OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Controllable Rag Agent

Controllable Rag Agent is an open-source Python implementation of a graph-guided retrieval-augmented generation agent that plans and coordinates tasks to answer complex questions from user-provided material.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Controllable Rag Agent — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use the repository when you want a code-based starting point for exploring graph-guided RAG on complex questions, or want to inspect how planning, retrieval, response generation, and evaluation are brought together.

Who it is for

  • Developers exploring agent-based retrieval-augmented generation.
  • Practitioners who want to study a planned, multi-step approach to answering questions over their own data.

Documented uses

  • Follow a notebook tutorial for a controllable RAG agent.
  • Inspect a workflow that chunks material, adds summaries and quotations, plans subtasks, retrieves and distills context, and generates an answer.
  • Launch a Streamlit visualization of agent activity.
  • Review documented Ragas evaluation measures, including answer correctness, faithfulness, relevance, recall, and similarity.
Before you choose

Requirements & limits

The public GitHub repository is licensed under Apache-2.0. The README documents local Python and Docker setup paths and requires an API key for an LLM provider.

  • The documented stack includes LangChain, FAISS, Streamlit, and Ragas.
  • The repository lists Python 3.8+ and API-key configuration as setup prerequisites.
  • The README describes both package-based and Docker-based setup, as well as a notebook tutorial and Streamlit visualization.

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 repository and open its tutorial

Prepare the documented Python environment and locate the project's step-by-step RAG tutorial.

Before you start

  • Python 3.8 or later
  • An API key for a supported LLM provider
  • Git and pip

Steps

  1. Clone the repository and change into its directory.

  2. Create a root-level .env file with the relevant provider key, using .env.example as a reference.

  3. Install the listed dependencies with pip install -r requirements.txt.

  4. Open sophisticated_rag_agent_harry_potter.ipynb to follow the tutorial.

Expected outcome

The repository is prepared for following its notebook tutorial with provider credentials configured.

Guide limitations

  • The README names OpenAI and Groq as example providers but describes flexible LLM integration; provider-specific configuration may differ.
  • These are repository instructions, not a report of an executed setup.
Documentation 1 ↗
Source-based practical guide

Launch the local agent visualization

Use the documented non-Docker command to start the Streamlit agent visualization.

Before you start

  • A cloned repository with dependencies installed
  • Python 3.8 or later
  • An API key configured in the root .env file

Steps

  1. From the repository directory, run streamlit run simulate_agent.py.

  2. Open the local address provided by Streamlit in a browser.

Expected outcome

The README's documented local visualization launch path is initiated.

Guide limitations

  • The README gives http://localhost:8501/ for its Docker route, not as a guaranteed address for the non-Docker route.
  • The launch instructions are documented steps, not independently verified execution.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

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
Controllable Rag AgentFollow a notebook tutorial for a controllable RAG agent.The public GitHub repository is licensed under Apache-2.0. The README documents local Python and Docker setup paths and requires an API key for an LLM provider.
Continuum — pouyahasanamrejiStore project lessons so coding agents can retrieve them across conversations.CLI, Self-hosted, ServerThe repository documents local Docker Compose and bare-metal development setups. Bare-metal startup requires Node 22.12.0 or later and pnpm 10.33 or later; the Compose path skips these host prerequisites.
Pro WorkflowTurn an agent correction into a searchable rule that can load in later sessions.CLI, Self-hostedThe project documents a native Claude Code plugin installation, a skills add route for other agents, and a manual installation route. Its repository is public.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
8 October 2026
Original website title
NirDiamant/Controllable-RAG-Agent · Official homepage title · retained in its source language
How we review sourcesSuggest a correction