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

Rag Langchain AI System

Rag Langchain AI System is an open-source web application for portfolio question answering. It combines document retrieval and LangChain orchestration with structured portfolio data APIs, and presents chat responses with source cards and tool traces.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rag Langchain AI System — 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 building or evaluating a portfolio-focused assistant that needs document retrieval alongside structured portfolio API lookups, rather than chat over documents alone.

Who it is for

  • Developers building a portfolio research assistant grounded in both documents and structured data.
  • Operators who want to run or adapt a multi-service application with a React chat frontend, a Flask RAG service and an Express/MongoDB backend.

Documented uses

  • Ask questions against indexed portfolio documents and retrieve relevant evidence.
  • Enrich answers by chaining to structured team, investment, sector or consultation data APIs.
  • Manage chat sessions and inspect response sources and tool traces.
Before you choose

Requirements & limits

The repository is public and specifies an MIT license. The README documents local Docker Compose endpoints and manual local setup.

  • The application has separate frontend, RAG-service and backend components, so local operation involves coordinating a multi-service stack.
  • Its retrieval layer combines Chroma vector retrieval and BM25 lexical retrieval, with optional cross-encoder reranking.
  • Portfolio API linkage is configurable, and the backend uses MongoDB; runtime settings include API connection details and authentication controls.
  • The repository lists Docker, Kubernetes and Terraform assets for deployment and operations.

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

Start the application with Docker Compose

Bring up the documented local application stack and check its listed service endpoints.

Before you start

  • The repository and its Docker Compose configuration.
  • Docker Compose.

Steps

  1. From the repository, run the command below.

    Documented command
    docker compose up -d

  2. Run the command below to inspect the Compose services.

    Documented command
    docker compose ps

  3. Use the documented local endpoints: frontend at http://localhost:3000, RAG API at http://localhost:5000, and backend docs at http://localhost:3456/docs.

  4. When finished, run the command below.

    Documented command
    docker compose down

Expected outcome

The Compose-defined stack is started, with the project listing local frontend, RAG API and backend documentation endpoints.

Guide limitations

  • The guide reflects the README's instructions; it does not verify that services start successfully in a particular environment.
  • The project separately documents runtime configuration for database connection, API linkage and optional gateway authentication.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
hoangsonww/RAG-LangChain-AI-System · Official homepage title · retained in its source language
How we review sourcesSuggest a correction