Use case
The knowledge base API for grounded answers.
Add retrieval-augmented, cited answers to your product with a single endpoint—knowledge-base-scoped keys, server-sent events, and no RAG pipeline to build or host.
Build versus operate
Ship the feature, not the retrieval pipeline
Building retrieval-augmented answers in-house means owning parsers for a dozen file formats, an embedding pipeline, a vector store, passage-splitting heuristics, retrieval tuning, citation plumbing, and the infrastructure to keep it all fresh. That is a platform project, and it starts before the first useful answer.
kbDrop collapses it to two steps: create a knowledge base from documents or a website, then call one endpoint with a scoped key. Your code renders events; kbDrop operates the pipeline.
What the endpoint gives you
Grounded answers as a contract
Retrieval and citations included
Each request runs retrieval over the knowledge base and streams the answer with citation events, so your product can render sources next to the text.
Keys scoped to one knowledge base
API secrets are stored as hashes, shown in full only at creation, rate limited, independently revocable, and unable to query any other knowledge base.
Streaming from the first event
Named server-sent events—status, citation, text_delta, done, error—let you show progress immediately instead of waiting on a blocking response.
One request
POST a question, stream the answer
Send the scoped key as a Bearer token and consume named SSE events until done or error ends the stream. The quickstart documents every event shape.
curl --no-buffer --request POST \
--url 'https://kbdrop.io/v1/knowledge-bases/<knowledge-base-id>/messages' \
--header 'Authorization: Bearer kb_live_...' \
--header 'Accept: text/event-stream' \
--header 'Content-Type: application/json' \
--data '{"input":"How do I reset the device?","stream":true}'What teams build with it
- In-product help that answers from your docs site with citations your users can open.
- A support assistant grounded in the manuals and macros your team already maintains.
- Internal tools that answer from a ZIP of policies, contracts, or runbooks.
- Prototypes that need credible retrieval this week, not after a quarter of pipeline work.
Questions, answered
Knowledge base API FAQ
Is this a RAG API?
Yes. kbDrop is retrieval-augmented generation as a managed service: source processing, passage splitting, indexing, retrieval, answer generation, and citations run server-side, and your application consumes one streaming endpoint.
How are API keys secured?
Keys are scoped to a single knowledge base, stored as hashes, shown in full only when created, rate limited, and revocable at any time from the knowledge base's API panel. Keep them on your server and send them as Bearer tokens.
What does the API cost?
API answers draw from the same monthly cited-answer quota as chat. The Free plan is enough to prototype against, and the Starter and Scale plans raise the quotas—see the pricing page for the current numbers.
Are there SDKs?
The API is plain HTTP plus server-sent events, so it works from any language without an SDK—curl, fetch, or your framework's HTTP client. The quickstart shows the full request and event contract.
How do I handle rate limits?
Rate-limited responses include a Retry-After header. Honor it, back off, and retry; the stream's error event also tells you when a request was rejected mid-flight.
First cited answer in an afternoon
Create a knowledge base, scope a key to it, and stream a grounded answer into your product before the day ends.
Create a free account