mastouille.fr est l'un des nombreux serveurs Mastodon indépendants que vous pouvez utiliser pour participer au fédiverse.
Mastouille est une instance Mastodon durable, ouverte, et hébergée en France.

Administré par :

Statistiques du serveur :

589
comptes actifs

#langchain

0 message0 participant0 message aujourd’hui

Want to really understand how RAG, vector search & chunking work?

Then stop reading theory and build your own chatbot.

This guide shows you how to create a local PDF chatbot using:

☕ LangChain

☕ FAISS (vector DB)

☕ Mistral via Ollama

☕ Python & Streamlit

Step-by-step, from environment setup to deployment. Ideal for learning how Retrieval-Augmented Generation works in practice.

👉 medium.com/data-science-collec

Comment “WANT” if you need the friends link to the article, as you don’t have paid Medium.

Data Science Collective · RAG in Action: Build your Own Local PDF Chatbot as a BeginnerPar Sarah Lea
#rag#tech#Technology

AI is becoming a must-have in modern applications. This article explains how to connect Ollama AI using Apache Camel and the LangChain4j component.

Here’s what you’ll learn:
- How to set up the integration step-by-step
- How Camel simplifies workflows
- Why LangChain4j is a great fit for Java developers

contenerizar.com/how-to-connec

Contenerizar · How to connect Ollama AI using Apache Camel and Langchain4j component. - ContenerizarImage generated with Meta AI. This post will explore the synergy between three such tools: Ollama, Apache Camel and LangChain4j. In this post Setting Up the Dev
#Java#AI#ApacheCamel
A répondu dans un fil de discussion

@Sempf

NotebookLM is essentially a RAG (Retrieval Augmented Generation) system. It “indexes” given corpus in the semantic space of the Google’s LLM. Then you can query it. The answers are restricted to the given corpus.

I’m sure there are some homebrew RAG systems. However, it’s more than just hosting the model (e.g., a quantized Llama 8B model). It’s a project.

You can look at #LangChain or #HuggingFace more generally. With NotebookLM you can test immediately.

“We are excited to announce huggingface-langchain🚀 A new open-source [Python] package to seamlessly integrate the latest open Models from Hugging Face into LangChain supporting local models & hosted models! 🤗🦜” - Philipp Schmid, Hugging Face

huggingface.co/blog/langchain

huggingface.coHugging Face x LangChain : A new partner packageWe’re on a journey to advance and democratize artificial intelligence through open source and open science.
#GenAI#LLMs#LangChain

A new Web-based journaling app from #LangChain remembers what you tell it and can chat with you about your entries using #GenAI

I wouldn't suggest putting anything personal in there -- it's a demo project and I don't know its privacy and security policies. But if you find the concept intriguing as opposed to creepy, you can try it at

journal.langchain.com/

Blog post explaining more about the "LangFriend" project: blog.langchain.dev/langfriend/
Video: youtube.com/watch?v=tSicjawrfU

journal.langchain.comLangChain Companion - JournalAdd journal entries inside LangChain Companion

RAG From Scratch - Langchain Tutorial 🦜👇🏼

The RAG From Scratch is a crash course by Lance Martin from LangChain focusing on the foundations of Retrieval Augmented Generation (RAG). This tutorial covers the process of index, retrieval, and generation of a query from scratch 🚀.

Video 📽️: youtube.com/playlist?list=PLfa
Code 🔗: github.com/langchain-ai/rag-fr

Image credit: Tutorial slides

#llm#rag#DataScience

The next Tampa Bay AI Meetup happens Wednesday, March 20th at 6:30 p.m., where we’ll cover building AI applications with Python and LangChain! LangChain enhances LLM-powered applications by enabling retrieval-augmented generation (RAG), providing “memory,” and giving LLMs the ability to respond with structured data. You’ll how to build better AI apps at this meetup!

#AI #ArtificialIntelligence #Python #LangChain #meetup #meetups #Tampa #TampaBay

meetup.com/tampa-artificial-in

MeetupHow to build AI applications with Python and LangChain, Wed, Mar 20, 2024, 6:30 PM | MeetupYou can build AI applications using only a large language model (LLM) like the one that powers ChatGPT, but you’ll eventually hit the limitations that all LLMs have, includ