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

Aml Multiagent Rag

Aml Multiagent Rag is a Python-based, self-hosted retrieval-augmented generation application that processes regulatory PDFs into a Qdrant vector database and uses AI agents to answer AML/CFT compliance questions with quality validation and consistency checking.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Aml Multiagent Rag — 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 it when you want to build or run a local document-grounded AML/CFT question-answering workflow from regulatory PDFs and can supply the required OpenAI credentials and Docker-based Qdrant service.

Who it is for

  • Compliance researchers seeking to query a collection of AML/CFT regulatory documents.
  • Developers building or adapting document-grounded compliance question-answering applications.

Documented uses

  • Ingest PDF regulations, extract and chunk their text, and build a searchable vector collection.
  • Ask AML/CFT questions against retrieved regulatory material.
  • Review generated responses through quality validation and consistency checking.
Before you choose

Requirements & limits

The repository is public and specifies the MIT license. The documented setup is self-hosted and requires Python 3.11 or later, Docker Desktop and an OpenAI API key.

  • The README documents PDF ingestion and language detection for English and Portuguese; it does not describe ingestion of other file formats.
  • The listed workflow depends on an OpenAI API key and a Docker-run Qdrant database.
  • The stack includes FastAPI for the backend and Streamlit for the chat interface; the README also lists API documentation and a Qdrant dashboard at local addresses.
  • The README names regulatory examples from the United States, EU and Brazil, so suitability depends on the documents and jurisdictional coverage relevant to the intended use.
  • The repository describes source-grounded answers and validation checks, but does not remove the need to assess responses against applicable source documents.

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 local document-questioning application

Prepare the documented Qdrant database and launch the ingestion pipeline, API and Streamlit interface.

Before you start

  • Python 3.11 or later
  • Docker Desktop
  • OpenAI API key
  • uv package manager

Steps

  1. Clone the repository and enter its directory; install dependencies with uv sync.

  2. Add the OpenAI API key to a .env file copied from .env.example.

  3. Start Qdrant in Docker, with its storage mounted to the project directory.

  4. Run the PDF processor, text splitter, OpenAI embeddings and Qdrant client modules in order.

  5. Start the FastAPI server and then launch streamlit_app.py in another terminal.

Expected outcome

The README lists a Streamlit chat interface at localhost:8501, API documentation at localhost:8000/docs and a Qdrant dashboard at localhost:6333/dashboard.

Guide limitations

  • The documented ingestion flow processes PDF documents placed in the raw-documents collection; the guide does not establish behavior for other formats.
  • An OpenAI API key is required for embeddings and language models.
  • The listed commands and outcomes describe the repository instructions, not independently verified execution.
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
Aml Multiagent RagIngest PDF regulations, extract and chunk their text, and build a searchable vector collection.Docker, Self-hostedThe repository is public and specifies the MIT license. The documented setup is self-hosted and requires Python 3.11 or later, Docker Desktop and an OpenAI API key.
VectaurantFind menu options by describing preferences, such as asking what is vegan or spicy.CLI, Docker, Linux, macOS
MindgeniusaiAsk questions across one or more attached PDFs using retrieval.Docker, Self-hosted, WebThe repository offers a live demo that requires visitors to bring their own API key. Local development requires Node.js 20 or later and pnpm; the README also documents a Docker image. The repository identifies the license as BSL 1.1.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
luuisotorres/AML-MultiAgent-RAG · Official homepage title · retained in its source language
How we review sourcesSuggest a correction