CodeChat: Enabling interaction with codebases present in GitHub repositories. Seamlessly explore, query, and discuss code with a powerful RAG pipeline, making coding intuitive and efficient
-
Updated
Jan 4, 2024 - Jupyter Notebook
CodeChat: Enabling interaction with codebases present in GitHub repositories. Seamlessly explore, query, and discuss code with a powerful RAG pipeline, making coding intuitive and efficient
Homework 3 for the machine learning class at Tsinghua University (fall term 23/24)
we learn how we can feed the output of vector databases (in our story, we employed ChromaDB) to a Large Language Model to build RAG
using mulimodal RAG to query texts, images and tables from pdf for QA
A Gemma based RAG that answers python specific questions
Exploring LLM RAG applications.
Build a RAG app from scratch using Chroma and the ChatGPT API
Vectara's RAG-Enhanced Customer Service Bot Platform
Dive into LangChain, a powerful platform that lets you interact with your data like never before. This guide offers insights on its unique capabilities, helping you tap into your data in conversational ways.
EMNLP'2023: Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System
Takes in a user's question and returns an answer along with URL resources.
"Chat with Databases using RAG" is a cutting-edge project that seamlessly integrates natural language inputs with database interactions. By leveraging advanced techniques like RAG and few-shot learning, it generates SQL queries from plain text and retrieves human-like responses from the database, revolutionizing the way we interact with data.
Offline Multi-Modal RAG. Execution Scripts optimized for for Intel, CUDA.
Using USearch vector-search engine for RAG with LangChain
a RAG framework that can search and answers questions from existing docs
JPT - An application using GPT-3.5, LangChain and ElasticSearch for learning Japanese. This repository is our work at Sun* Hackathon 2023
A Retrieval-Augmented Generation (RAG) based Medical Chatbot. With the base model as Llama2 from Meta, the Retrieval system uses a medical document as corpus to generate context-rich output.
Prototipo per l'implementazione di un chatbot con Gemini 1.5 Pro o PaLM 2 chat-bison, LangChain4J, Spring.
just attempting to build a retrieval augmented generation package primarily focused on the antropic llm claude AI if everything goes as planned will start working on other LLMS. I'll appreciate the opportunity to talk about this.
Add a description, image, and links to the retrieval-augmented-generation topic page so that developers can more easily learn about it.
To associate your repository with the retrieval-augmented-generation topic, visit your repo's landing page and select "manage topics."