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

Rag App Hacktogether

Rag App Hacktogether is a self-hosted .NET 8 application that indexes private PDF documents in Qdrant and uses retrieval-augmented generation to answer multilingual questions from their contents. PdfPig extracts and chunks text, Microsoft Semantic Kernel coordinates retrieval and generation, and Azure OpenAI produces answers grounded in the retrieved passages.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rag App Hacktogether — 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 when answers should be drawn from a specific PDF collection and the project’s .NET, Qdrant and Azure OpenAI stack matches your implementation needs.

Who it is for

  • People building a multilingual question-answering interface for a private PDF collection.
  • Developers exploring a C#/.NET implementation that combines PDF extraction, vector search and language-model generation.
  • Teams organizing bounded reference material, such as official guidance, into a document-grounded assistant.

Documented uses

  • Ask natural-language questions in multiple languages about a supplied PDF collection.
  • Retrieve semantically relevant PDF passages rather than relying on keyword-only lookup.
  • Create a .NET-based RAG demonstration with PDF ingestion, vector storage and Azure OpenAI generation.
Before you choose

Requirements & limits

The documented setup requires a .NET 8 SDK, an Azure OpenAI deployment and API key, and a reachable Qdrant instance. Docker is needed for the documented local Qdrant setup.

  • The ingestion path is PDF-specific; other document formats require modification.
  • The application uses fixed-size text chunking, which may be unsuitable without changes for complex tables or layouts.
  • Azure OpenAI is the demonstrated generation provider; another provider is an Experimental adaptation, not a demonstrated configuration.
  • The project describes Docker for running Qdrant locally, not a complete application deployment recipe.
  • No automated evaluation harness is documented.

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

Set up the PDF question-answering application

Prepare the documented local prerequisites, configure PDF input, and start the application.

Before you start

  • .NET 8 SDK
  • Azure OpenAI deployment and API key
  • Qdrant running locally in Docker or reachable at a configured endpoint
  • Docker if running Qdrant locally
  • PDF documents for the assistant

Steps

  1. Clone the repository and change into its directory.

  2. Start Qdrant locally with Docker, or configure the application to use an existing Qdrant endpoint.

  3. Set the AZURE_OPENAI_API_KEY environment variable for your operating system.

  4. Place the PDF files in the data/ directory.

  5. Run dotnet run; on first run, the application indexes the documents into Qdrant, after which questions can be asked in any language.

Expected outcome

A running application that indexes the supplied PDFs and accepts multilingual questions grounded in the indexed material.

Guide limitations

  • Answers are limited to provided documents; questions outside their coverage return no answer.
  • Chunking is fixed-size and may need reconsideration for PDFs with complex tables or layouts.
  • The repository reports no automated evaluation harness.
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 App HacktogetherAsk natural-language questions in multiple languages about a supplied PDF collection.Docker, Self-hostedThe documented setup requires a .NET 8 SDK, an Azure OpenAI deployment and API key, and a reachable Qdrant instance. Docker is needed for the documented local Qdrant setup.
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
edilma/RAG-App-HackTogether · Official homepage title · retained in its source language
How we review sourcesSuggest a correction