cognita
AI app builder
A modular framework for building production-ready AI applications with integrated data management and model deployment capabilities
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry
3k stars
33 watching
281 forks
Language: Python
last commit: about 1 month ago
Linked from 1 awesome list
agentaiapplicationdatadeep-learningfine-tuningframeworkgenerative-aillmllm-opsllmopsmachine-learningmlopsmodel-deploymentpythonragretrieval-augmented-generationtypescript
ethicalml/awesome-production-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
 infiniflow/ragflow | An RAG (Retrieval-Augmented Generation) engine based on deep document understanding to provide truthful question-answering capabilities. | 25,479 |
 sciphi-ai/r2r | An AI-powered retrieval system with multimodal content ingestion and hybrid search capabilities | 4,010 |
 weaviate/verba | An end-to-end chatbot application utilizing Retrieval-Augmented Generation (RAG) for querying and interacting with data | 6,489 |
 pathwaycom/llm-app | Provides pre-built AI application templates to integrate Large Language Models (LLMs) with various data sources for scalable RAG and enterprise search. | 7,426 |
 llmware-ai/llmware | A framework for building enterprise LLM-based applications using small, specialized models | 8,303 |
 pipedreamhq/pipedream | An integration platform that enables developers to automate workflows across multiple applications and services using pre-built components and custom code | 9,075 |
 adithya-s-k/omniparse | A platform for ingesting and processing unstructured data from various sources to generate structured, actionable data optimized for AI applications. | 5,813 |
 neuml/txtai | An all-in-one embeddings database for semantic search, LLM orchestration and language model workflows | 9,709 |
 towhee-io/towhee | A framework for building efficient neural data processing pipelines using large language models and state-of-the-art deep learning models. | 3,255 |
 gothinkster/realworld | A demo application platform allowing users to create and showcase their own implementations of a full-stack web app using various frontend and backend technologies. | 80,838 |
 scisharp/llamasharp | An efficient C#/.NET library for running Large Language Models (LLMs) on local devices | 2,750 |
 whyhow-ai/rule-based-retrieval | A Python package that enables the creation and management of Retrieval Augmented Generation applications with filtering capabilities. | 229 |
 explodinggradients/ragas | A toolkit for evaluating and optimizing Large Language Model applications with objective metrics, test data generation, and seamless integrations. | 7,598 |
 deepset-ai/haystack | An AI orchestration framework to build customizable LLM applications with advanced retrieval methods. | 18,094 |
 ml-tooling/opyrator | Automates conversion of machine learning code into production-ready microservices with web API and GUI. | 3,116 |