openai-quickstart-node VS chroma

Github repo link: https://github.com/openai/openai-quickstart-node

Building with OpenAI API

The next step is to pass this context to an LLM. We'll use SOTA gpt-3.5-turbo model. You'll need an OpenAI API key for this, which you can get here.

You can check out OpenAI's docs, including their quick start example here: https://platform.openai.com/docs/quickstart

For these prompts, I used the quickstart tutorial from Open AI: https://beta.openai.com/docs/quickstart

Overview: Chroma is a versatile vector database that excels in managing and retrieving high-dimensional data. It's optimized for AI-driven applications, offering powerful tools for developers.

git clone -b 0.5.0 --depth=1 https://github.com/chroma-core/chroma cd chroma docker-compose up -d

https://news.ycombinator.com/item?id=40115099 :

> lancedb/lance is faster than pandas with dtype_backend="arrow" and has a vector index

From https://github.com/lancedb/lance :

> Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow,

> [...] Vector Search

> comparison of different data formats in each stage of ML development cycle: Lance, Parquet & ORC, JSON & XML, TFRecord, Database, Warehouse

What can ChromaDB do that lancedb can't, and will either work in WASM?

From https://github.com/chroma-core/chroma :

> By default, Chroma uses Sentence Transformers to embed for you but you can also use OpenAI embeddings, Cohere (multilingual) embeddings, or your own.

In an era where data privacy is paramount, setting up your own local language model (LLM) provides a crucial solution for companies and individuals alike. This tutorial is designed to guide you through the process of creating a custom chatbot using Ollama, Python 3, and ChromaDB, all hosted locally on your system. Here are the key reasons why you need this tutorial:

Package installer for Python (pip), we use this for installing the Python-based packages, such as Jupyter Lab, and we're going to use this for installing other Python-based tools like the Chroma DB vector database

Optional: You can use SillyTavern[1] for a more "rich" chat experience

The above lets me chat, at least superficially, with my friend. It's nice for simple interactions and banter; I've found it to be a positive and reflective experience.

0. https://www.trychroma.com/

Chroma DB is a newer entrant in the vector database arena, designed specifically for handling high-dimensional color vectors. It's particularly useful for applications in digital media, e-commerce, and content discovery, where color similarity plays a crucial role in search and recommendation algorithms.

View on GitHub

For Python I believe Chroma [1] can be used embedded.

For Go I recently started building chromem-go, inspired by the Chroma interface: https://github.com/philippgille/chromem-go

It's neither advanced nor for scale yet, but the RAG demo works.

[1] https://github.com/chroma-core/chroma