> ## Documentation Index
> Fetch the complete documentation index at: https://docs.intelligence-management-platform.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Requirements

> Runtime, infrastructure, and license prerequisites for self-hosting IMP.

This page lists every hard requirement before you start the quickstart. Skipping any of these will cause the deployment to fail at a specific step.

## Node.js

The backend requires Node.js **exactly `22.18.0`**. The `@exulu/backend` package includes a `preinstall` script that checks `process.version` and exits with a non-zero code if the version does not match:

```bash theme={null}
node -e "if (process.version !== 'v22.18.0') { process.exit(1); }"
```

Use [nvm](https://github.com/nvm-sh/nvm) to pin the version. The example repo ships an `.nvmrc`. The Docker images (`Dockerfile.backend`, `Dockerfile.worker`) use `node:22.18.0-slim` explicitly.

## Container base image

Both the backend and worker Dockerfiles use `node:22.18.0-slim` (Debian-based). **Alpine Linux is not supported.** The ONNX runtime binaries that the knowledge-processing stack depends on are not published for Alpine. Switching to an Alpine base image will cause runtime errors during Python environment setup.

## Postgres with pgvector

IMP requires Postgres 13 or later with the `pgvector` extension. The example compose file uses the official `pgvector/pgvector:pg17` image, which ships with the extension pre-installed. On managed Postgres (AWS RDS, Azure, Google Cloud SQL), enable the `pgvector` extension yourself before first boot.

## A second Postgres database for LiteLLM

The LiteLLM proxy needs its own Postgres database for key management and spend tracking. Set `LITELLM_DATABASE_URL` to a connection string pointing to this separate database. It can be on the same Postgres server but must be a different database name.

<Warning>
  Never set `LITELLM_DATABASE_URL` to the same database as the IMP application. The proxy runs schema migrations on startup and will attempt to drop tables that belong to the IMP schema.
</Warning>

## Redis 7

Redis is required when you run workers. Without Redis, BullMQ cannot enqueue or dequeue background jobs (knowledge ingestion, evals, routines). The example compose file uses `redis:7`.

If you deploy without workers (backend only), Redis is optional.

## S3-compatible storage

File uploads require an S3-compatible bucket. Supported targets include MinIO (local) and AWS S3 (production). The bucket must be created before you start the backend — IMP does not create buckets automatically.

Supply the bucket details via the `COMPANION_S3_*` environment variables.

## Version pins

The following component versions are tested and pinned. Do not upgrade these without testing — the pins exist because upstream releases have broken compatibility.

| Component              | Pinned version                                     | Source                               |
| ---------------------- | -------------------------------------------------- | ------------------------------------ |
| Node.js                | `22.18.0` (exact)                                  | `backend/package.json` engines field |
| `litellm[proxy]`       | `1.85.1`                                           | `backend/ee/python/requirements.txt` |
| `prisma` (Python)      | `0.15.0`                                           | `backend/ee/python/requirements.txt` |
| `torch` / `torchaudio` | `2.5.1`                                            | `backend/ee/python/requirements.txt` |
| pgvector image         | `pgvector/pgvector:pg17`                           | `docker-compose.services.yml`        |
| MinIO image            | `quay.io/minio/minio:RELEASE.2025-04-22T22-12-26Z` | `docker-compose.services.yml`        |
| Redis image            | `redis:7`                                          | `docker-compose.services.yml`        |

### Notes on the Python pins

* **`litellm[proxy]==1.85.1`** — the tested version for the embedded proxy. LiteLLM's API surface changes frequently; upgrade deliberately.
* **`prisma==0.15.0`** — not included in `litellm[proxy]` at this version; pinned separately so the LiteLLM database integration works.
* **`torch==2.5.1`** — pinned because `pyannote.audio` (used for speaker diarization in transcription) imports `torchaudio.AudioMetaData`, which was removed in torch 2.6+.
* **`transformers>=4.48,<5`** — the 5.x line removed a kwarg that `pyannote.audio` 3.x still passes to `hf_hub_download()`.

## GPU (optional — Whisper transcription only)

The Whisper transcription server uses WhisperX with CUDA acceleration. Required only if you use the meeting transcription feature.

* CUDA `12.4`
* NVIDIA driver `≥ 550`
* At least 8 GB VRAM recommended for the default model size

## Hardware guidance

| Service  | Minimum                    | Notes                                                                                                           |
| -------- | -------------------------- | --------------------------------------------------------------------------------------------------------------- |
| Backend  | 2 vCPU, 2 GB RAM           | LiteLLM proxy runs in the same process                                                                          |
| Worker   | 2 vCPU, **8 GB RAM**       | `--max-old-space-size=8192` is set in the start script; below 8 GB the Node.js heap will OOM on large documents |
| Postgres | 2 vCPU, 4 GB RAM           | Scale with the number of knowledge chunks                                                                       |
| Redis    | 1 vCPU, 1 GB RAM           | Queue depth is typically low                                                                                    |
| MinIO    | 1 vCPU, 1 GB RAM + storage | Size storage to your file upload volume                                                                         |