From a29e6fc250af7947159deddaa2031b43ddf18f7f Mon Sep 17 00:00:00 2001 From: Richard R Date: Thu, 21 May 2026 20:57:10 -0600 Subject: [PATCH] docs(compute): align worker env docs and model override vars --- .env.example | 3 +++ compute/worker/.env.example | 4 ++++ docs-site/docs/deploy/compute-worker.md | 4 ++++ 3 files changed, 11 insertions(+) diff --git a/.env.example b/.env.example index 71e4d4b..cb40fba 100644 --- a/.env.example +++ b/.env.example @@ -88,6 +88,9 @@ COMPUTE_MODE=local # - local compute runtime # - worker compute runtime # - worker client wait budgets +# Optional local compute concurrency (in-process compute only). +# Worker mode uses compute-worker service `COMPUTE_JOB_CONCURRENCY` instead. +# COMPUTE_JOB_CONCURRENCY=1 # COMPUTE_WHISPER_TIMEOUT_MS=30000 # COMPUTE_PDF_TIMEOUT_MS=300000 # Worker mode requires worker-reachable shared object storage. diff --git a/compute/worker/.env.example b/compute/worker/.env.example index 4e2a6b6..941c118 100644 --- a/compute/worker/.env.example +++ b/compute/worker/.env.example @@ -33,6 +33,10 @@ S3_FORCE_PATH_STYLE=true # COMPUTE_JOB_CONCURRENCY=1 # COMPUTE_WHISPER_TIMEOUT_MS=30000 # COMPUTE_PDF_TIMEOUT_MS=300000 +# Optional Whisper ONNX base URL override (must contain all expected files) +# WHISPER_MODEL_BASE_URL=https://huggingface.co/onnx-community/whisper-base_timestamped/resolve/main +# Optional PDF layout ONNX base URL override (must contain all expected files) +# PDF_LAYOUT_MODEL_BASE_URL=https://huggingface.co/Bei0001/PP-DocLayoutV3-ONNX/resolve/main # COMPUTE_PDF_JOB_ATTEMPTS=1 # COMPUTE_JOBS_STREAM_MAX_BYTES=268435456 # COMPUTE_JOB_STATES_MAX_BYTES=67108864 diff --git a/docs-site/docs/deploy/compute-worker.md b/docs-site/docs/deploy/compute-worker.md index 7b0fc91..abea144 100644 --- a/docs-site/docs/deploy/compute-worker.md +++ b/docs-site/docs/deploy/compute-worker.md @@ -51,6 +51,8 @@ Advanced tuning (usually leave unset unless you need overrides): - `COMPUTE_JOB_CONCURRENCY=1` (shared total compute jobs across whisper + PDF) - `COMPUTE_WHISPER_TIMEOUT_MS=30000` - `COMPUTE_PDF_TIMEOUT_MS=300000` +- `WHISPER_MODEL_BASE_URL=https://huggingface.co/onnx-community/whisper-base_timestamped/resolve/main` (optional override) +- `PDF_LAYOUT_MODEL_BASE_URL=https://huggingface.co/Bei0001/PP-DocLayoutV3-ONNX/resolve/main` (optional override) - `COMPUTE_PDF_JOB_ATTEMPTS=1` (PDF layout retry attempts) - `COMPUTE_JOBS_STREAM_MAX_BYTES=268435456` (256MB JetStream jobs stream cap) - `COMPUTE_JOB_STATES_MAX_BYTES=67108864` (64MB JetStream KV bucket cap) @@ -126,6 +128,8 @@ COMPUTE_WORKER_TOKEN= # COMPUTE_JOB_CONCURRENCY=1 # COMPUTE_WHISPER_TIMEOUT_MS=30000 # COMPUTE_PDF_TIMEOUT_MS=300000 +# WHISPER_MODEL_BASE_URL=https://huggingface.co/onnx-community/whisper-base_timestamped/resolve/main +# PDF_LAYOUT_MODEL_BASE_URL=https://huggingface.co/Bei0001/PP-DocLayoutV3-ONNX/resolve/main # COMPUTE_PDF_JOB_ATTEMPTS=1 # COMPUTE_JOBS_STREAM_MAX_BYTES=268435456 # COMPUTE_JOB_STATES_MAX_BYTES=67108864