OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Evaluation & Observability

Sentrev

SenTrEv is a Python package that evaluates dense and sparse text retrieval on documents to help users choose embedding models for retrieval-augmented generation. It uses Sentence Transformers or FastEmbed encoders and Qdrant vector storage, then reports retrieval and resource-use metrics.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Sentrev — OpenViST project profile in AI Evaluation & Observability.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use SenTrEv when selecting or comparing retrieval encoders for a RAG workflow and you want to evaluate them against your own documents with Qdrant.

Who it is for

  • RAG developers comparing embedding models on their document collections.
  • Practitioners evaluating dense or sparse retrieval with Sentence Transformers, FastEmbed and Qdrant.

Documented uses

  • Compare retrieval performance across embedding models on a document collection.
  • Measure ranking quality, precision, retrieval time and estimated carbon emissions.
  • Evaluate retrieval over supported document formats including PDF, PPTX, DOCX, HTML, CSV and XML.
Before you choose

Requirements & limits

The project is an open-source Python package under the MIT license. Its README documents installation with pip or from source.

  • Dense encoders are loaded through Sentence Transformers; sparse encoders use FastEmbed.
  • Qdrant is the documented vector database and may be local or cloud-hosted.
  • The workflow uses shortened chunks as retrieval queries, with a default sampling percentage of 25%.
  • Reported measures include success rate, MRR@10, precision, non-relevant ratio, retrieval time and carbon emissions.

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

Build and install SenTrEv from source

Install an editable local build using the documented source-build steps.

Before you start

  • Python 3
  • Git
  • The Python build package

Steps

  1. Clone https://github.com/AstraBert/SenTrEv.git.

  2. Change into the SenTrEv repository directory.

  3. Run the command below.

    Documented command
    python3 -m build

  4. Run the command below.

    Documented command
    python3 -m pip install -e .

Expected outcome

The package is built and installed locally in editable mode.

Guide limitations

  • The README describes source installation as more difficult and customizable; these steps cover installation, not an evaluation run.
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
SentrevCompare retrieval performance across embedding models on a document collection.CLIThe project is an open-source Python package under the MIT license. Its README documents installation with pip or from source.
DiragnosisGenerate synthetic evaluation questions from supplied documents.Docker, Linux, macOS, Self-hostedThe repository identifies the software as open source under the MIT license. The README documents a local Docker application and a pip-installable Python package.
BergenRun reproducible experiments with configurable RAG pipeline components.CLIBERGEN is released under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 license.
Evidence and transparency

Sources & review

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