Natural language

Ask questions.
Get database results.

Turn a plain-English question into a query against your registered tables, with a plan you can inspect.

From a question to a query.

OriginChainDB turns your question into a query plan, runs it and returns database rows.

Question and table scope, compiled into a query plan.Illustrative example

Start with a question

“Show the first 10 pending orders.”

Table scope shop.orders

A matching cached plan can go straight to execution.

Cache hit Reuse plan

On a cache miss

Recognized questions become a query plan.

Only for questions outside those rules

The model helps compile a plan when available.

Compiled plan

Readshop.orders

Filterstatus = pending

Limit10 rows

The database runs the plan

order_idstatus

order-042pending

order-057pending

Database rows, plus the plan when requested.

Give the question context
Name the tables your question is about. Specific column names help OriginChainDB identify the data you need.
Turn the question into a query
OriginChainDB tries built-in query rules first. Questions outside those rules can use the configured language model. The database then runs the resulting plan.

Questions that need a model are sent to the configured provider. Keep sensitive values out of prompts.

From your application

One request carries the question, the tables to consider and whether to return the plan.

nlThe question: Name the data and the condition you want. Here, we ask for up to ten pending orders.
schemasThe context: Limit the compiler to relevant registered tables instead of your entire catalogue.
show_planThe explanation: Return the compiled plan with the rows so you can review the query before using it in your application.

POST/v1/tenants/:tenant/ask

{
  "nl": "top 10 shop.orders where status = pending",
  "schemas": ["shop.orders"],
  "show_plan": true
}

Example request · authenticated with your database credentials.

Question → plan → review

Start with a specific question

“Show important customers.”

“Top 5 customers by total order amount.”

Say which quantity matters and whether it is a total, count or individual value. Split unrelated requests into separate questions.

Check the selected tables.Confirm the plan reads the records you intended.
Review filters and limits.A valid plan can still express the wrong business question.
Test with familiar records.Compare returned rows with a small example you understand before adding the query to a workflow.