Distributed multimodal database
One database.
Four data models.
SQL, vector, graph, and full-text search.
One engine for your next application.
Start free/Scale with dedicated resources
Why OriginChainDB
Different questions.
Connected context.
Use shared identifiers to connect a result to its source.
passage:07Vector + full-text search
passage:07Structured record
product:ax7Graph relationship
One OriginChainDB engineYour app prepares indexes and connects query results.01 / Four data models
Give each question
the right query.
Start with one. Connect the others when you need them.
Query your records.
Filter, join, and aggregate your records.
01 / Explore SQLFind similar meaning.
Find nearby items, passages, and memories.
02 / Explore VectorFollow relationships.
Explore the connections between records.
03 / Explore GraphMatch the words that matter.
Rank documents by keywords and phrases.
04 / Explore Full-text02 / How it works
One passage.
Four ways to find it.
Choose a query. See what it reveals.
passage:07 AX-7 service manual
Replace the battery when capacity drops.
- Product
- AX-7
- Version
- 3
Which passages cover AX-7?
passage:07Battery replacement
Product AX-7 · version 3
03 / Inside the console
All your data.
One place to work.
Query, explore, and inspect in one workspace.
Write SQL. Inspect results. Understand the plan.
Explore SQL
Explore embeddings and their nearest neighbors.
Explore Vector
Map relationships across tables and namespaces.
Explore Graph
Search documents and inspect the matching text.
Explore Full-text
04 / Built for developers
Start with a query.
Go from a table to an application result. Use SQL directly or send it over the HTTP API.
SELECT id, title
FROM public.documents
LIMIT 3;curl --request POST \
"$OC_URL/v1/tenants/$OC_TENANT/sql" \
--header "Authorization: Bearer $OC_TOKEN" \
--header "Content-Type: application/json" \
--data '{"sql":"SELECT id, title FROM public.documents LIMIT 3;"}'| id | title |
|---|---|
doc-001 | Getting started |
doc-002 | Vectors and similarity |
doc-003 | Relationships in your data |
Example only. No request is sent.
Get your connection details.
Set
Open the quickstartOC_URL,OC_TENANTandOC_TOKENfrom your instance.Create and populate the table.
This example requires
Create your first recordspublic.documentswithidandtitlecolumns.Read your data.
Run the SQL in your workbench or send the HTTP request from your application.
Explore the query API
First-party SDKs
Connect your tools
PostgreSQL wire: limited preview. Elasticsearch: supported API subset.
05 / Deployment & operations
Start with an idea.
Build for production.
Start free. Move to dedicated resources in your region.
Your region. Dedicated compute.
Optional warm standby.Asynchronous replication.
Access controls. Daily snapshots.Configure for your dedicated instance.
Your chosen region
Illustrative dedicated topology Read the details ↗
06 / Built around your workload
What will you
build with it?
Search & RAG
Give your model context from relevant passages.
Vector / Full-text / SQLAI agents
Store run state. Recall useful memories.
SQL / Vector / GraphRecommendations
Find similar items. Rank them with your rules.
Vector / Graph / SQLFraud investigation
Trace shared devices and connected accounts.
Graph / SQLPersonalization
Turn preferences into relevant experiences.
SQL / Vector / Full-textOperational analytics
Turn application records into useful metrics.
SQL07 / Make an informed choice
Look inside.
Then put it to work.
Review the architecture, test your workload, and know what your application will own.
Understand what runs underneath.
Read about the engine, indexes, persistence, and replication.
02BenchmarksInspect the test before the number.
Check workloads, configurations, and methodology before comparing results.
03CompatibilityCheck the queries your app needs.
Review supported SQL and adapter behavior before planning an integration.
What does multimodal mean here?
Four ways to work with data in one engine: SQL for records, vector search for similarity, graph traversal for relationships, and full-text search for words. Natural-language /ask is another query interface.
Explore the databaseDoes adding a record also create its embedding and search index?
Create the indexes your workload needs. Table full-text indexes follow row writes. On dedicated configurations, use a saved embedder and a schedule for new or changed rows, or supply vectors yourself. Your application combines the query results.
Explore embedding runs and schedulesCan I use my existing database tools?
Use the HTTP API and SDKs, or supported wire and Elasticsearch adapters. Compatibility depends on the enabled adapter and its supported operations; check your queries against the integration guides.
Find an integrationHow do I move from an experiment to production?
Start on the free tier, then choose a dedicated configuration for your workload and region. Review access controls, capacity, snapshots, and the optional asynchronous standby before launch.
Plan your deploymentThe latest /
Built since your last visit.
From your first query to your next application.