1. **Creativity Expansion**: It allows humans to explore new creative possibilities and ideas that were previously unimaginable.
2. **Content Generation**: It enables fast and efficient content creation for various industries like media, advertising, or education.
3. **Personalization**: It can create customized experiences tailored to individual preferences.

In summary, Generative AI is a powerful tool that leverages machine learning to generate new and original content across various domains, pushing the boundaries of human creativity and innovation!

from langchain_ollama import ChatOllama
from langchain_core.prompts import PromptTemplate
from langchain_core.output_parsers import StrOutputParser

prompt = PromptTemplate.from_template("""
You are an expert AI tutor.
Explain the topic below clearly, using a friendly tone.

Topic: {topic}

Keep the answer under 100 words.
""")

chain = prompt | ChatOllama(
    model="llama3.1",
    base_url="http://192.168.29.191:11434"
) | StrOutputParser()

print(chain.invoke({"topic": "Neural Networks"}))

from langchain_ollama import ChatOllama
from langchain_core.prompts import PromptTemplate
from langchain_core.output_parsers import StrOutputParser

prompt = PromptTemplate.from_template("""
You are an expert AI tutor.
Explain the topic below clearly, using a friendly tone.

Topic: {topic}

Keep the answer under 100 words.
""")

chain = prompt | ChatOllama(
    model="llama3.1",
    base_url="http://192.168.29.191:11434"
) | StrOutputParser()

print(chain.invoke({"topic": "Neural Networks"}))

(venv) ➜  python langchain_second.py
Let's dive into Neural Networks!

Imagine you're trying to recognize a cat in a picture. You'd look at its whiskers, ears, and fur texture. A Neural Network is like a super-smart brain that breaks down complex information (like a picture) into smaller parts, analyzes each one, and then puts the pieces together to make a decision.

Inside a Neural Network, there are many layers of "neurons" (think tiny computers) that communicate with each other to learn patterns in data. This helps them become super-good at recognizing things like pictures, speech, or even predicting future events!

(venv) ➜  python langchain_second.py
Let's dive into Neural Networks!

Imagine you're trying to recognize a cat in a picture. You'd look at its whiskers, ears, and fur texture. A Neural Network is like a super-smart brain that breaks down complex information (like a picture) into smaller parts, analyzes each one, and then puts the pieces together to make a decision.

Inside a Neural Network, there are many layers of "neurons" (think tiny computers) that communicate with each other to learn patterns in data. This helps them become super-good at recognizing things like pictures, speech, or even predicting future events!

ollama serve

ollama serve