sasadangelo/langchain-tutorials

Langchain tutorials

These tutorials will help you to build, step by step, a RAG Chatbot using Large Languages Models (LLM) and Lanch Chain. Here the list of lessons:

• Lesson 1: Hello LLM
• Lesson 2: Hello LLM with providers configuration
• Lesson 3: a simple Chatbot
• Lesson 4: a simple Chatbot with Context
• Lesson 5: just a few improvements
• Lesson 6: an Object Oriented ChatBOT with Lang Chain
• Lesson 7: Configure generation parameters
• Lesson 8: Memory Management during the conversation
• Lesson 9: DataWaeve CLI and Qdrant
• Lesson 10: RAG implementation
• Lesson 11: Add UI interface with Streamlit

Prerequisites

How to install Python 3 (min version 3.12)

To run the tutorials you need Python 3 installed on your machine. On Mac you can simply type:

brew install python3

How to setup Ollama

To run the tutorials with Ollama provider you need to install ollama cli:

brew install ollama

You can start the ollama server with the command:

ollama serve

In another terminal:

• you should download the LLM llama3 model in the ~/.ollama folder:

ollama pull llama3

• you can list the downloaded model using the commands:

ollama list

Clone the LangChain-Tutorials repository

To run the tutorials you need to clone the langchain-tutorials repository in a <workspace> folder:

cd <workspace>
git clone https://github.com/sasadangelo/langchain-tutorials
cd langchain-tutorials

How to run the tutorials

To run the tutorials do the following steps:

1. Create and activate the Python virtual environment:

python3 -m venv venv
source venv/bin/activate

2. Install the dependencies

pip3 install -r requirements.txt

3. Run the tutorial following the instructions in each lesson