Search Results for "text generation"
Sort By:
Showing 65 open source projects for "text generation"
View related business solutions-
Veeam Data Platform v13.1 - Get Your Free TrialTry Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
1
PdfPig
Read and extract text and other content from PDFs in C#
This project allows users to read and extract text and other content from PDF files. In addition the library can be used to create simple PDF documents containing text and geometrical shapes. -
2
Cookbook (Google Gemini)
Examples and guides for using the Gemini API
...It provides a structured learning path with quick-start tutorials for beginners and practical examples for advanced users. The repository covers a wide range of Gemini capabilities, including text, images, video, speech, robotics, and multimodal interactions. It highlights newly introduced features such as Gemini 2.5 models (Flash and Pro), Gemini’s native image generation, Veo for video generation, robotics-focused reasoning models, and Lyria for TTS and music generation. The Cookbook also includes tutorials on advanced API workflows such as grounding answers with external tools, batch-mode request handling, and live multimodal interactivity with LiveAPI. ... -
3
LLPhant
A comprehensive PHP Generative AI Framework
...The framework focuses on usability by offering straightforward APIs for tasks like embeddings, question answering, and vector search, which are commonly required in real-world applications. It includes support for vector stores, enabling developers to build retrieval-augmented generation systems using structured or unstructured data. LLPhant also allows integration with external services and tools, making it possible to extend model capabilities beyond text generation into actionable workflows. -
4
rollama
Wrap the Ollama API, which allows you to run different LLMs
rollama is an R package that provides a convenient interface for interacting with local large language models through the Ollama API, bringing modern AI capabilities into the R ecosystem. It is designed to make LLM usage accessible to data scientists and researchers who work primarily in R, allowing them to generate text, analyze data, and create embeddings without relying on external cloud services. The package emphasizes reproducibility and privacy by enabling local execution of models, which is especially valuable for sensitive or research-oriented workflows. It supports common LLM tasks such as text generation, annotation, and embedding creation, making it useful for tasks like document analysis and data labeling. ... -
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
5
Ollama Swift Client
A Swift client library for interacting with Ollama
...It is designed to feel natural within the Swift ecosystem, using modern language features like async/await and strong typing to provide a clean and intuitive developer experience. The library wraps the Ollama REST API into structured Swift calls, making it easy to perform tasks such as chat completion, text generation, and embeddings without dealing with raw HTTP requests. It supports streaming responses, allowing applications to display generated content progressively, which is especially useful for chat interfaces. The project emphasizes simplicity and integration with native app development, making it ideal for building AI-powered mobile or desktop applications that leverage local models. -
6
Ollama-Laravel Package
Ollama-Laravel is a Laravel package providing seamless integration
...It abstracts the Ollama API into a developer-friendly facade, allowing Laravel developers to interact with models using familiar patterns such as service containers, configuration files, and fluent method chaining. The package supports a wide range of AI capabilities including text generation, chat-based interactions, embeddings, and multimodal vision analysis, making it suitable for both simple features and complex AI-driven systems. It also includes support for reasoning models and function calling, enabling developers to build more advanced workflows where models can trigger tools or structured actions. Real-time streaming responses are supported, allowing applications to deliver incremental outputs for better user experience. -
7
Ollama-rs
A simple and easy-to-use library for interacting with the Ollama API
...It follows the official Ollama API closely, ensuring compatibility while offering an idiomatic Rust experience with strong typing and asynchronous execution. The library supports a wide range of operations, including text generation, chat interactions, embeddings, and model management, making it suitable for both simple applications and more advanced AI workflows. It includes streaming capabilities for real-time output, allowing developers to process responses incrementally rather than waiting for full completions. The project also introduces support for tool calling and custom function integration, enabling more dynamic and agent-like behavior within applications. -
8
xhtml2pdf
A library for converting HTML into PDFs using ReportLab
xhtml2pdf enables users to generate PDF documents from HTML content easily and with automated flow control such as pagination and keeping text together. The Python module can be used in any Python environment, including Django. The Command line tool is a stand-alone program that can be executed from the command line. -
9
Jianying Headless
Native Jianying drafts, isolated editing/export
Jianying Headless is a local automation toolkit for creating and editing Jianying Pro video projects on macOS. Structured editing plans can generate editable drafts with multiple video, audio, text, and overlay tracks. Existing projects can be modified inside isolated copies so the original draft is not overwritten. The system supports local media, fonts, keyframes, selected masks, transitions, and native MP4 export through an installed Jianying engine. A Python command-line interface and... -
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
10
Asciidoctor PDF
Asciidoctor PDF: A native PDF converter for AsciiDoc
A fast text processor & publishing toolchain for converting AsciiDoc to HTML5, DocBook & more. Asciidoctor is a fast, open source, Ruby-based text processor for parsing AsciiDoc® into a document model and converting it to output formats such as HTML 5, DocBook 5, manual pages, PDF, EPUB 3, and other formats. Asciidoctor also has an ecosystem of extensions, converters, build plugins, and tools to help you author and publish content written in AsciiDoc. -
11
unipdf
Golang PDF library for creating and processing PDF files (pure go)
UniDoc UniPDF is a PDF library for Go (golang) with capabilities for creating and reading, processing PDF files. The library is written and supported by FoxyUtils.com, where the library is used to power many of its services. Every release of our libraries is automatically tested against known vulnerabilities and do not pass unless everything is remediated. All changes are carefully reviewed by our team. -
12
MIME Component
Allows manipulating MIME messages
...It is commonly used for handling email content and attachments in Symfony applications. The component supports building complex email structures, including multi-part messages, and correctly encoding text and binary data. Mime is an essential part of Symfony Mailer but can be utilized independently to handle MIME message generation. -
13
baoyu-skills
Skills shared by Baoyu for improving daily work efficiency with Claude
baoyu-skills is a comprehensive plugin-based toolkit designed to enhance productivity within AI-assisted development environments, particularly Claude Code, by providing a wide range of modular “skills” for content generation, automation, and data processing. The project organizes its functionality into categories such as content creation, AI generation, and utility tools, enabling users to extend their workflows through reusable components. Each skill is implemented as a structured module with its own configuration, scripts, and execution logic, allowing for flexible customization and extension. ... -
14
ollama-hpp
Modern, Header-only C++ bindings for the Ollama API
...It is designed with performance and portability in mind, making it suitable for systems where low-level control and minimal overhead are important. The library exposes core Ollama functionality such as text generation and chat through a C++-friendly API, allowing developers to integrate local LLM capabilities into desktop, embedded, or high-performance applications. It includes support for streaming responses, enabling applications to process output as it is generated rather than waiting for full completions. The project also evolves alongside the Ollama API, adding support for newer features such as blob handling and improved model interaction capabilities. ... -
15
Ollama4j
A simple Java library for interacting with Ollama server
...It provides a clean and developer-friendly API that abstracts the underlying REST communication, allowing users to focus on building features rather than handling low-level networking details. The library supports a wide range of core capabilities, including chat-based interactions, text generation, embeddings, and model management, making it suitable for both simple applications and more advanced AI-driven systems. It integrates seamlessly into Java ecosystems through Maven or Gradle dependencies, and it works with standard Java environments starting from JDK 11 and above. Ollama4j also includes support for advanced features such as tool or function calling, enabling models to interact with external systems and execute more complex workflows. -
16
Claude Cookbooks
A collection of notebooks/recipes showcasing ways of using Claude
...It serves as both a learning resource and a reference library, helping developers understand how to apply AI capabilities such as classification, summarization, and retrieval-augmented generation in real-world scenarios. The repository includes structured examples for integrating Claude with external tools, databases, and APIs, showcasing how to extend its functionality beyond basic text generation. It also covers advanced techniques like sub-agent orchestration, prompt optimization, and automated evaluation workflows. ... -
17
HummusJS
Node.js module for high performance creation and modification of PDFs
PDFWriter latest release (4.5.12) includes support for fonts that contain Emojis. Notable examples for Emoji fonts are Windows Segoe UI emoji and Google Noto font. This means that writing text that include emojis will result in lovely colorful emojis, rather than black and white representations. PDFHummus is a fast and free PDF Writing, Parsing and Modification library. -
18
MIT License
Hosted MIT License with details controlled through this repo
...This repository offers an easy way to copy the license text, understand its legal language, and see example usage in a context that is separate from any specific software project. It can also be useful for automated tooling and templates where a standard license file is needed across multiple repositories or as part of a code generation process. While not a software library or application, the repository serves an important role in open-source governance by centralizing a commonly adopted license with clear formatting. -
19
borb
borb is a library for reading, creating and manipulating PDF files
borb is a library for creating and manipulating PDF files in python. borb is a pure python library to read, write, and manipulate PDF documents. It represents a PDF document as a JSON-like data structure of nested lists, dictionaries and primitives (numbers, string, booleans, etc) This is currently a one-man project, so the focus will always be to support those use-cases that are more common in favor of those that are rare. -
20
xAI Python SDK
The official Python SDK for the xAI API
xAI Python SDK is the official Python library for building applications with xAI’s APIs. It is a gRPC-based SDK designed for Python 3.10 and above, with both synchronous and asynchronous clients for different application styles. Developers can use it to generate text, images, videos, and structured outputs through xAI’s model services. The package is built for direct integration into Python projects, making it useful for backend apps, automation scripts, AI tools, research prototypes, and... -
21
GPT-Image2-Skill
GPT Image 2 prompt gallery, image prompt library, agentic skill
GPT-Image2-Skill is a prompt gallery, image prompt library, agent skill, and CLI for OpenAI image generation and editing workflows. It collects curated prompt examples with generated outputs so users can reuse strong visual patterns instead of starting from scratch. The project includes categories such as anime, gaming, cyberpunk, animation, character design, typography, illustration, watercolor, ink, pixel art, isometric scenes, product visuals, and food imagery. It can be installed as an... -
22
PageIndex
Document Index for Vectorless, Reasoning-based RAG
PageIndex is an innovative open-source framework that reimagines retrieval-augmented generation (RAG) by eliminating conventional vector similarity search and instead building hierarchical semantic indexes that mirror a document’s natural structure. Rather than chunking text and embedding it into a vector database, PageIndex constructs a tree-structured index — similar to a detailed, AI-enhanced table of contents — that a large language model can traverse to locate the most relevant sections of long documents. ... -
23
VGGT-Ω
[CVPR 2026 Oral] VGGT Omega
VGGT-Omega is a Facebook Research computer vision project for feed-forward camera and depth reconstruction. It takes images as input and predicts camera parameters, depth maps, confidence values, and related scene tokens. The project is associated with 3D understanding workflows where models infer scene geometry without a traditional multi-stage reconstruction pipeline. It includes pretrained model variants with different resolutions and text-alignment capabilities, though checkpoint access... -
24
magic-string
Manipulate strings like a wizard
magic-string is a small JavaScript utility for editing strings while preserving accurate source maps. It is designed for compilers, bundlers, preprocessors, and code transformation tools that need to rewrite source code safely. The library lets developers overwrite, append, prepend, remove, move, and slice sections of text without losing track of where transformed content came from. This makes it especially useful when generated output still needs to map back to the original source for... -
25
patent-disclosure-skill
Point excavation and submission book
Patent Disclosure Skill is an Agent Skills package for creating and interpreting Chinese patent materials. In disclosure mode, it scans project documents, code, or a technical topic to identify candidate invention points. It can perform prior-art searching, organize technical comparisons, generate diagrams, and produce editable Markdown and Word disclosure documents. Existing disclosures can be revised through versioned updates with correction tracking. A separate reading mode turns patent...
