Search Results for "context" - Page 27
Sort By:
Showing 785 open source projects for "context"
View related business solutions-
$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.
-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
1
Functionary
Chat language model that can use tools and interpret the results
...Function definitions are typically provided in JSON schema format, allowing the model to generate structured function calls compatible with modern tool-calling interfaces used in AI applications. Functionary can decide whether to execute tools sequentially or in parallel and can analyze the outputs of those tools to produce context-aware responses. This capability allows AI systems to interact with external services, APIs, or computation engines rather than relying solely on knowledge embedded in the model. -
2
elevenlabs-api
elevenlabs-api is an open source Java wrapper around the ElevenLabs
...Generate top-quality spoken audio in any voice and style with the most advanced and multipurpose AI speech tool out there. Our deep learning model renders human intonation and inflections with unprecedented fidelity and adjusts delivery based on context. -
3
Auto-Photoshop-StableDiffusion-Plugin
Plug-in that makes it easy to generate stable diffusion images
...With this plugin, users can generate new visuals from text prompts, use selectable areas for inpainting or outpainting, and adjust images using AI features while still leveraging traditional design tools such as brushes, filters, and adjustment layers. The integration dramatically reduces context switching between standalone AI tools and professional design software, empowering more efficient experimentation and iteration. -
4
RWKV
RNN with great LLM performance
...The project is built around the idea that a model can be trained in a parallelizable way like a GPT-style transformer while running inference with recurrent efficiency. This gives RWKV important advantages for long-context use, including lower memory pressure and no traditional key-value cache requirement. The repository includes training code, model notes, research material, and references to current RWKV weights. Its main value is providing the foundation for experimenting with efficient large language models that combine transformer-like scalability with RNN-like runtime behavior. -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
5
Feishu ChatGPT
Voice dialogue, role-playing, multi-topic discussion, picture creation
Feishu × (GPT-3.5 + DALL·E + Whisper) = flying-like work experience. Voice dialogue, role-playing, multi-topic discussion, picture creation, table analysis, document export. Golang language, it goes without saying! Master the gin framework proficiently, developing the backend is as natural as breathing! Familiar with the SDKs of DingTalk, Feishu, Qiwei and other platforms, and be able to develop and integrate a series of amazing functions! Proficient in platform-based detail thinking, let... -
6
gpu_poor
Calculate token/s & GPU memory requirement for any LLM
...The project focuses on calculating GPU memory requirements and predicted inference speed for different models, hardware configurations, and quantization strategies. By analyzing factors such as model size, context length, batch size, and GPU specifications, the system estimates how much VRAM will be required and how fast tokens can be generated during inference. The tool also provides a detailed breakdown of where GPU memory is allocated, including model weights, KV cache, activations, and other runtime overhead. This information allows developers to evaluate trade-offs between different quantization methods such as GGML, bitsandbytes, and QLoRA before attempting to deploy a model. gpu_poor is particularly useful for researchers and hobbyists. -
7
AutoGPT.js
Auto-GPT on the browser
AutoGPT.js is an open-source project that brings autonomous AI agent capabilities similar to AutoGPT directly into the browser environment. The system allows users to run an AI agent capable of performing tasks such as generating code, searching the web, and interacting with files on the local computer. Unlike traditional AutoGPT implementations that require server infrastructure, AutoGPT.js is designed to run primarily in the browser, making it easier to deploy and experiment with... -
8
ChatGPT Web
ChatGPT demo webpage built with Express and Vue3
ChatGPT demo webpage built with Express and Vue3. Supports dual models, providing two unofficial ChatGPT API methods. You should first use the API way. If the network is not available, it means that the country is blocked, and you need to build your own proxy. Never use other people's public proxy, it is dangerous. The reverse proxy will expose your access tokens to third parties when using the accessTokenthe method, and doing so should have no ill effects, but consider the risks before... -
9
HttpRunner
Testing framework that began with API and performance testing
HttpRunner is an open-source testing framework that began with API and performance testing and has evolved into a general, extensible test platform. The current major version is implemented in Go, with the legacy Python edition split to a separate repository; this shift emphasizes a single, fast, cross-platform runtime for modern pipelines. It provides declarative test cases, data-driven parametrization, and plugin mechanisms so teams can compose reusable steps and validations at scale.... -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
10
LLM Applications
A comprehensive guide to building RAG-based LLM applications
...It provides step-by-step guidance for constructing systems that ingest documents, split them into chunks, generate embeddings, index them in vector databases, and retrieve relevant context during inference. The repository also shows how these components can be scaled and deployed using distributed computing frameworks such as Ray. In addition to development workflows, the project includes notebooks, datasets, and evaluation tools that help developers experiment with different retrieval strategies and model configurations. -
11
ChatGPT UI
A ChatGPT web client that supports multiple users, and databases
A ChatGPT web client that supports multiple users, multiple database connections for persistent data storage, supports i18n. Provides Docker images and quick deployment scripts. Support gpt-4 model. You can select the model in the "Model Parameters" of the front-end. The GPT-4 model requires whitelist access from OpenAI. Added web search capability to generate more relevant and up-to-date answers from ChatGPT! This feature is off by default, you can turn it on in `Chat->Settings` in the... -
12
LLaMA
Inference code for Llama models
“Llama” is the repository from Meta (formerly Facebook/Meta Research) containing the inference code for LLaMA (Large Language Model Meta AI) models. It provides utilities to load pre-trained LLaMA model weights, run inference (text generation, chat, completions), and work with tokenizers. Tokenizer utilities, download scripts, shell helpers to fetch model weights with correct licensing/permissions. Includes example scripts for chat completions and text completions to show how to call the... -
13
D2L.ai
Interactive deep learning book with multi-framework code
...Adopted at 300 universities from 55 countries including Stanford, MIT, Harvard, and Cambridge. This open-source book represents our attempt to make deep learning approachable, teaching you the concepts, the context, and the code. The entire book is drafted in Jupyter notebooks, seamlessly integrating exposition figures, math, and interactive examples with self-contained code. Offers sufficient technical depth to provide a starting point on the path to actually becoming an applied machine learning scientist. -
14
GPT-Code UI
An open source implementation of OpenAI's ChatGPT Code interpreter
An open source implementation of OpenAI's ChatGPT Code interpreter. Simply ask the OpenAI model to do something and it will generate & execute the code for you. You can put a .env in the working directory to load the OPENAI_API_KEY environment variable. For Azure OpenAI Services, there are also other configurable variables like deployment name. See .env.azure-example for more information. Note that model selection on the UI is currently not supported for Azure OpenAI Services. -
15
mindflow
AI-powered CLI git wrapper, boilerplate code generator, chat history
...Interact with chatGPT directly just like on the chatGPT website. We also have chat persistence, so it will remember the previous chat messages. You can provide single or multi-file context to chatGPT by passing in any number of files as a separate argument in the mf chat call. -
16
ChatGPT-Vercel
Elegant and Powerfull. Powered by OpenAI and Vercel
...The application supports multiple independent conversations, each with its own title, icon, role settings, URL, and behavioral controls. Users can search prompt presets and message history with fuzzy matching, lock important messages, and manage which context is sent with later requests. It displays token use in real time and allows a response to be interrupted before additional tokens are consumed. Conversations and settings can be imported, exported, preserved locally, or converted into Markdown and shareable images. PWA support, URL-based queries, configurable actions, and responsive controls make it usable as both a personal chatbot and a lightweight search-style interface. -
17
DiT (Diffusion Transformers)
Official PyTorch Implementation of "Scalable Diffusion Models"
DiT (Diffusion Transformer) is a powerful architecture that applies transformer-based modeling directly to diffusion generative processes for high-quality image synthesis. Unlike CNN-based diffusion models, DiT represents the diffusion process in the latent space and processes image tokens through transformer blocks with learned positional encodings, offering scalability and superior sample quality. The model architecture parallels large language models but for image tokens—each block... -
18
RasaGPT
Headless Rasa chatbot platform with LLM integration and APIs
RasaGPT is a headless chatbot platform that combines Rasa with modern LLM tooling such as Langchain and LlamaIndex. It serves as a reference implementation and boilerplate for building conversational AI systems with retrieval and context injection. RasaGPT includes a FastAPI backend for creating custom bot endpoints, along with document ingestion and a training pipeline. It simplifies integration challenges between Rasa and LLM libraries, including metadata handling and library conflicts. RasaGPT supports multi-tenant deployments, session management, and custom schemas using pgvector. ... -
19
texturize
Generate photo-realistic textures based on source images
...Useful if you want to create variations on a theme or elaborate on an existing texture. A command-line tool and Python library to automatically generate new textures similar to a source image or photograph. It's useful in the context of computer graphics if you want to make variations on a theme or expand the size of an existing texture. This software is powered by deep learning technology, using a combination of convolution networks and example-based optimization to synthesize images. We're building texturize as the highest-quality open source library available! ... -
20
VALL-E
PyTorch implementation of VALL-E (Zero-Shot Text-To-Speech)
...During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that VALL-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find VALL-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis. -
21
Clarity AI
A Perplexity clone
Clarity AI is an AI-powered “search + chat” tool (similar in spirit to a simplified “AI-powered search engine / assistant”) created by Mckay Wrigley — intended to let users ask questions, get answers, and explore information via conversational interface rather than traditional search. The codebase (TypeScript) leverages LLMs / embeddings to process user queries, retrieve relevant data or context, and respond conversationally; this makes it useful as a personal knowledge assistant, research helper, or Q&A front end over arbitrary datasets or web-available info. Because Clarity AI is open-source, developers can adapt the backend or retrieval logic, integrate their own data sources (databases, documents, APIs), and build custom assistants or knowledge bots tailored to their needs. ... -
22
chatgpt HTML
PHP version calls the OpenAI interface for question and answer
...EventSource is used at the front end to support Markdown format analysis, and formula display, the code is colored. The UI on the page is concise and supports continuous conversations in the context. The source code has only a few files, no frame is used, all PHP versions are supported, all open source, and it is extremely easy to open. Nanny-level tutorials, all surrounding resources, welcome to communicate, everything is free. There is no requirement for the PHP version, no database is required. The core code has only a few files, and no frame is used. ... -
23
MAE (Masked Autoencoders)
PyTorch implementation of MAE
...It trains a Vision Transformer (ViT) by randomly masking a high percentage of image patches (typically 75%) and reconstructing the missing content from the remaining visible patches. This forces the model to learn semantic structure and global context without supervision. The encoder processes only the visible patches, while a lightweight decoder reconstructs the full image—making pretraining computationally efficient. After pretraining, the encoder serves as a powerful backbone for downstream tasks like image classification, segmentation, and detection, achieving top performance with minimal fine-tuning. ... -
24
Deeplearning.ai
Study notes, summaries, and auxiliary materials for deep learning
...By organizing the content as “books” or structured notes, it gives students a consistent reference to revisit as models and tooling evolve. Many learners use it to supplement course videos, reinforcing concepts before implementing assignments or projects. As a consolidated guide, it reduces context-switching and helps build a durable mental model of deep learning fundamentals. -
25
MTBook
Machine Translation: Foundations and Models
...This book is written in tex, and all source codes are open. This book is divided into four parts, each of which consists of several chapters. The order of the chapters refers to the time context of the development of machine translation technology, while taking into account the internal logic of the machine translation knowledge system.
