LangChain

LangChain is an open-source framework designed to build applications like RAG and Agents with Large Language Models (LLMs). It provides following key components:

• Chat models and prompts: Build LLM applications that can scale across resources, using prompt templates and chat models.
• Semantic search: Process large research datasets and PDFs efficiently by combining document loaders, embedding models, and vector stores.
• Classification: Classify text into categories or labels using chat models with structured outputs.
• Extraction: Extract structured data from text and other unstructured media using chat models and few-shot examples.

Quick guide

The LangChain module comes with following Extensions: jsonpatch, jsonpointer, LangChain, langchain-core, langchain-text-splitters, langsmith, orjson, packaging, tenacity and gets loaded by loading LangChain module: module load LangChain

Simple python example

from langchain.text_splitter import CharacterTextSplitter

def main():
    # Example text
    text = """
    LangChain is a framework for developing applications powered by language models.
    It enables developers to chain together different components to create more complex applications.
    """

    # Initialize a text splitter
    text_splitter = CharacterTextSplitter(
        separator="\n",  # Split by newlines
        chunk_size=50,   # Maximum size of each chunk
        chunk_overlap=10 # Overlap between chunks
    )

    # Split the text into chunks
    chunks = text_splitter.split_text(text)

    # Print the resulting chunks
    print("Text Chunks:")
    for i, chunk in enumerate(chunks):
        print(f"Chunk {i + 1}: {chunk}")

if __name__ == "__main__":
    main()