Sold by: UpnixappÂ
Deployed on AWS
This product has charges associated with it for seller support. Deploy a ready-to-use Retrieval Augmented Generation RAG stack on Ubuntu 24.04 LTS. RAG Studio lets you upload PDF DOCX or text files and query them with AI using FastAPI Chroma FAISS and Ollama. Includes a web chat UI CloudWatch integration and hardened security defaults.
Overview
This is a repackaged open source software product wherein additional charges apply for support. RAG Studio by UpnixApp is a developer ready AMI that enables fast deployment of Document Question and Answer systems powered by Large Language Models LLMs.
With FastAPI APIs a simple chat UI and built in document ingestion pipeline for PDF DOCX TXT and S3 URLs you can launch your own internal knowledge base in minutes. Documents are embedded into a Chroma FAISS vector store making it easy to retrieve and answer questions accurately.
Features include:
- Pre installed FastAPI service with endpoints for document upload ingestion and query.
- RAG pipeline powered by Chroma FAISS configurable for your docs.
- Web chat interface for quick interaction and demos.
- Ollama integration for running models locally such as Mistral LLaMA or bring your own models.
- CloudWatch Agent enabled for logs and metrics.
- Hardened Ubuntu 24.04 with IMDSv2 enforced firewall enabled fail2ban and non root services.
RAG Studio is ideal for SMBs educators researchers and enterprises that need a quick secure way to search and query private knowledge sources without building everything from scratch.
Highlights
- Upload and Ask
- End to End RAG Pipeline
- Flexible Deployment
Details
Sold by
Delivery method
Delivery option
64-bit (x86) Amazon Machine Image (AMI)
Latest version
Operating system
Ubuntu 24.04
Deployed on AWS
Unlock automation with AI agent solutions
Fast-track AI initiatives with agents, tools, and solutions from AWS Partners.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time. Alternatively, you can pay upfront for a contract, which typically covers your anticipated usage for the contract duration. Any usage beyond contract will incur additional usage-based costs.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Cost/hour |
|---|---|
c7i.24xlarge Recommended | $0.16 |
t3.xlarge | $0.08 |
c7i.48xlarge | $0.20 |
c7i-flex.12xlarge | $0.12 |
t3a.medium | $0.06 |
t3.medium | $0.06 |
c7i-flex.16xlarge | $0.12 |
t3a.xlarge | $0.08 |
t3a.large | $0.08 |
t3.large | $0.08 |
Vendor refund policy
Support fees refundable within 7 days if issues remain unresolved
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA)Â .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Preinstalled Software: Python 3.12 FastAPI Uvicorn LangChain Chroma FAISS Ollama CloudWatch Agent
Additional details
Usage instructions
- Start the instance with 1-Click. When launching, ensure you create or select an existing EC2 key pair. The private key file will be needed for SSH access.
- Connect to the instance via SSH. Private key: the .pem file created during the EC2 provisioning process Username: ubuntu SSH port: 22 Example: ssh -i your-key.pem ubuntu@<public-ip-address>
- Default services available after boot. RAG Studio API runs on port 8000 Web UI available through the public IP or domain name (if Caddy configured) CloudWatch Agent is preinstalled and sends system logs and metrics to AWS CloudWatch
- Upload and query documents. Open http://<public-ip> in your browser Upload supported files: PDF, DOCX, TXT, or S3 URLs Enter your questions in the chat box and receive answers from the ingested documents
- Configuration. Edit environment variables at /opt/ragstudio/.env to select model name and add optional API keys (OpenAI, Anthropic, or Bedrock) Sample notebooks are available in /opt/ragstudio/examples
- Logs and monitoring. Local logs are stored in /var/log/ragstudio/ CloudWatch integration is enabled for centralized monitoring
Support
Vendor support
Email: support@upnixapp.com Included with 48 hour response time Monday to Friday
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
FloTorch - GenAI RAG Accelerator
By Fission Labs Inc.
FloTorch is an open source tool designed to expedite the proof of concept journey for Generative AI workloads significantly. It enables users to optimize RAG implementations through systematic experimentation and validation, ensuring secure, automated, and cost efficient deployment within their AWS infrastructure.
Medical LLM - Medium
By John Snow Labs
Use for chat, RAG, medical summarization, open-book question answering with context of up to 32K tokens.
Progress Agentic RAG
By Progress Software Corporation
Unlock the power of your unstructured data with Progress Agentic RAG - a no-code, multilingual, agentic RAG platform that delivers traceable, verifiable AI search across documents, media, and systems.
voyage-3 Embedding Model
By Voyage AI
Text embedding model optimized for general-purpose (including multilingual) retrieval/search and AI applications. 32K context length.
voyage-3-large Embedding Model
By Voyage AI
State-of-the-art text embedding model with the best general-purpose and multilingual retrieval quality. 32K context length.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.