eQuiLabs
Building tools to enrich our digital lives
Open-source AI engineering by Justin Parker \\ updated continuously from GitHub
Featured \\
Hand-picked highlights from 54 open-source projects.
-
semantic-chunking
NPM Package for Semantically creating chunks from large texts. Useful for workflows involving large language models (LLMs).
NPM Package for semantically creating chunks from large texts, useful for workflows involving LLMs.
-
embedding-utils
Vector math, similarity search, ANN indexing, clustering, async pipelines, evaluation metrics, and multi-provider embedding generation -- zero dependencies,...
Vector math, similarity search, ANN indexing, clustering, async pipelines, evaluation metrics, and multi-provider embedding generation.
-
fast-topic-analysis
A tool for analyzing text against predefined topics using average weight embeddings and cosine similarity.
A tool for analyzing text against predefined topics using average weight embeddings and cosine similarity.
-
pixel-banner
Pixel Banner is a powerful Obsidian plugin that transforms your notes with customizable banner images, creating visually stunning headers that enhance your k...
Obsidian plugin that transforms notes with customizable banner images, creating headers that enhance your knowledge workspace.
-
mcp-sqlite
This is a Model Context Protocol (MCP) server that provides comprehensive SQLite database interaction capabilities.
Model Context Protocol (MCP) server that provides comprehensive SQLite database interaction capabilities.
-
bedrock-wrapper
Bedrock Wrapper is an npm package that simplifies the integration of existing OpenAI-compatible API objects with AWS Bedrock's serverless inference LLMs. Fol...
npm package that simplifies the integration of existing OpenAI-compatible API objects with AWS Bedrock's serverless inference LLMs.
-
llm-distillery
Use LLMs to distill large texts down to a manageable size by utilizing a map-reduce approach. This ensures that the text fits within a specified token limit,...
Use LLMs to distill large texts down to a manageable size by utilizing a map-reduce approach.