docs: align managed runtime examples

This commit is contained in:
Andrey Avtomonov 2026-05-11 12:51:24 +02:00
parent 428fd829fc
commit d88bec4e42
5 changed files with 151 additions and 83 deletions

100
README.md
View file

@ -20,13 +20,11 @@ artifacts. You can inspect them, commit them, and serve them to any MCP client.
## Quick start
Run the pre-seeded demo from the repository root:
Run the pre-seeded demo through the public npm package:
```bash
pnpm install
pnpm run setup:dev
pnpm run ktx -- setup demo --no-input
pnpm run ktx -- setup demo inspect
npx @kaelio/ktx setup demo --no-input
npx @kaelio/ktx setup demo inspect
```
The default demo uses packaged sample data and prebuilt context. It does not
@ -35,7 +33,7 @@ require API keys, network access, or an LLM provider.
To replay the packaged ingest run, use:
```bash
pnpm run ktx -- setup demo --mode replay --no-input
npx @kaelio/ktx setup demo --mode replay --no-input
```
To run the full agentic demo with an LLM provider, set a provider key for the
@ -43,22 +41,29 @@ current process:
```bash
ANTHROPIC_API_KEY=$YOUR_ANTHROPIC_API_KEY \
pnpm run ktx -- setup demo --mode full --no-input
npx @kaelio/ktx setup demo --mode full --no-input
```
Interactive full-demo setup can prompt for a provider key without writing the
key to `ktx.yaml`.
## Build a local project
Create a project from the repository root:
You can also install the CLI in a project or globally:
```bash
uv sync --all-packages
source .venv/bin/activate
npm install @kaelio/ktx
npx ktx --help
npm install -g @kaelio/ktx
ktx --help
```
## Build a local project
Create a project from a local workspace:
```bash
npm install @kaelio/ktx
PROJECT_DIR="$(mktemp -d)/ktx-demo"
pnpm run ktx -- init "$PROJECT_DIR" --name ktx-demo
npx ktx init "$PROJECT_DIR" --name ktx-demo
```
Create a SQLite warehouse:
@ -112,7 +117,7 @@ YAML
Write and validate a semantic-layer source:
```bash
pnpm run ktx -- sl write accounts --project-dir "$PROJECT_DIR" \
npx ktx sl write accounts --project-dir "$PROJECT_DIR" \
--connection-id warehouse --yaml 'name: accounts
table: accounts
description: CRM accounts with segmentation attributes.
@ -133,14 +138,14 @@ measures:
joins: []
'
pnpm run ktx -- sl validate accounts --project-dir "$PROJECT_DIR" \
npx ktx sl validate accounts --project-dir "$PROJECT_DIR" \
--connection-id warehouse
```
Generate SQL and execute the query:
```bash
pnpm run ktx -- sl query --project-dir "$PROJECT_DIR" \
npx ktx sl query --project-dir "$PROJECT_DIR" \
--connection-id warehouse \
--measure accounts.account_count \
--dimension accounts.segment \
@ -148,7 +153,7 @@ pnpm run ktx -- sl query --project-dir "$PROJECT_DIR" \
--limit 5 \
--format sql
pnpm run ktx -- sl query --project-dir "$PROJECT_DIR" \
npx ktx sl query --project-dir "$PROJECT_DIR" \
--connection-id warehouse \
--measure accounts.account_count \
--dimension accounts.segment \
@ -161,8 +166,8 @@ pnpm run ktx -- sl query --project-dir "$PROJECT_DIR" \
List and test the warehouse connection:
```bash
pnpm run ktx -- connection list --project-dir "$PROJECT_DIR"
pnpm run ktx -- connection test warehouse --project-dir "$PROJECT_DIR"
npx ktx connection list --project-dir "$PROJECT_DIR"
npx ktx connection test warehouse --project-dir "$PROJECT_DIR"
```
The connection test prints the configured driver and discovered table count:
@ -179,34 +184,55 @@ Scan artifacts are written under
```bash
SCAN_OUTPUT="$(pnpm run ktx -- scan warehouse --project-dir "$PROJECT_DIR")"
SCAN_OUTPUT="$(npx ktx scan warehouse --project-dir "$PROJECT_DIR")"
printf '%s\n' "$SCAN_OUTPUT"
SCAN_RUN_ID="$(printf '%s\n' "$SCAN_OUTPUT" | awk '/^Run: / { print $2 }')"
pnpm run ktx -- scan status --project-dir "$PROJECT_DIR" "$SCAN_RUN_ID"
pnpm run ktx -- scan report --project-dir "$PROJECT_DIR" "$SCAN_RUN_ID"
npx ktx scan status --project-dir "$PROJECT_DIR" "$SCAN_RUN_ID"
npx ktx scan report --project-dir "$PROJECT_DIR" "$SCAN_RUN_ID"
```
For non-SQLite drivers, prefer credential references such as `--url env:NAME`
or `--url file:PATH` over literal credential URLs.
## Managed Python runtime
KTX installs its Python runtime only when a Python-backed command needs it.
The runtime lives outside the npm cache, is versioned by the installed CLI
version, and is managed by `ktx runtime` commands:
```bash
npx ktx runtime install --yes
npx ktx runtime status
npx ktx runtime doctor
npx ktx runtime start
npx ktx runtime stop
```
Commands such as `npx @kaelio/ktx sl query ... --yes` can install the core
runtime lazily from the bundled wheel. Local embeddings remain lazy; prepare
them only when you select local `sentence-transformers` embeddings:
```bash
npx ktx runtime install --feature local-embeddings --yes
npx ktx runtime start --feature local-embeddings
```
## Serve MCP
Start the Python compute daemon in one terminal:
Start the stdio MCP server from the project directory:
```bash
source .venv/bin/activate
uv run ktx-daemon serve-http --host 127.0.0.1 --port 8765
```
Start the stdio MCP server in another terminal:
```bash
pnpm run ktx -- serve --mcp stdio --project-dir "$PROJECT_DIR" \
npx ktx serve --mcp stdio --project-dir "$PROJECT_DIR" \
--user-id local \
--semantic-compute-url http://127.0.0.1:8765 \
--execute-queries
--semantic-compute \
--execute-queries \
--yes
```
The `--semantic-compute` flag uses the managed Python runtime when no explicit
semantic compute URL is provided. KTX starts or reuses the managed runtime as
needed.
The MCP server exposes `connection_list`, `knowledge_search`,
`knowledge_read`, `knowledge_write`, `sl_list_sources`, `sl_read_source`,
`sl_write_source`, `sl_validate`, `sl_query`, `ingest_trigger`,
@ -252,10 +278,10 @@ packages.
## Release status
This repository is prepared for source publication. Package publishing is still
disabled by `release-policy.json`; registry names, public versions, package
visibility, and provenance policy must be chosen before publishing artifacts to
npm or Python package indexes.
This repository builds a single public npm artifact named `@kaelio/ktx`.
Package publishing is still disabled by `release-policy.json`; registry
credentials, public versions, release tags, and provenance policy must be
chosen before publishing artifacts to npm or Python package indexes.
Build local package artifacts with: