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

Super Rag

Super Rag is a Python framework for building retrieval-augmented generation pipelines in AI applications. It provides a REST API for ingesting, querying and deleting documents, with configurable document chunking, encoding, vector-database connections, retrieval and reranking. Its interpreter mode supports computational question answering using E2B custom runtimes.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Super Rag — 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 Super Rag when an application needs document ingestion and retrieval exposed through a REST API, with configurable processing and vector-store settings. Consider interpreter mode when a question requires computation and an E2B runtime can be configured.

Who it is for

  • Developers building AI applications that answer questions from indexed documents.
  • Teams that need to configure document processing and connect a vector database.
  • Developers adding computational question answering through an E2B-backed interpreter.

Documented uses

  • Ingest files into a named vector index through a REST endpoint.
  • Configure document splitting and encoding for an application’s retrieval pipeline.
  • Query indexed documents and remove a document by URL.
  • Add an interpreter mode for computational questions.
Before you choose

Requirements & limits

The repository is public and licensed under MIT. The README describes a cloud API as free to use within reasonable limits; it does not specify those limits.

  • The documented framework is Python-based and includes a FastAPI-powered REST API.
  • The README lists Pinecone, Qdrant, Weaviate, Astra and PGVector; Chroma is labeled as coming soon.
  • Encoder options listed as supported are OpenAI, Cohere, HuggingFace and FastEmbed; Mistral and Anthropic are labeled as coming soon.
  • Interpreter mode uses E2B custom runtimes and requires either an E2B API key for cloud sandboxes or a self-managed runtime setup.
  • Self-hosted setup uses Poetry, environment variables configured from .env.example, and Uvicorn.

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 Super Rag server

Prepare the repository and start its documented development server.

Before you start

  • A Python environment with virtualenv or venv available.
  • The Super Rag repository and Poetry.
  • Environment variables to configure from .env.example.

Steps

  1. Clone the repository and change into the super-rag directory.

  2. Create and activate a virtual environment using virtualenv or python3 -m venv.

  3. Install dependencies with Poetry using poetry install.

  4. Rename .env.example to .env and set the required environment variables.

  5. Start the server with uvicorn main:app --reload.

Expected outcome

The README's documented Uvicorn server command is running the Super Rag application.

Guide limitations

  • The README does not enumerate the environment variables or their values.
  • This setup procedure does not demonstrate a successful API request or deployment.
Documentation 1 ↗
Source-based practical guide

Ingest and query documents through the REST API

Use the documented API stages to add files to a vector index and submit a document question.

Before you start

  • A running Super Rag API or access to its cloud API.
  • A document URL and an index name.
  • A configured supported vector database; the example uses Qdrant credentials and host.
  • Encoder settings appropriate to the chosen provider.

Steps

  1. Send a POST request to /api/v1/ingest with the file URL, vector database configuration and index name; document processor settings are optional in the example.

  2. Send a POST request to /api/v1/query with the question, matching vector database configuration and index name.

  3. Set interpreter_mode to true only when using computational question answering; the README identifies E2B custom runtimes for this mode.

Expected outcome

The documented workflow submits documents for indexing and then sends a question against that index through the REST API.

Guide limitations

  • The README provides example payloads but not a complete client command or sample response.
  • Interpreter mode additionally requires an E2B cloud API key or a self-managed E2B setup.
  • The cloud API is described as free within reasonable limits, which are not specified.
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
Super RagIngest files into a named vector index through a REST endpoint.Cloud, ServerThe repository is public and licensed under MIT. The README describes a cloud API as free to use within reasonable limits; it does not specify those limits.
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
15 October 2026
Original website title
superagent-ai/super-rag · Official homepage title · retained in its source language
How we review sourcesSuggest a correction