Giter VIP home page Giter VIP logo

fosdem2024's Introduction

LangChain From 0 To 1: Unveiling the Power of LLM Programming

The talk

https://video.fosdem.org/2024/ub2252a/fosdem-2024-2384-langchain-from-0-to-1-unveiling-the-power-of-llm-programming.av1.webm

Install

(optional) create virtualenv

python -m venv fosdemvenv && source fosdemvenv/bin/activate

Install requirements

pip install -r requirements.txt

API Key

export OPENAI_API_KEY=xx-xXxXxXxXxXxXxXxXxXxXxXxXxXxXxXxXxXxXxXxXxXxXxXxX 

run

python src/rag/rag.py

Talk Abstract

Unlocking the realm of Artificial Intelligence has never been more accessible than with LangChain and its seamless integration of external APIs or locally hosted OS Language Model Models (LLMs). In this talk, we embark on a journey from zero to Retrieval Augmented Generation (RAG).

Our hands-on exploration will guide you through the basics of LangChain and LLMs, demonstrating how just a few lines of code can transform any application into an intelligent powerhouse. We'll delve into the construction of a simple Python application, serving as a springboard for grasping more intricate functions and concepts within the LangChain framework.

Key Takeaways:

  • Querying LLMs via APIs: Witness the simplicity of tapping into the vast capabilities of Language Models through straightforward API calls.

  • Textual Data Handling: Learn to load text from a diverse array of documents, enabling your application to process information from various sources.

  • Text Splitting Techniques: Explore the world of text splitting, understanding different methods to break down textual data into meaningful units.

  • Introduction to Embeddings: Gain insights into the fundamental concept of embeddings, unraveling why they are pivotal in enhancing the intelligence of applications.

  • Vector Databases: Navigate the landscape of vector databases and understand their role in optimizing data retrieval and manipulation.

  • RAG (Retrieval Augmented Generation): Witness the transformative power of RAG as we leverage it to query LLMs over your dataset, showcasing a synergy between retrieval and generation.

  • Chains and other notable use cases

Join us in this concise yet comprehensive session, where we demystify LangChain and empower you to harness the full potential of LLM programming. Whether you're a novice or an experienced developer, this talk is your gateway to building intelligent applications with ease.

Useful links

Presentation

https://docs.google.com/presentation/d/1frjlNBY0Et7xpNizhKVtdtTLe09DXuQv8BjGmbRZyNk/

Rag in production

LangChain chatbot

https://chat.langchain.com/

https://github.com/langchain-ai/chat-langchain

LangChain documentation

https://python.langchain.com/docs/get_started/introduction

LangChain GitHub

https://github.com/langchain-ai/langchain

python src/rag/rag.py

Links, tools, credits

LangChain on X is worth following https://x.com/LangChainAI

Visualize different text splitters https://chunkviz.up.railway.app/

Text splitting tutorial https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/5_Levels_Of_Text_Splitting.ipynb

LangChain State of AI 2023 https://blog.langchain.dev/langchain-state-of-ai-2023/

Code screenshot generated with Carbon https://carbon.now.sh/

Contacts

https://twitter.com/Stll00

fosdem2024's People

Contributors

stell0 avatar

Stargazers

Jan Kostulski avatar Paolo Di Filippo avatar  avatar  avatar Tobias Kutning avatar Vincent van Dam avatar Timothy Spann avatar Thomas Darimont avatar  avatar pietrodev07 avatar Andrea Nuzzo avatar Lanfeust21 avatar FCastanedo avatar Przemyslaw Mejna avatar Alessandro Guttrof avatar  avatar Daniele Barbaro avatar Stephane de Labrusse avatar Pensegi avatar m.d. avatar Leroy Shirto avatar Sissel avatar

Watchers

 avatar

Forkers

danielfl

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.