Turn any website into a knowledge base for LLMs
Crawl, chunk, and vectorize any website so you can use their content with LLMs.
curl --request POST \
--url https://api.embedding.io/v0/query \
--header 'Authorization: Bearer V09XIFlPVSdSRSBBIEhBQ0tFUg==' \
--json '{
"collection": "col_lPMjKLBRLZ4qVe",
"query": "Why should I avoid sunflower oil?"
}'
How it works
Create a Collection
Use our API or web interface to make a collection. This holds the pages or websites you want to use.
curl --request POST \
--url https://api.embedding.io/v0/collections \
--header 'Authorization: Bearer V09XIFlPVSdSRSBBIEhBQ0tFUg==' \
--json '{
"name": "Health Gurus"
}'
Ingest Content
Add web pages to your collection. We will handle the rest, including updates.
curl --request POST \
--url https://api.embedding.io/v0/collections/col_lPMjKLBRLZ4qVe/websites \
--header 'Authorization: Bearer V09XIFlPVSdSRSBBIEhBQ0tFUg==' \
--json '{
"domains": [
"https://peterattiamd.com/",
"https://www.foundmyfitness.com/"
]
}'
Query your Collection
Once your collection is ready, query it using our API. We keep the data updated for you.
curl --request POST \
--url https://api.embedding.io/v0/query \
--header 'Authorization: Bearer V09XIFlPVSdSRSBBIEhBQ0tFUg==' \
--json '{
"collection": "col_lPMjKLBRLZ4qVe",
"query": "Why should I avoid sunflower oil?"
}'
Public collections
Try our public collections
Pricing
Get started for free.
Free
500 credits
$0 /month
- Up to 500 pages per month
- Up to 1 collection
- Chat with your collections
- Monthly updates
- API access
Hobby
2,000 credits
$20 /month
- Up to 2,000 pages
- Up to 5 collections
- Chat with your collections
- Weekly updates
- API access
Startup
20,000 credits
$100 /month
- Up to 20,000 pages
- Up to 10 collections
- Chat with your collections
- Daily updates
- API access
Prices are in USD and exclude any applicable taxes.
Enterprise
Everything in Startup, plus:
- Unlimited pages
- Unlimited collections
- Hourly updates
- Custom crawlers
- SLAs
- Concierge onboarding
FAQ
Frequently Asked Questions
-
A credit is a unit of measurement used to track your usage of our services. Each page you add to your collection consumes one credit. Additionally, each time a page is updated, it also consumes one credit.
-
You can embed any publicly available content on the internet, including websites, blogs, documentation, and more.
-
No, your website does not need to have a sitemap. Our system can crawl and extract content from any publicly accessible web pages.
-
Our crawler will extract the main content of the page, leaving aside the navigation, ads, and other irrelevant content. We use a combination of machine learning and heuristics to determine what is the main content of the page.
-
The content is updated based on the plan you are subscribed to. The Free plan updates the content monthly, the Hobby plan updates the content weekly, and the Startup plan updates the content daily. You can also trigger an update manually.
-
Yes, you can use our API to create, manage, and query your collections. Detailed API documentation is available to help you get started.
-
If you exceed your credit limit, you will need to upgrade to a higher plan to continue adding pages to your collections. You can also contact us for custom solutions.
-
Yes, with the Enterprise plan, you can have custom crawlers tailored to your specific needs. Contact us for more details.
-
Yes, you can cancel your subscription at any time. Your account will remain active until the end of the current billing cycle.
Turn your content into a knowledge base
Plug your content into an LLM in less than 5 minutes.