OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Onerag

Onerag is an open-source Python and FastAPI framework for building retrieval-augmented generation backends. It connects retrieval providers and language models through configuration, offers a Docker-based API server and a local command-line chatbot, and documents an OpenAI-compatible chat API.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Onerag — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Onerag when you need a Python-based RAG service with configurable retrieval and model providers, or want to explore a local chatbot workflow before integrating an API.

Who it is for

  • Developers building retrieval-grounded chatbots or knowledge-base assistants.
  • Teams integrating a RAG service with software that uses the OpenAI SDK.
  • Developers evaluating a local CLI workflow before building an API-backed application.

Documented uses

  • Assemble a RAG backend using a selected vector database and language-model provider.
  • Start a terminal chatbot over the included sample data.
  • Expose RAG chat through an OpenAI-compatible API.
  • Configure retrieval, reranking, caching, and query-routing components.
Before you choose

Requirements & limits

The repository identifies the project as open source under the MIT license. The README documents Python 3.11 or later and provides both a Docker-based API setup and a CLI setup that does not require Docker.

  • The full API quickstart uses Docker and documents Weaviate; the local CLI path uses ChromaDB and does not require Docker.
  • The quickstart API configuration calls for a Google API key, while the CLI supports provider options including Google, OpenRouter, and Ollama.
  • The README describes an OpenAI-compatible chat-completions endpoint and a models endpoint.
  • Provider selection and additional components are configured through environment variables or YAML.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the Docker-based API server

Install Onerag and start its documented full API quickstart.

Before you start

  • Python 3.11 or later
  • uv
  • Docker
  • A Google API key for the quickstart configuration

Steps

  1. Clone the Onerag repository and change into its directory.

  2. Run the command below to install project dependencies.

    Documented command
    uv sync

  3. Copy quickstart/.env.quickstart to .env and set GOOGLE_API_KEY.

  4. Run the command below.

    Documented command
    make start

Expected outcome

The quickstart is documented to provide a FastAPI server with Weaviate and Swagger UI at `http://localhost:8000/docs`.

Guide limitations

  • This describes the repository's setup instructions, not an independently tested deployment.
  • The quickstart configuration requires a Google API key.
Documentation 1 ↗
Source-based practical guide

Set up the local CLI chatbot

Install Onerag and start its documented terminal chatbot without Docker.

Before you start

  • Python 3.11 or later
  • uv
  • A configured answer-generation provider, such as a Google or OpenRouter API key, or an Ollama model

Steps

  1. Clone the Onerag repository and change into its directory.

  2. Run the command below.

    Documented command
    uv sync

  3. Run the command below.

    Documented command
    make easy-start

Expected outcome

The README describes a terminal chatbot using ChromaDB, with 25 sample items loaded automatically and hybrid search enabled.

Guide limitations

  • AI answer generation requires a configured provider; the documented local-model option uses Ollama.
  • The sample-data loader does not delete an existing collection by default.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
OneragAssemble a RAG backend using a selected vector database and language-model provider.CLI, Docker, Linux, Self-hostedThe repository identifies the project as open source under the MIT license. The README documents Python 3.11 or later and provides both a Docker-based API setup and a CLI setup that does not require Docker.
LangsearchCrawl website or local data for a knowledge base.CLI, Self-hosted, Server
Hybrid Search RagCombine document retrieval and language-model generation in a configurable workflow.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
notadev-iamaura/OneRAG · Official homepage title · retained in its source language
How we review sourcesSuggest a correction