datris) is a command-line interface for the Datris Data Platform. It communicates with the platform via the MCP server, providing a simple way to ingest data, run queries, search vector stores, and manage pipelines — all from the terminal.
Installation
datris-mcp-server) and the CLI (datris).
Configuration
The CLI connects to the MCP server via SSE. Set the server URL with an environment variable:Commands
datris pipelines
List all registered pipelines.
datris ingest
Create a pipeline and ingest a data file in one step. The schema is auto-detected from the file.
| Option | Description |
|---|---|
--pipeline, -p | Pipeline name (default: derived from filename) |
--dest, -d | Destination: postgres, mongodb, qdrant, weaviate, milvus, chroma, pgvector (default: postgres) |
--table, -t | Table/collection name (default: pipeline name) |
--database | Database name (default: datris) |
--ai-validate | AI data quality rule — plain-English instruction |
--ai-transform | AI transformation instruction — plain-English instruction |
--ai-validate): Datris generates a Python validation script from your instruction and runs it locally against all data. The script checks every row and reports failures. Cost is ~$0.003 per rule regardless of file size.
AI Transformation (--ai-transform): Datris generates a Python transformation script from your instruction and runs it locally against all data. The script transforms every row according to your instruction.
datris query
Execute a read-only SQL SELECT query against PostgreSQL.
| Option | Description |
|---|---|
--limit | Max rows returned (default: 100, max: 1000) |
datris search
Semantic search across a vector database.
| Option | Description |
|---|---|
--store | Vector store: qdrant, weaviate, milvus, chroma, pgvector (default: pgvector) |
--collection | Collection/table name (required) |
--top-k | Number of results (default: 5) |
datris ask
RAG — search a vector store and generate an AI answer from the results.
datris search.
datris ask-sql
Natural language SQL — describe what you want in plain English, and Datris generates and executes the SQL query.
| Option | Description |
|---|---|
--table | Table name (required) |
--schema | Schema name (default: public) |
--database | Database name (default: datris) |
--limit | Max rows (default: 100) |
datris query-mongo
Query a MongoDB collection with optional filter and projection.
| Option | Description |
|---|---|
--filter | MongoDB filter JSON (default: {}) |
--projection | Fields to include/exclude |
--limit | Max documents (default: 100) |
datris status
Get the latest job status for a pipeline.
datris delete
Delete a pipeline configuration and optionally its destination data.
| Option | Description |
|---|---|
--keep-data | Keep destination data (only delete the pipeline config) |
datris health
Check the health of all backend services.
datris secrets
List all configured secrets.
datris version
Get the server version.
Pipeline Name Auto-Detection
When--pipeline is not specified, the CLI derives the pipeline name from the filename:
sales-data.csv→sales_dataQ1 Revenue Report.csv→q1_revenue_reporttrades.json→trades