Explore how LocalStack serves as a drop-in replacement for AWS, allowing developers to test and develop AWS services locally.
LiteLLM is a library to deploy and manage LLM (Large Language Model) APIs using a standardized format. It supports multiple LLM providers, includes proxy server features for load balancing and cost tracking, and offers various integrations for logging and observability.
This page provides documentation for the rerank API, including endpoints, request parameters, and response formats.
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.
The article provides an overview of 12 essential Web APIs every developer should know, including Storage API, Payment Request API, DOM API, HTML Sanitizer API, Canvas API, History API, Clipboard API, Fullscreen API, FormData API, Fetch API, Drag and Drop API, and Geolocation API. Each API is explained with code examples.
TabbyAPI is a FastAPI based application that allows for generating text using an LLM (large language model) using the Exllamav2 backend. It supports various model types and features like HuggingFace model downloading, embedding model support, and more.
Airbyte, a data integration platform, has introduced a feature allowing AI to automatically create API connectors by reading documentation, enhancing its low-code/no-code capabilities and supporting the growing demand for robust data services to power AI initiatives in enterprises.
This article discusses the importance of API scalability for handling traffic spikes, improving user experience, and optimizing resource utilization. It covers key concepts, scaling strategies with code examples, and best practices for scaling the API layer.
High-performance deployment of the vLLM serving engine, optimized for serving large language models at scale.
A Fortune 50 CTO evaluates the pros and cons of OpenAPI and GraphQL API standards, and their relevance to data governance.
