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

Go Qdrant Rag Sample

Go Qdrant Rag Sample is a Go application demonstrating semantic search and retrieval-augmented question answering over product catalog data, using OpenAI models and Qdrant. It ingests product records from a CSV file, creates embeddings, stores them in a Qdrant collection, and exposes REST endpoints for search and generated answers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Go Qdrant Rag Sample — 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 reference or starting point when a Go application needs to turn structured catalog data into semantic search and retrieval-grounded answers.

Who it is for

  • Go developers exploring semantic search and RAG patterns.
  • Builders prototyping catalog search or product-question answering over structured data.

Documented uses

  • Ingest CSV product records and create vector embeddings.
  • Search catalog items by semantic query.
  • Return an OpenAI-generated answer using retrieved catalog data.
Before you choose

Requirements & limits

The documented local setup uses an OpenAI API key and a Qdrant service; it shows Qdrant running in Docker Compose.

  • The sample is built around product records in data/products.csv.
  • It documents Go 1.24.0, Qdrant, OpenAI, Fiber, and Resty.
  • The REST API is documented at localhost:8080, with /search and /rag routes.
  • Startup ingestion runs only when the Qdrant collection is empty.

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 local catalog search API

Configure the sample, start Qdrant, and launch its local REST API.

Before you start

  • Go 1.24.0
  • Docker Compose and the repository's Qdrant service
  • An OpenAI API key
  • Qdrant reachable at the configured host
  • The repository dataset at data/products.csv

Steps

  1. Create env/.env with OPENAI_API_KEY and QDRANT_HOST=http://localhost:6333.

  2. From the project root, start Qdrant with docker-compose up -d qdrant.

  3. Run go run ./cmd/api from the project root.

Expected outcome

The application initializes its Qdrant collection if needed, ingests products if the collection is empty, and starts the REST API at http://localhost:8080. The documented routes are /search?q=... and /rag?q=...&top=3.

Guide limitations

  • The documented flow uses the included product CSV and catalog example.
  • On startup, ingestion is skipped when the Qdrant collection is not empty.
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
Go Qdrant Rag SampleIngest CSV product records and create vector embeddings.Cloud, Docker, Self-hosted, ServerThe documented local setup uses an OpenAI API key and a Qdrant service; it shows Qdrant running in Docker Compose.
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
18 October 2026
Original website title
yuniko-software/go-qdrant-rag-sample · Official homepage title · retained in its source language
How we review sourcesSuggest a correction