chroma_db

ChromaDB is a vector database designed to efficiently store and retrieve high-dimensional data, particularly useful in applications involving machine learning and natural language processing. It leverages advanced techniques such as cosine similarity for similarity searches, allowing users to find the nearest neighbors of a given query. ChromaDB integrates seamlessly with frameworks like FastAPI, enabling developers to build applications that require quick access to large datasets. By utilizing embedding functions, it enhances the performance of data retrieval tasks, making it a valuable tool for developers working with complex data patterns and AI-driven applications.

Embeddings and Vector Databases With ChromaDB

Real Python

Vector databases are a crucial component of many NLP applications. This tutorial will give you hands-on experience with ChromaDB, an open-source vector database that's quickly gaining traction. Along ...

Python Embraces ChromaDB and ParquetDB for New Data Patterns

Python in Plain English

The data tools world keeps changing. Two newer systems ChromaDB and ParquetDB are attracting attention in Python workflows. They serve different use cases but share a goal: give developers simpler, mo...

Building Vector Databases with FastAPI and ChromaDB

Level Up Coding

Beginners guide to ChromaDB vectorstores and FastAPI with Langchain Returning to writing after a lengthy break, I’m finally carving out some time to dive into it. With the amount of innovations and n...

Using GraphSAGE to Learn Paper Embeddings in CORA

Towards Data Science

CORA[1] is a dataset of academic papers of seven different classes. It contains the citation relations between the papers as well as a binary vector for each paper that specifies if a word occurs in…

DuckDB

Better Programming

Member-only story DuckDB A Deep Dive into a Fast and Efficient Database Using Python Thomas Reid · Follow Published in Better Programming · 9 min read · Just now -- Share DuckDB is an in-memory analyt...

— Unicode Database

The Python Standard Library

unicodedata — Unicode Database This module provides access to the Unicode Character Database (UCD) which defines character properties for all Unicode characters. The data contained in this database i...

MongoDB

Level Up Coding

MongoDB is a cross-platform document-oriented database. Document-oriented databases strongly contrast with the traditional relational databases. MongoDB is a NoSQL database which allows you to store…

Document Summarization & QA in RAG without Frameworks (PyMuPDF & ChromaDB)

Towards AI

Photo by Arisa Chattasa on Unsplash Explore how RAG works under the hood by building a PDF summarization pipeline with PyMuPDF and ChromaDB — no frameworks needed. Table of Contents · Introduction · O...

Databases

The Hitchhiker's Guide to Python!

Databases DB-API The Python Database API (DB-API) defines a standard interface for Python database access modules. It’s documented in PEP 249 . Nearly all Python database modules such as sqlite3 , psy...

— The shadow password database

The Python Standard Library

spwd — The shadow password database This module provides access to the Unix shadow password database. It is available on various Unix versions. You must have enough privileges to access the shadow pa...

The Database Zoo: Probabilistic / Approximate Databases

Level Up Coding

Photo by Mick Haupt on Unsplash This post is part of The Database Zoo: Exotic Data Storage Engines , a series exploring purpose-built databases engineered for specific workloads. Each post dives into ...

— Interfaces to Unix “databases”

The Python Standard Library

dbm — Interfaces to Unix “databases” Source code: Lib/dbm/__init__.py dbm is a generic interface to variants of the DBM database — dbm.gnu or dbm.ndbm . If none of these modules is installed, the slo...