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

Rag Boilerplate

Rag Boilerplate is an open-source Python RAG starter project that ingests and chunks documents, retrieves results through Qdrant BM25 and dense hybrid search, and uses LLM reranking and query enhancement with a CrewAI conversation agent to support chat with data.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rag Boilerplate — 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 it as a starting point when you want to inspect or adapt a Python RAG system that connects document ingestion, hybrid retrieval, conversational chat and retrieval evaluation.

Who it is for

  • Python developers building a question-answering chat interface for an organization’s document collection.
  • Teams prototyping document ingestion and hybrid retrieval pipelines.
  • Practitioners comparing retrieval configurations using Hit-Rate and MRR evaluation.

Documented uses

  • Ingest and index documents for a RAG application.
  • Retrieve relevant material with BM25 and dense search, then rerank results.
  • Enhance queries and use retrieved context in a conversational agent.
  • Compare retrieval configurations with evaluation metrics.
Before you choose

Requirements & limits

The repository is public and identified as open source. The README’s run instructions use Docker Compose and a configured .env file.

  • The stack includes Qdrant, Redis, MongoDB, Celery, FastAPI, Gradio and CrewAI, so adapting it involves multiple services.
  • The project describes Redis for cached or hot conversation data and MongoDB for longer-lived sessions and evaluation data.
  • Its evaluation workflow focuses on Hit-Rate comparisons and retrieval combinations with or without reranking and query enhancement.
  • The README identifies Hugging Face models for embedding or proposition tasks and describes the chat LLM as configurable.

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 project services with Docker Compose

Prepare the environment file and start the repository’s defined services.

Before you start

  • The project repository.
  • Docker Compose.
  • Values to fill in the supplied .env.example file.

Steps

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

  2. Fill in .env.example and rename it to .env.

  3. Run docker-compose up -d.

Expected outcome

The README lists a Gradio interface on port 7860, FastAPI on port 8000, Qdrant on ports 6333 and 6334, Redis on port 6379, and MongoDB on port 27017, along with supporting services.

Guide limitations

  • The README’s displayed clone command uses a different repository path; confirm the intended repository before following it.
  • This setup guidance does not establish that the stack has been executed or tested.
Documentation 1 ↗
Source-based practical guide

Prepare optional EURLEX sample documents

Generate mock PDF documents and select a small sample for the project’s assets directory.

Before you start

  • A Python 3.10 environment.
  • uv, reportlab and python-dotenv.

Steps

  1. Create and activate a virtual environment with uv.

  2. Install reportlab and python-dotenv.

  3. Run the project’s EURLEX preparation module with --no_docs 300.

  4. Create assets/sample_pdfs and copy 10 randomly selected PDFs from assets/pdfs.

Expected outcome

A sample_pdfs directory containing selected PDFs, following the README’s optional data-preparation sequence.

Guide limitations

  • The README presents this as an optional preparation step, not a complete ingestion or chat procedure.
  • The documented commands assume the required project files and shell utilities are available.
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
Rag BoilerplateIngest and index documents for a RAG application.Server, WebThe repository is public and identified as open source. The README’s run instructions use Docker Compose and a configured .env file.
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
18 October 2026
Original website title
mburaksayici/RAG-Boilerplate · Official homepage title · retained in its source language
How we review sourcesSuggest a correction