RAG on codebases using treesitter and LanceDB
-
Updated
Nov 17, 2024 - Python
RAG on codebases using treesitter and LanceDB
Harness the power of Retrieval-Augmented Generation with the Personal AI Assistant, an innovative tool designed to extract and synthesize information from web and PDF sources efficiently. This cutting-edge solution transforms complex data into concise, actionable insights, making it indispensable for researchers and professionals alike.
Implementing LangChain concepts and building meaningful stuffs
[WORK IN PROGRESS] Complete vector search stack • Document processing pipeline • Semantic chunking • Embedding generation • Advanced retrieval strategies • Production-ready microservice
Insurance AI Assistant A smart system combining PostgreSQL, Milvus, and specialized AI agents (Life/Home/Auto) to answer insurance queries accurately. Features real-time sync, semantic search via OpenAI embeddings, and a Streamlit UI. Perfect for insurance tech demos or customer service augmentation.
Detailed description given in the README
Make multiple Collections on Qdrant with Langchain & Openai
Personal Project | A personal and private recommendation engine for the internet
Langchain RAG AstraDB
Creates mapping table to merge 2 tables
This is the backend server for LifeKb which vector embeds the journal entries.
A RAG chatbot which enables user to chat with their pdf documents
A simple Text Embedding API Server
A website that summarizes PDFs into simple paragraphs based on user's queries_using Streamlit, LangChain, OpenAI, and ChromaDB Docker Image technologies.
Successfully designed and developed a customer support chatbot that leverages LangChain and Pinecone for efficient retrieval-augmented generation (RAG), enabling intelligent and context-aware responses to user queries.
Chat with any website using Python and Langchain
Document Retrieval System with Hybrid Embeddings using LangChain, OpenAI embeddings, FastEmbedSparse, ChatGroq.
An API that generates questions, answers, explanations, and sources based on a provided PDF textbook and specified content to learn.
A data-driven approach to designing an optimal Data Science curriculum. This project extracts skills from job postings, applies NLP and clustering techniques (K-Means, Hierarchical, DBSCAN), and maps industry demands to educational recommendations. Uses Python, Scikit-learn, OpenAI embeddings, and Seaborn for visualization.
Add a description, image, and links to the openai-embeddings topic page so that developers can more easily learn about it.
To associate your repository with the openai-embeddings topic, visit your repo's landing page and select "manage topics."