@connectai/selfhost - npm Package Compare versions

Comparing version 0.1.8 to 0.1.9

assets/docker-compose.selfhost.yml

@@ -198,17 +198,2 @@ # ConnectAI self-host stack — IMAGE-BASED variant (no source clone).
 
-  # Local, offline inference (text + 1024-dim embeddings). To use a hosted model
-  # instead, remove this service and set the BYO path in deploy/selfhost/.env.
-  # ConnectAI's billed gateway is forbidden in self-host mode.
-  ollama:
-    image: ollama/ollama:latest
-    restart: unless-stopped
-    volumes:
-      - ollama-data:/root/.ollama
-    # The bundled Ollama is reached by the api/loop-svc over the compose network at
-    # http://ollama:11434, so it needs no host port. Publishing 11434 to the host
-    # collides with a native `ollama serve` (common on a dev box). Uncomment +
-    # remap to a free host port only if you want to reach this Ollama from the host.
-    # ports:
-    #   - "11435:11434"
-
 volumes:
@@ -218,2 +203,1 @@ db-data:
   infisical-redis-data:
-  ollama-data:

assets/scripts/selfhost/up.sh

@@ -127,3 +127,3 @@ #!/usr/bin/env bash
 # --- 4. full stack -----------------------------------------------------------
-log "Bringing up the full stack (db, api, loop-svc, console, ollama)."
+log "Bringing up the full stack (db, api, loop-svc, console)."
 "${COMPOSE[@]}" up -d
@@ -174,3 +174,3 @@
   2. Open ${SETUP_URL} and paste the token.
-  3. Create the first administrator, confirm inference, and connect a source.
+  3. Create the first administrator, confirm the configured inference endpoint, and connect a source.
 
@@ -177,0 +177,0 @@ Full walkthrough + troubleshooting: SELF_HOSTING.md

lib/boot.js

 // Boot orchestration for `connectai run`. Delegates the actual stack bring-up to
 // the bundled up.sh (the hardened, idempotent boot ENGINE) rather than
-// re-implementing compose orchestration, then pulls models (soft-fail) and prints
-// the next step. CON-131 scope items 5-7.
+// re-implementing compose orchestration, then prints the next step.
 import { spawn } from 'node:child_process'
@@ -47,3 +46,3 @@ import path from 'node:path'
   ui.raw(`  Images:   ghcr.io/connectai-os/connectai-{app,console}:${imageTag}`)
-  ui.raw(`  Models:   ${DEFAULT_CHAT_MODEL} + ${EMBED_MODEL}`)
+  ui.raw(`  Default endpoint models: ${DEFAULT_CHAT_MODEL} + ${EMBED_MODEL}`)
   ui.raw('')
@@ -50,0 +49,0 @@ ui.raw('  NEXT STEP: copy the one-time setup token, then open the setup URL.')

lib/cli.js

@@ -5,4 +5,2 @@ // `@connectai/selfhost` CLI entry. Dependency-free arg parsing + command dispatch.
 // Flags:     --dir <path>   working dir (default ~/.connectai-selfhost)
-//            --model <name> override the chat model to pull (run only)
-//            --no-pull      skip model pull (run only)
 //            --yes / -y     non-interactive (already the default; accepted for CI)
@@ -15,3 +13,3 @@ //            --tag <tag>    override the GHCR image tag (sets CONNECTAI_IMAGE_TAG)
 import { fileURLToPath } from 'node:url'
-import { DEFAULT_DIR, DEFAULT_CHAT_MODEL, DEFAULT_IMAGE_TAG, LEGACY_DEFAULT_DIR } from './constants.js'
+import { DEFAULT_DIR, DEFAULT_IMAGE_TAG, LEGACY_DEFAULT_DIR } from './constants.js'
 import { ui } from './ui.js'
@@ -22,3 +20,2 @@ import { runPreflight } from './preflight.js'
 import { runUpScript, printNextStep } from './boot.js'
-import { pullModels } from './models.js'
 import { down, getBootstrapStatus, logs, printSetupToken } from './compose.js'
@@ -32,3 +29,3 @@
 export function parseArgs(argv) {
-  const flags = { dir: DEFAULT_DIR, model: DEFAULT_CHAT_MODEL, pull: true, yes: false, tag: undefined }
+  const flags = { dir: DEFAULT_DIR, yes: false, tag: undefined }
   const rest = []
@@ -48,11 +45,5 @@ let command
         break
-      case '--model':
-        flags.model = argv[++i] ?? DEFAULT_CHAT_MODEL
-        break
       case '--tag':
         flags.tag = argv[++i]
         break
-      case '--no-pull':
-        flags.pull = false
-        break
       case '--yes':
@@ -181,10 +172,3 @@ case '-y':
 
-  // 5. Model pull (soft-fail).
-  if (flags.pull) {
-    await pullModels(flags.dir, { chatModel: flags.model })
-  } else {
-    ui.step('Skipping model pull (--no-pull). Pull a model later from the wizard.')
-  }
-
-  // 6. Output.
+  // 5. Output.
   printNextStep(flags.dir)
@@ -242,3 +226,3 @@ return 0
   run        (default) pre-flight, materialize assets, write .env, boot the
-             stack, pull local models, print the console URL + next step
+             stack and print the console URL + next step
   down       stop the stack (add -v to also remove volumes / wipe the brain)
@@ -253,4 +237,2 @@ logs       tail stack logs (e.g. \`logs api\`)
   --dir <path>    working directory (default: ~/.connectai-selfhost)
-  --model <name>  chat model to pull (default: ${DEFAULT_CHAT_MODEL})
-  --no-pull       skip the model pull
   --tag <tag>     GHCR image tag to run (default: ${DEFAULT_IMAGE_TAG})
@@ -263,3 +245,3 @@ --yes, -y       non-interactive (already the default; accepted for CI)
   npx @connectai/selfhost run
-  npx @connectai/selfhost run --dir /opt/connectai --no-pull
+  npx @connectai/selfhost run --dir /opt/connectai
   npx @connectai/selfhost token
@@ -266,0 +248,0 @@ npx @connectai/selfhost down -v

package.json

 {
   "name": "@connectai/selfhost",
-  "version": "0.1.8",
-  "description": "One-command self-host installer for ConnectAI. Takes a clean machine (only Docker + Node) to a running, health-checked company-brain in one command, with no source clone and no local image build: `npx @connectai/selfhost run`. Bundles the image-based docker-compose stack + boot scripts, generates a strong .env (CSPRNG ENCRYPTION_SECRET + POSTGRES_PASSWORD), boots the stack, and soft-pulls the local inference models.",
+  "version": "0.1.9",
+  "description": "One-command self-host installer for ConnectAI. Takes a clean machine (only Docker + Node) to a running, health-checked company-brain in one command, with no source clone and no local image build: `npx @connectai/selfhost run`. Bundles the image-based docker-compose stack + boot scripts, generates a strong .env (CSPRNG ENCRYPTION_SECRET + POSTGRES_PASSWORD), and boots the stack.",
   "type": "module",
@@ -6,0 +6,0 @@ "bin": {

README.md

@@ -15,3 +15,3 @@ # @connectai/selfhost
 
-The CLI pulls prebuilt images, writes a hardened `.env`, boots the stack, pulls the local inference models, and prints the console URL + your single next step.
+The CLI pulls prebuilt images, writes a hardened `.env`, boots the stack, and prints the console URL + your single next step. The installed stack is endpoint-first: use your `INFERENCE_*` values to point at an OpenAI-compatible provider, with host-local Ollama as the default starter endpoint.
 
@@ -41,5 +41,4 @@ ## Quick start
 3. **Generate `.env`**: copies the example, then fills the secrets with a CSPRNG (`crypto.randomBytes`): `INFISICAL_*`, **`ENCRYPTION_SECRET`** (32 bytes / 64 hex), and a strong **`POSTGRES_PASSWORD`** (with `DATABASE_URL` updated to match). Written `chmod 600`. **Idempotent**: it never overwrites a value you already set, and a second run is a no-op. Secrets are local-only: never logged, never transmitted.
-4. **Boot**: delegates to the bundled `up.sh`, which `docker compose pull`s the prebuilt images, brings up Infisical, provisions the vault identity, brings up the full stack, and waits for the API `/health` + the console. By default the installer runs the first-party GHCR images at the pinned, pullable tag **`v0.1.7`**: the merged backend image `ghcr.io/connectai-os/connectai-app:v0.1.7` (used by both api + worker roles) plus `ghcr.io/connectai-os/connectai-console:v0.1.7`. You can override the release with `--tag` / `CONNECTAI_IMAGE_TAG`. It also pulls the pinned support images from the compose bundle: `infisical/infisical:v0.159.28`, `pgvector/pgvector:pg16`, `postgres:16-alpine`, `redis:7-alpine`, and `ollama/ollama:latest`.
-5. **Pull models** (`qwen2.5:1.5b` chat + `mxbai-embed-large` embed) into the bundled Ollama. **Soft-fail**: a pull error warns and points at the wizard, it never fails the install.
-6. **Print** the console URL, the setup-token command, and the next step.
+4. **Boot**: delegates to the bundled `up.sh`, which `docker compose pull`s the prebuilt images, brings up Infisical, provisions the vault identity, brings up the full stack, and waits for the API `/health` + the console. By default the installer runs the first-party GHCR images at the pinned, pullable tag **`v0.1.7`**: the merged backend image `ghcr.io/connectai-os/connectai-app:v0.1.7` (used by both api + worker roles) plus `ghcr.io/connectai-os/connectai-console:v0.1.7`. You can override the release with `--tag` / `CONNECTAI_IMAGE_TAG`. It also pulls the pinned support images from the compose bundle: `infisical/infisical:v0.159.28`, `pgvector/pgvector:pg16`, `postgres:16-alpine`, and `redis:7-alpine`.
+5. **Print** the console URL, the setup-token command, and the next step.
 
@@ -50,3 +49,3 @@ ## Command examples
 npx @connectai/selfhost run
-npx @connectai/selfhost run --dir /opt/connectai --no-pull
+npx @connectai/selfhost run --dir /opt/connectai
 npx @connectai/selfhost logs api
@@ -72,4 +71,2 @@ npx @connectai/selfhost token
 | `--dir <path>` | working directory (default `~/.connectai-selfhost`) |
-| `--model <name>` | chat model to pull (default `qwen2.5:1.5b`) |
-| `--no-pull` | skip the model pull |
 | `--tag <tag>` | GHCR image tag to run (default: `v0.1.7`; also `CONNECTAI_IMAGE_TAG`) |
@@ -92,3 +89,3 @@ | `--yes`, `-y` | non-interactive (already the default; accepted for CI) |
 - The packaged installer defaults to the verified `v0.1.7` release tag. If you override it, keep the same tag across your operator docs and rollout notes.
-- The first run downloads several GB (images + models) and can take a few minutes; re-runs are fast and idempotent.
+- The first run downloads several GB of images and can take a few minutes; re-runs are fast and idempotent.
 - This is a thin front door over the same hardened `up.sh` boot engine used by a source checkout; it does not re-implement orchestration.
@@ -95,0 +92,0 @@

lib/models.js

-// Pull the local inference models into the bundled Ollama. SOFT-FAIL by contract
-// (CON-131 scope item 6): a pull failure WARNS and points at the wizard, it never
-// fails the install. The stack is already healthy at this point; models only affect
-// first-query latency.
-import { spawn } from 'node:child_process'
-import { composeArgs, composeEnv } from './compose.js'
-import { DEFAULT_CHAT_MODEL, EMBED_MODEL } from './constants.js'
-import { ui } from './ui.js'
-
-export function pullOne(dir, model, { spawnImpl = spawn, composeEnvImpl = composeEnv } = {}) {
-  return new Promise((resolve) => {
-    // `docker compose exec -T ollama ollama pull <model>` streams progress to the
-    // inherited stdout. -T disables TTY allocation (safe in non-interactive runs).
-    const child = spawnImpl('docker', [...composeArgs(dir), 'exec', '-T', 'ollama', 'ollama', 'pull', model], {
-      stdio: 'inherit',
-      env: composeEnvImpl(dir),
-    })
-    child.on('error', () => resolve(false))
-    child.on('exit', (code) => resolve(code === 0))
-  })
-}
-
-// Pull the chat model (override via --model) + the embedding model. Returns a
-// summary; the caller decides messaging. Always resolves (never rejects).
-export async function pullModels(dir, { chatModel = DEFAULT_CHAT_MODEL } = {}) {
-  const targets = [chatModel, EMBED_MODEL]
-  const results = []
-  for (const model of targets) {
-    ui.step(`Pulling model ${ui.bold(model)} into the bundled Ollama (this can take a while).`)
-    const ok = await pullOne(dir, model)
-    results.push({ model, ok })
-    if (ok) ui.ok(`pulled ${model}`)
-    else ui.warn(`could not pull ${model}; you can pull it later from the setup wizard.`)
-  }
-  return results
-}

New alerts

Long strings

Supply chain risk

Contains long string literals, which may be a sign of obfuscated or packed code.

Found 1 instance in 1 package

Fixed alerts

Long strings

Supply chain risk

Contains long string literals, which may be a sign of obfuscated or packed code.

Found 1 instance in 1 package

Worsened metrics

Total package byte prevSize

83057

-3.86%

Number of package files

16

-5.88%

Lines of code

745

-6.52%

Number of lines in readme file

91

-3.19%

No dependency changes