Theodore Li 4e6594dc54 feat(pii): add opt-in GLiNER NER engine (PII_ENGINE), device-agnostic (#5495)
* feat(pii): add opt-in GLiNER NER engine (PII_ENGINE), device-agnostic

Swap the 4 NER entity types (PERSON/LOCATION/NRP/DATE_TIME) to a single
multilingual GLiNER zero-shot model when PII_ENGINE=gliner; spaCy stays the
default and all ~36 regex/checksum recognizers are identical on both engines.
Device-agnostic via PII_DEVICE / cuda auto-detect — same code on Fargate CPU
now and EC2-GPU later.

- engines.py: side-effect-free builders; SharedModelGLiNERRecognizer loads
  ONE model shared across the 5 per-language instances and restricts labels
  to the entities it owns; small spaCy models keep tokenization/lemmas for
  the regex recognizers; fail-fast on the lean image
- pii.Dockerfile: multi-stage — default target unchanged (lean spaCy);
  --target gliner is a superset (torch CPU + gliner + baked model) where
  both engines work; gliner-gpu scaffold for the GPU fleet
- CI publishes the gliner variant (:staging-gliner/:latest-gliner, amd64)
- Helm: pii.engine / pii.device values wired to PII_ENGINE/PII_DEVICE
- scripts/bench_engines.py: throughput + NER-parity diff harness
- tests: unit (mocked GLiNER) + in-image integration for both engines

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Up3F97mjCH9HCj1pX4J8VJ

* refactor(pii): ship both engines in one image — engine is a pure env flip

Collapse the gliner build target into the single pii image: spaCy lg models,
torch (CPU), gliner, and the baked GLiNER weights all ship in it, so
PII_ENGINE switches engines with no image swap and no tag matrix. CI reverts
to the single pii build (no -gliner tags). The GPU variant becomes the same
Dockerfile built with --build-arg TORCH_INDEX_URL=.../cu128. Image grows
~6.1GB -> ~9.6GB.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Up3F97mjCH9HCj1pX4J8VJ

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-07 22:37:33 -04:00

Sim.ai Documentation Discord X

Ask DeepWiki Set Up with Cursor

Sim — Integrate, Context, Build, and Monitor AI agents

A workspace to build, deploy and manage AI agents and workflows.

Quickstart

Cloud-hosted: sim.ai

Open sim.ai

Self-hosted

npx simstudio

Open http://localhost:3000

Docker must be installed and running. Use -p, --port <port> to run Sim on a different port, or --no-pull to skip pulling the latest Docker images.

The Sim platform — chat on the left, the visual workflow builder on the right

Capabilities

  • Connect 1,000+ integrations and every major LLM
  • Add Slack, Notion, HubSpot, Salesforce, databases, and more
  • Build agents visually, conversationally, or with code
  • Ingest files, knowledge bases, and structured table data
  • Monitor runs, logs, schedules, and workflow activity

One workspace, every surface

Chat and workflows are just the start — tables, files, knowledge, and scheduled tasks all live in the same workspace.

Tables in Sim — structured data your agents can query

Tables — a database, built in

Files in Sim — documents for your team and every agent

Files — one store for your team and every agent

Knowledge bases in Sim — synced docs your agents can search

Knowledge — your agents' memory

Scheduled tasks in Sim — recurring agent runs on a calendar

Scheduled tasks — runs on your schedule

Self-hosting

Docker Compose

git clone https://github.com/simstudioai/sim.git && cd sim
docker compose -f docker-compose.prod.yml up -d

Open http://localhost:3000

Sim also supports local models via Ollama and vLLM. See the Docker self-hosting docs for setup details.

Manual Setup

Requirements: Bun, Node.js v20+, PostgreSQL 12+ with pgvector

  1. Clone and install:
git clone https://github.com/simstudioai/sim.git
cd sim
bun install
bun run prepare  # Set up pre-commit hooks
  1. Set up PostgreSQL with pgvector:
docker run --name simstudio-db -e POSTGRES_PASSWORD=your_password -e POSTGRES_DB=simstudio -p 5432:5432 -d pgvector/pgvector:pg17

Or install manually via the pgvector guide.

  1. Configure environment:
cp apps/sim/.env.example apps/sim/.env
# Create your secrets
perl -i -pe "s/your_encryption_key/$(openssl rand -hex 32)/" apps/sim/.env
perl -i -pe "s/your_internal_api_secret/$(openssl rand -hex 32)/" apps/sim/.env
perl -i -pe "s/your_api_encryption_key/$(openssl rand -hex 32)/" apps/sim/.env
# DB configs for migration
cp packages/db/.env.example packages/db/.env
# Edit both .env files to set DATABASE_URL="postgresql://postgres:your_password@localhost:5432/simstudio"
  1. Run migrations:
cd packages/db && bun run db:migrate
  1. Start development servers:
bun run dev:full  # Starts Next.js app and realtime socket server

Or run separately: bun run dev (Next.js) and cd apps/sim && bun run dev:sockets (realtime).

Chat API Keys

Chat is a Sim-managed service. To use Chat on a self-hosted instance:

  • Go to https://sim.ai → Settings → Chat keys and generate a Chat API key
  • Set COPILOT_API_KEY environment variable in your self-hosted apps/sim/.env file to that value

Environment Variables

See the environment variables reference for the full list, or apps/sim/.env.example for defaults.

Tech Stack

Next.js · Bun · PostgreSQL · Drizzle · Better Auth · Tailwind — and the rest of the stack

Contributing

We welcome contributions! Please see our Contributing Guide for details.

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Built by the Sim team in San Francisco

Languages
TypeScript 77%
MDX 20.8%
JavaScript 1.9%
CSS 0.1%