RAG.
Right out of the box.
Meet Ragie, fully managed RAG-as-a-Service for developers.
Built for developers
Easy to use APIs and SDKs get you started in minutes. Our intuitive developer experience will help you ship in minutes instead of months.
Optimized for results
Built-in advanced features like LLM re-ranking, summary index, entity extraction, flexible filtering, and hybrid semantic and keyword search help you deliver state-of-the-art generative AI.
Connected to your data
Connect directly to popular data sources like Google Drive, Notion, Confluence and more. Automatic syncing keeps your data up-to-date, ensuring your application delivers accurate and reliable information.
Led by Craft Ventures
Your data,
connected in seconds.
With Ragie connectors, getting your data into your AI application has never been simpler. With just a few clicks, you can access your data where it already lives. Automatic syncing keeps your data up-to-date ensuring your application delivers accurate and reliable information.
And with Embedded Connectors (coming soon), allow your users to connect their own data directly in your application.
Here’s how Ragie works.
And what makes it special.
curl -X POST https://api.ragie.ai/documents \
- -H "Content-Type: multipart/form-data" \
- -H "Authorization: Bearer $RAGIE_API_KEY" \
- -F 'metadata={"tags":["human_resources"]}' \
- -F ”file=@./policy.pdf”
curl -X POST https://api.ragie.ai/retrievals \
- -H "Content-Type: application/json" \
- -H "Authorization: Bearer $RAGIE_API_KEY" \
- -d '{
- "query": "what is our parental leave policy?",
- "rerank": true,
- "filter": {"tags": {"$in": ["human_resources", "legal"]}}
- }'
Ingest
The first step in a RAG pipeline is to ingest the relevant data. Use Ragie’s simple APIs to upload files directly. Or, connect directly to popular data sources like Google Drive, Notion, and Confluence. Automatic syncing keeps your data up-to-date, handling everything from text and PDFs to images and PowerPoint presentations.
curl -X POST https://api.ragie.ai/documents \
- -H "Content-Type: multipart/form-data" \
- -H "Authorization: Bearer $RAGIE_API_KEY" \
- -F 'metadata={"tags":["human_resources"]}' \
- -F ”file=@./policy.pdf”
Chunking and indexing
The next step is to prepare the data for LLM processing. Ragie automatically chunks and embeds your data into vectors using the latest multi-lingual LLMs. These vectors are then stored in a highly-scalable vector database. Out of the box, Ragie builds vectory, summary, and keyword indexes.
Retrieval
The final step is to use Ragie’s retrieval API to get relevant chunks for your semantic search query. Built-in advanced features like LLM re-ranking, summary index, entity extraction, flexible filtering, and hybrid semantic and keyword search ensure your RAG pipeline delivers the most accurate and relevant results to your AI application.
curl -X POST https://api.ragie.ai/retrievals \
- -H "Content-Type: application/json" \
- -H "Authorization: Bearer $RAGIE_API_KEY" \
- -d '{
- "query": "what is our parental leave policy?",
- "rerank": true,
- filter": {"tags": {"$in": ["human_resources", "legal"]}}
}'
We focus on RAG
so you don’t have to.
With Ragie, you’ll leverage our deep expertise as we stay at the forefront of AI research and development, utilizing best-in-class techniques. This is our core focus.
Focus on what matters the most – developing your applications – while we handle the rest.
No matter what you're building,
know what you're paying
Ragie offers simple, straightforward pricing without setup fees, hidden costs, or surprises.