Search

More Filters

Show More
Add Listing
Go Back

cognita

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Cognita is an open-source framework to organize, develop and productionize Retrieval-Augmented Generation (RAG) applications. It provides a modular codebase that separates parsers, loaders, embedders, retrievers, indexing jobs and an API server so teams can move from notebook prototypes to deployable services. Cognita includes a FastAPI backend, a frontend UI for no-code ingestion and querying, an LLM Gateway to proxy different model providers, and support for vector databases such as Qdrant and SingleStore. It supports local development via docker-compose and production deployment with Truefoundry, a metadata store backed by Prisma/Postgres, incremental indexing, and configurable model providers. The repo is intended for developers and teams building document search and Q&A systems who need a reusable, extensible RAG architecture and an optional UI for non-technical users.

Links

Stars
4186
App URL
https://github.com/truefoundry/cognita
Github Repository
https://github.com/truefoundry/cognita/blob/main/README.md

Categorization

App Details

Features
Cognita offers modular components and extensibility including custom dataloaders, parsers and vector DB adapters. It ships with an API-driven FastAPI server, an LLM Gateway to unify embeddings and LLM providers, and a metadata store using Prisma and Postgres. Operational features include incremental indexing, an asynchronous indexing job, support for SOTA open-source embedders and rerankers (mixedbread-ai), optional Ollama and Infinity Server integration, and profiles for conditional docker builds. UI features let users create data sources and collections, start ingestion and run queries without code. The project supports multimodal parsing (audio/video), pydantic v2, sample configurations for models, and the ability to register custom retrievers and query controllers.
Use Cases
Cognita helps teams convert experimental RAG workflows into scalable applications by providing reusable infrastructure for data ingestion, chunking, embedding and retrieval. It automates indexing with jobs that detect added, updated or deleted documents and embeds chunks into a vector DB to avoid redundant work. The FastAPI query service composes retrievers and LLM chains to return answers with referenced documents, and the UI enables non-technical users to upload data and run QnA. Integration with Truefoundry adds deployment, metrics and feedback hooks. Developers can customize parsers, embedders and vector stores, test locally with docker-compose, and deploy production-ready RAG apps while reusing a standard architecture.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*