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

Porag

PoRAG is a self-hosted Python retrieval-augmented generation pipeline for querying Bengali text data with natural-language questions. It combines LangChain, Transformers, recursive character splitting and ChromaDB, and supports configurable local or Hugging Face language models and Sentence Transformers-compatible embeddings.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Porag — 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 PoRAG when you want to prototype or build a configurable Bengali RAG workflow over plain-text files and can manage its Python environment and model choices.

Who it is for

  • Developers building Bengali-language question-answering tools over text collections.
  • Teams seeking configurable, self-hosted retrieval and generation for Bengali documents.

Documented uses

  • Ask questions in Bengali about information in a Bengali text corpus.
  • Build a knowledge-search or question-answering workflow over .txt documents.
  • Tune model selection, retrieval count, chunking and generation parameters.
Before you choose

Requirements & limits

PoRAG is a public GitHub repository with an MIT license; the documented workflow is self-hosted.

  • Input ingestion is documented for .txt files only; other formats require text conversion.
  • The pipeline uses ChromaDB for vector storage and Sentence Transformers-compatible embeddings with a stated dimension of 768.
  • The README documents a quantization option and configurable generation and retrieval parameters.
  • Installation is via Python dependencies in the repository; a Hugging Face token may be needed for some model choices.

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

Run questions against a Bengali text file

Use the documented command-line workflow to ask questions about a Bengali .txt corpus.

Before you start

  • Python and Git
  • A clone of the PoRAG repository with its requirements installed
  • A Bengali text corpus saved as a .txt file
  • A Hugging Face token if required by the selected model

Steps

  1. Clone the repository and change into its directory.

  2. Install the listed dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  3. Prepare a Bengali text file and run the command below, replacing the filename with your file’s path.

    Documented command
    python main.py --text_path test.txt

  4. Type a question when prompted; add --show_context to display retrieved context.

Expected outcome

An interactive terminal workflow returns an answer based on information retrieved from the supplied text file.

Guide limitations

  • The documented ingestion format is .txt only; the README notes Bengali PDF parsing limitations.
  • Model and embedding choices must be compatible with the supported Transformers and Sentence Transformers integrations.
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
PoragAsk questions in Bengali about information in a Bengali text corpus.Self-hostedPoRAG is a public GitHub repository with an MIT license; the documented workflow is self-hosted.
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
16 October 2026
Original website title
Bangla-RAG/PoRAG · Official homepage title · retained in its source language
How we review sourcesSuggest a correction