Docling is a tool that parses documents and exports them to desired formats like Markdown and JSON. It supports various document formats and provides advanced PDF understanding, metadata extraction, and integration with LlamaIndex and LangChain for RAG / QA applications.
Karishma Shukla announces the open-sourcing of Maxun, a no-code web data extraction platform. Maxun allows users to build custom data scraping robots easily, bypass geolocation restrictions, captchas, and anti-bot measures. The project aims to democratize access to web data and offer a simple API for users.
A guided series of tutorials/notebooks to build a PDF to Podcast workflow using Llama models for text processing, transcript writing, dramatization, and text-to-speech conversion.
A list of 11 open source AI projects designed to help developers streamline their work, from training models to improving productivity and data management.
| Project Name | Description |
|----------------------|-----------------------------------------------------------------------------|
| Upscayl | Increases image resolution for enhanced detail, ideal for digital artwork. |
| Nyro | Automates mundane tasks like taking screenshots and resizing windows. |
| Geppetto | Enhances Slack documentation with help from LLMs and can request art from Dall-E. |
| E2B sandboxes | Allows LLMs to use web browsers, GitHub, and command-line tools for tasks like cloud management. |
| Dataline | Generates SQL commands to extract data and create data science reports locally. |
| Swirl Connect | Links standard databases with LLMs and RAG search indices for easier data access. |
| DSPy | Offers a systematic approach to LLM training by connecting modules and optimizers. |
| Guardrails | Integrates controls into generative AI pipelines to refine AI-generated answers and reduce errors. |
| Unsloth | Optimizes training of open-source models for faster and more accurate results. |
| Wren AI for SQL | Translates natural language questions into SQL queries, simplifying data retrieval. |
| AnythingLLM | Organizes digital documents and allows querying with any LLM or RAG system. |
| Project Name | Description |
|----------------------|-----------------------------------------------------------------------------|
| Upscayl | Increases image resolution for enhanced detail, ideal for digital artwork. |
| Nyro | Automates mundane tasks like taking screenshots and resizing windows. |
| Geppetto | Enhances Slack documentation with help from LLMs and can request art from Dall-E. |
| E2B sandboxes | Allows LLMs to use web browsers, GitHub, and command-line tools for tasks like cloud management. |
| Dataline | Generates SQL commands to extract data and create data science reports locally. |
| Swirl Connect | Links standard databases with LLMs and RAG search indices for easier data access. |
| DSPy | Offers a systematic approach to LLM training by connecting modules and optimizers. |
| Guardrails | Integrates controls into generative AI pipelines to refine AI-generated answers and reduce errors. |
| Unsloth | Optimizes training of open-source models for faster and more accurate results. |
| Wren AI for SQL | Translates natural language questions into SQL queries, simplifying data retrieval. |
| AnythingLLM | Organizes digital documents and allows querying with any LLM or RAG system. |
PocketPal AI is an application that brings language models directly to your phone, offering offline AI assistance and model flexibility for both iOS and Android devices.
This repository contains the Llama Stack API specifications as well as API Providers and Llama Stack Distributions. The Llama Stack aims to standardize the building blocks needed for generative AI applications across various development stages.
It includes API specifications and providers for the Llama Stack, which aims to standardize components needed for developing generative AI applications. The stack includes APIs for Inference, Safety, Memory, Agentic System, Evaluation, Post Training, Synthetic Data Generation, and Reward Scoring. Providers offer actual implementations for these APIs, either through open-source libraries or remote REST services.
It includes API specifications and providers for the Llama Stack, which aims to standardize components needed for developing generative AI applications. The stack includes APIs for Inference, Safety, Memory, Agentic System, Evaluation, Post Training, Synthetic Data Generation, and Reward Scoring. Providers offer actual implementations for these APIs, either through open-source libraries or remote REST services.
Dune is a shell designed for powerful scripting, combining elements of bash and Lisp, offering normal shell operations and functional programming abstractions for sysadmin tasks.
Datasette is introduced as a functional interactive frontend to tabulated data, either in CSV format or a database schema, catering to data journalists, museum curators, archivists, local governments, and researchers.
The author explores creating tables and inserting data into a SQLite database, then targets the database with Datasette to showcase how errors in data can be identified and corrected.
The author explores creating tables and inserting data into a SQLite database, then targets the database with Datasette to showcase how errors in data can be identified and corrected.
ASCVIT V1 aims to make data analysis easier by automating statistical calculations, visualizations, and interpretations.
Includes descriptive statistics, hypothesis tests, regression, time series analysis, clustering, and LLM-powered data interpretation.
- Accepts CSV or Excel files. Provides a data overview including summary statistics, variable types, and data points.
- Histograms, boxplots, pairplots, correlation matrices.
- t-tests, ANOVA, chi-square test.
- Linear, logistic, and multivariate regression.
- Time series analysis.
- k-means, hierarchical clustering, DBSCAN.
Integrates with an LLM (large language model) via Ollama for automated interpretation of statistical results.
Includes descriptive statistics, hypothesis tests, regression, time series analysis, clustering, and LLM-powered data interpretation.
- Accepts CSV or Excel files. Provides a data overview including summary statistics, variable types, and data points.
- Histograms, boxplots, pairplots, correlation matrices.
- t-tests, ANOVA, chi-square test.
- Linear, logistic, and multivariate regression.
- Time series analysis.
- k-means, hierarchical clustering, DBSCAN.
Integrates with an LLM (large language model) via Ollama for automated interpretation of statistical results.
InstructLab is an open-source project that facilitates contributions to Large Language Models (LLMs) by enabling community members to add 'skills' or 'knowledge' to existing models. InstructLab uses a model-agnostic technology to allow model creators to integrate new skills without retraining the entire model.
