AgentSearch

It lets you either batch index and search data stored in an SQL database, NoSQL storage, or just files quickly and easily — or index and search data on the fly, working with it pretty much as with a database server.

It is a framework built around LLMs. It can be used for chatbots, generative question-answering, summarization, and much more. The core idea of the library is that we can “chain” together different components to create more advanced use cases around LLMs.

It is an open-source library designed to help developers build conversational streaming user interfaces in JavaScript and TypeScript. The SDK supports React/Next.js, Svelte/SvelteKit, and Vue/Nuxt as well as Node.js, Serverless, and the Edge Runtime.

Search the world's information, including webpages, images, videos and more. Google has many special features to help you find exactly what you're looking for.

It uses the tools you use to make application building a snap. It is built on the battle-tested Apache Zookeeper, it makes it easy to scale up and down.

Lucene Core, our flagship sub-project, provides Java-based indexing and search technology, as well as spellchecking, hit highlighting and advanced analysis/tokenization capabilities.

It builds completely static HTML sites that you can host on GitHub pages, Amazon S3, or anywhere else you choose. There's a stack of good looking themes available. The built-in dev-server allows you to preview your documentation as you're writing it. It will even auto-reload and refresh your browser whenever you save your changes.

Build, train, and deploy state of the art models powered by the reference open source in machine learning.

It allows you to run open-source large language models, such as Llama 2, locally.

It is a project that provides a central interface to connect your LLMs with external data. It offers you a comprehensive toolset trading off cost and performance.

It is an open-source Vector Search Engine and Vector Database written in Rust. It deploys as an API service providing search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more.

It is an open-source embedding database. Chroma makes it easy to build LLM apps by making knowledge, facts, and skills pluggable for LLMs.

An open-source, high-performance, distributed SQL database built for resilience and scale. Re-uses the upper half of PostgreSQL to offer advanced RDBMS features, architected to be fully distributed like Google Spanner.

It is a Rust ecosystem of libraries for running inference on large language models, inspired by llama.cpp. On top of llm, there is a CLI application, llm-cli, which provides a convenient interface for running inference on supported models.

It is an open-source vector search engine. It allows you to store data objects and vector embeddings from your favorite ML-models, and scale seamlessly into billions of data objects.

It is an open-source, drag & drop UI to build your customized LLM flow. It is built on top of LangChainJS, with the aim to make it easy for people to visualize and build LLM apps.

Searchkick learns what your users are looking for. As more people search, it gets smarter and the results get better. It’s friendly for developers - and magical for your users.

It is the easiest way for customers to build and scale generative AI-based applications using FMs, democratizing access for all builders.

It is a library for building stateful, multi-actor applications with LLMs, built on top of (and intended to be used with) LangChain. It extends the LangChain Expression Language with the ability to coordinate multiple chains (or actors) across multiple steps of computation in a cyclic manner.

It is an easy to use desktop app for experimenting with local and open-source Large Language Models (LLMs). It supports any ggml Llama, MPT, and StarCoder model on Hugging Face (Llama 2, Orca, Vicuna, Nous Hermes, WizardCoder, MPT, etc.)

It aims to enable developers (and even non-developers) to quickly build useful applications based on large language models, ensuring they are visual, operable, and improvable.

It is a full-stack application and tool suite that enables you to turn any document, resource, or piece of content into a piece of data that any LLM can use as reference during chatting. This application runs with very minimal overhead as by default the LLM and vectorDB are hosted remotely, but can be swapped for local instances.

It is an open-source product analytics suite for LLM-based applications. Iterate faster on your application with a granular view of exact execution traces, quality, cost, and latency.

We help your website visitors find what they are looking for. AddSearch is a lightning fast, accurate and customizable site search engine with a Search API. AddSearch works on all devices and is easy to install, customize and tweak.

It organizes your search results into topics. With an instant overview of what's available, you will quickly find what you're looking for.

It is a C++ based full-text search engine including similarity ranking capabilities natively integrated into ArangoDB. It allows users to combine two information retrieval techniques: boolean and generalized ranking retrieval. Search results “approved” by the boolean model can be ranked by relevance to the respective query using the Vector Space Model in conjunction with BM25 or TFIDF weighting schemes.

It is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. AutoGen agents are customizable, conversable, and seamlessly allow human participation.

It is a platform for building production-grade LLM applications. It lets you debug, test, evaluate, and monitor chains and intelligent agents built on any LLM framework and seamlessly integrates with LangChain, the go-to open source framework for building with LLMs.

Haystack is an open source NLP framework to interact with your data using Transformer models and LLMs (GPT-4, ChatGPT, etc.). It offers production-ready tools to build NLP backend services, e.g., question answering or semantic search.

It is an SDK that integrates Large Language Models (LLMs) like OpenAI, Azure OpenAI, and Hugging Face with conventional programming languages like C#, Python, and Java. It achieves this by allowing you to define plugins that can be chained together in just a few lines of code.

It is the framework for solving advanced tasks with language models (LMs) and retrieval models (RMs). It unifies techniques for prompting and fine-tuning LMs — and approaches for reasoning, self-improvement, and augmentation with retrieval and tools.

It provides all you need to build and deploy computer vision models, from data annotation and organization tools to scalable deployment solutions that work across devices.

It is a chat interface that lets you interact with Ollama. It offers features such as code syntax highlighting, Markdown and LaTeX support, local RAG integration, and prompt preset support. It can be installed using Docker or Kubernetes.

It is an open-source monitoring & observability for AI apps and agents. It is designed to be usable with any model, not just OpenAI. It is easy to integrate and simple to self-host.

A fast, lightweight and schema-less search backend. It ingests search texts and identifier tuples that can then be queried against in microseconds.

It is a powerful generative large language model that is designed to improve search accuracy and provide personalized recommendations. It is capable of performing a range of generative AI tasks, including text summarization, and text generation, etc.

It is a search engine that does full text indexing. It is a lightweight alternative to Elasticsearch and runs in less than 100 MB of RAM. It uses bluge as the underlying indexing library. It is very simple and easy to operate as opposed to Elasticsearch which requires a couple dozen knobs to understand and tune.

It is an open platform for operating large language models (LLMs) in production. Fine-tune, serve, deploy, and monitor any LLMs with ease. Run inference with any open-source large-language models, deploy to the cloud or on-premise, and build powerful AI apps.

It enables LLMs to use tools by invoking APIs. Given a natural language query, it comes up with the semantically and syntactically correct API to invoke.

It is a lightning-fast inference platform that helps you serve your large language models (LLMs). Use a state-of-the-art, open-source model or fine-tune and deploy your own at no additional cost.

It is a tool that enables fast and efficient local LLM finetuning. It uses a manual autograd engine and Flash Attention v2 to achieve 2-5x speedup and 50% memory reduction compared to QLoRA, without compromising accuracy.

It is a light package to simplify calling OpenAI, Azure, Cohere, Anthropic, Huggingface API Endpoints. Manages input/output translation.

It is a framework to easily create LLM powered bots over any dataset. It abstracts the entire process of loading a dataset, chunking it, creating embeddings, and then storing it in a vector database.

It is a low code platform to rapidly annotate data, train and then deploy custom Natural Language Processing (NLP) models. It takes care of model training, data selection and deployment for you. You upload your data and we provide an annotation interface for you to teach a classifier. As you label we train a model, work out what data is most valuable and then deploy the model for you.

It is the easiest way to customize and serve LLMs. In LLM Engine, models can be accessed via Scale's hosted version or by using the Helm charts in the repository to run model inference and fine-tuning in your own infrastructure.

It is the interface between your app and hosted LLMs. It streamlines API requests to OpenAI, Anthropic, Mistral, LLama2, Anyscale, Google Gemini, and more with a unified API.

It is designed to provide a flexible framework to define and deploy large language model apps without having to write any execution code.

It is a Multi-agent Meta programming framework that assigns different roles to GPTs to form a collaborative software entity for complex tasks. It takes a one-line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc.

It is an embeddable super fast full text search engine. It can be embedded into MySQL. Mroonga is a storage engine that is based on it.

It is a general video interaction platform based on large language models. Build a chatbot for video understanding, processing, and generation.