Search Results for "extraction" - Page 2
Sort By:
Showing 142 open source projects for "extraction"
View related business solutions-
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
1
Prompt Engineering Interactive Tutorial
Anthropic's Interactive Prompt Engineering Tutorial
...The course leans heavily on realistic failure modes (ambiguity, hallucination, brittle instructions) and shows how to iteratively debug prompts the way you would debug code. Lessons include building prompts from scratch for common tasks like extraction, classification, transformation, and step-by-step reasoning, with checkpoints that let you compare your outputs against solid baselines. You’ll also practice advanced patterns such as tool use, constrained generation, and response validation so outputs are trustworthy and machine-consumable. -
2
ANTLR
Parser generator to read, process, or translate structured text
...Twitter search uses ANTLR for query parsing, with over 2 billion queries a day. The languages for Hive and Pig, the data warehouse and analysis systems for Hadoop, both use ANTLR. Lex Machina uses ANTLR for information extraction from legal texts. Oracle uses ANTLR within SQL Developer IDE and their migration tools. NetBeans IDE parses C++ with ANTLR. The HQL language in the Hibernate object-relational mapping framework is built with ANTLR. -
3
Passmark
The open-source Playwright library for AI browser regression testing
The Passmark project is an open-source AI-powered regression testing framework built on top of Playwright that enables developers to write end-to-end browser tests using natural language instead of traditional scripting. It is designed to simplify and accelerate testing workflows by allowing AI models to interpret human-readable instructions and translate them into executable browser actions. One of its defining features is a cache-first execution model, where AI is used initially to... -
4
RAG Anything
RAG-Anything: All-in-One RAG Framework
RAG-Anything is an open-source unified framework that extends the Retrieval-Augmented Generation (RAG) paradigm to fully multimodal document and knowledge retrieval, enabling systems to ingest, parse, represent, and query rich content that includes text, images, tables, formulas, and other structured or visual elements. Traditional RAG systems are typically limited to text and cannot effectively work across heterogeneous document layouts, but RAG-Anything addresses this by modeling... -
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
5
PromptingTools.jl
Streamline your life using PromptingTools.jl
...It focuses on reducing the complexity of prompt creation by introducing templating systems, macros, and reusable functions that standardize how prompts are constructed and executed. The library provides a family of ai* functions that handle tasks such as generation, embeddings, classification, and data extraction, all following a consistent structure. It supports multiple backends, including OpenAI-compatible APIs and local models such as those served through Ollama, allowing users to switch providers without rewriting prompts. The toolkit also includes advanced capabilities such as asynchronous execution, routing, OCR, and experimental agent workflows, making it suitable for both simple and complex AI applications. -
6
Integrant
Micro-framework for data-driven architecture
Integrant is a minimalistic micro-framework for building applications following a data-driven architecture. It lets you define system components declaratively as configuration data and handles lifecycle actions (init, halt, resume) in dependency order, serving as a modern alternative to Component or Mount. Integrant was built as a reaction to fix some perceived weaknesses with Component. In Component, systems are created programmatically. Constructor functions are used to build records,... -
7
WebMagic
A scalable web crawler framework for Java
WebMagic is a scalable crawler framework. It covers the whole lifecycle of crawler, downloading, url management, content extraction and persistent. It can simplify the development of a specific crawler. WebMagic is a simple but scalable crawler framework. You can develop a crawler easily based on it. WebMagic has a simple core with high flexibility, a simple API for html extracting. It also provides annotation with POJO to customize a crawler, and no configuration is needed. -
8
KodExplorer
A web based file manager, web IDE / browser based code editor
...Selectable files & folders support (mouse click & Ctrl & Shift & words & Keyboard shortcuts). Background file upload with Drag & Drop HTML5 support; Folder upload with Chrome, Firefox and Edge. Direct extraction to the current working directory. -
9
h265web.js
A HEVC/H.265 Web Player
h265web.js is a WebAssembly-powered video decoding library designed to enable playback and processing of H.265/HEVC video streams directly in web browsers without relying on native browser codec support. It provides a low-level decoding API that allows developers to build custom video players capable of handling raw H.265 streams, which are typically not widely supported natively in browsers. The project includes components for parsing H.265 bitstreams into NAL units and decoding them into... -
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
10
Gooo
Toolkit for developing web applications in Vue, Templ, and Go
...The project emphasizes simplicity and flexibility, enabling users to integrate its components into scripts or larger systems. While not as feature-heavy as enterprise frameworks, it serves as a foundation for experimentation and rapid prototyping in data extraction or automation tasks. Its design reflects a developer-centric approach, prioritizing extensibility and ease of modification over polished interfaces. -
11
Scalatra
Tiny Scala high-performance, async web framework
Scalatra is a lightweight, high-performance micro web framework written in Scala, inspired by the Ruby framework Sinatra. Its goal is to provide a minimal but expressive foundation for building web applications or REST APIs in Scala without the verbosity or steep learning curve of larger frameworks. It supports asynchronous request handling, routing, filters, content negotiation, and easy integration with templating, JSON libraries, and other web middleware. Being unopinionated, it lets... -
12
OSRFramework
OSRFramework, the Open Sources Research Framework is a AGPLv3+ project
...They include references to a bunch of different applications related to username checking, DNS lookups, information leaks research, deep web search, regular expressions extraction and many others. At the same time, by means of ad-hoc Maltego transforms, OSRFramework provides a way of making these queries graphically as well as several interfaces to interact with like OSRFConsole or a Web interface. If everything went correctly (we hope so!), it's time for trying usufy., mailfy and so on. But where are they locally? ... -
13
Figma Code Connect
A tool for connecting your design system components
Figma Code Connect is an open-source tool that enhances collaboration between designers and developers by synchronizing design components with source code in real time. Instead of treating design files and codebases as separate artifacts, it creates a continuous link so when a designer updates a UI element in Figma, developers see corresponding code changes or annotations immediately, making handoffs more precise and frictionless. The system supports multiple frameworks and languages,... -
14
LangExtract
A Python library for extracting structured information
...LangExtract supports a wide range of models, including Google Gemini, OpenAI GPT, and local LLMs via Ollama, making it adaptable to different deployment environments and compliance needs. The system excels at handling long documents using optimized chunking, multi-pass extraction, and parallel processing to ensure both high recall and structured consistency. -
15
react-docgen
A CLI and toolbox to extract information from React component files
react-docgen is a CLI and toolbox to help extracting information from React components, and generate documentation from it. It uses @babel/parser to parse the source into an AST and provides methods to process this AST to extract the desired information. The output / return value is a JSON blob / JavaScript object. It provides a default implementation for React components defined via React.createClass, ES2015 class definitions or functions (stateless components). These component definitions... -
16
ffsend
Easily and securely share files from the command line
Easily and securely share files and directories from the command line through a safe, private and encrypted link using a single simple command. Files are shared using the Send service and may be up to 1GB. Others are able to download these files with this tool, or through their web browser. All files are always encrypted on the client, and secrets are never shared with the remote host. An optional password may be specified, and a default file lifetime of 1 (up to 20) download or 24 hours is... -
17
Down
Streaming downloads using Net::HTTP, http.rb or HTTPX
Down is a small, reliable Ruby library for downloading files that favors correctness, streaming, and clear error handling. It follows redirects safely, supports timeouts and retries, and streams responses to disk to keep memory usage low—ideal for large downloads or server environments. The API returns file-like objects (often Tempfile) with helpful metadata such as original filename and content type, which plays nicely with file-attachment libraries and background jobs. Multiple HTTP... -
18
txtai
Build AI-powered semantic search applications
...Innovation is happening at a rapid pace, models can understand concepts in documents, audio, images and more. Machine-learning pipelines to run extractive question-answering, zero-shot labeling, transcription, translation, summarization and text extraction. Cloud-native architecture that scales out with container orchestration systems (e.g. Kubernetes). Applications range from similarity search to complex NLP-driven data extractions to generate structured databases. The following applications are powered by txtai. -
19
Web data extraction (web data mining, web scraping) tool. It leverages well proved XML and text processing techologies in order to easely extract useful data from arbitrary web pages.
-
20
Patch-NetVLAD
Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition
This repository contains code for the CVPR2021 paper "Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition". -
21
SecurePose
Automated Face Blurring, Kinematics Extraction and Leg dystonia Dx
...This validation establishes its effectiveness and usability in clinically recorded gait videos for face blurring and kinematics extraction. For installation, https://www.rishabh-bajpai.com/secureposeinstallation Tutorial Videos https://www.youtube.com/playlist?list=PLO4_jCYO5Ib23MoBpn-Wpj1_b6DAYlDwk Please cite the paper: https://arxiv.org/abs/2402.14143 -
22
OmniPull
Just pull anything
OmniPull is a powerful, cross-platform download manager built with Python and PySide6. It provides a modern, intuitive interface for managing downloads with advanced features like multi-threading, queue management, and media extraction. -
23
java-pdf-table-extractor-lib
Java Pdf Table extraction library
The command line application is an example of usage of the Java library. The library is based on pdfbox library and works by looking for the layout of each selected pdf page, and looking for table structure patterns. After calling the library (passing the pdf filename, and the page range), the result is a List<PdfTextElement>. PdfTextElement is an interface that has two implementations. * A basic text (outside the tables) * And PdfTextTabulaElement, for table structures. That... -
24
anti-copy-paster
A plugin for IntelliJ IDEA for just-in-time code duplicates extraction
The plugin monitors the copying and pasting that takes place inside the IDE. As soon as a code fragment is pasted, the plugin checks if it introduces code duplication, and if it does, the plugin calculates a set of code metrics for it, and these metrics are compared against the currently selected metrics thresholds. If the chosen thresholds are surpassed, the plugin suggests the developer to perform the Extract Method refactoring and applies the refactoring if necessary. -
25
[ARCHIVAL] The central forum for the MWE community. Share your open-source data sets and MWE extraction tools, exchange ideas on evaluation strategies and further development of the tools, and discuss theoretical definitions and linguistic properties of MWEs.
