pyr0ball
f941ebdeeb
Extends Pagepiper's document shelving pipeline (renamed from "ingest" — see below) to cover the formats most likely to appear in a real-world engineering document corpus, prompted by scoping a STERIS licensing pitch that needs DOCX/ODT coverage. - Rename the ingest pipeline to "shelve" throughout (scripts/, app/api, tests, docs, frontend). "Glean" (Turnstone's term) was considered and rejected — that's a harvest metaphor for log/knowledge extraction, not a fit for documents entering a library. Documented as a general CF naming principle in the org-level CLAUDE.md. - Wire DOCX into the upload/scan UI, README, and docs — the extraction logic (heading-based chunking, table serialization) already existed but wasn't exposed to users or covered by tests. - Add ODT support via odfpy, mirroring DOCX's chunking strategy. - Add Apple Pages support via headless LibreOffice conversion to ODT. No maintained Python library parses the IWA format directly; libreoffice bundles libetonyek, the only real open-source Pages parser. Adds libreoffice-writer to the Docker image (~300-400MB) for this. - 24 new/updated tests across shelve_docx, shelve_odt, and shelve_pages; full suite (72 tests) passing. Known gaps not addressed here: no Windchill/DocPortal connector exists yet (metadata-only PowerShell recon only), Excel/.xlsx is unsupported, and circuitforge_core.tasks.dispatch_task does not currently exist in circuitforge-core — cf-orch dispatch is dead code, always falling through to local BackgroundTasks. See circuitforge-plans/pagepiper/superpowers/plans/2026-07-10-steris-licensing-pitch.md for the full writeup.
49 lines
1.4 KiB
Markdown
49 lines
1.4 KiB
Markdown
# Ollama Setup
|
|
|
|
Hybrid vector search and RAG chat are gated behind a local Ollama instance. This is the BYOK (bring your own key) unlock for the Free tier — no paid subscription required.
|
|
|
|
## Install Ollama
|
|
|
|
```bash
|
|
curl -fsSL https://ollama.ai/install.sh | sh
|
|
```
|
|
|
|
## Pull the required models
|
|
|
|
```bash
|
|
# Embedding model — converts pages into vectors
|
|
ollama pull nomic-embed-text
|
|
|
|
# Chat model — answers questions using retrieved page excerpts
|
|
ollama pull mistral:7b
|
|
```
|
|
|
|
`nomic-embed-text` produces 1024-dimensional vectors and runs comfortably on 8 GB of VRAM.
|
|
`mistral:7b` requires roughly 5 GB of VRAM. Substitute any compatible model.
|
|
|
|
## Configure Pagepiper
|
|
|
|
In your `.env`:
|
|
|
|
```bash
|
|
PAGEPIPER_OLLAMA_URL=http://localhost:11434
|
|
PAGEPIPER_EMBED_MODEL=nomic-embed-text
|
|
PAGEPIPER_CHAT_MODEL=mistral:7b
|
|
```
|
|
|
|
Restart Pagepiper:
|
|
|
|
```bash
|
|
./manage.sh restart
|
|
```
|
|
|
|
## Verify
|
|
|
|
Upload or re-index a document. The document card should show **Embedding N / M pages** while shelving. Once complete, the Chat tab becomes active.
|
|
|
|
## Changing embedding models
|
|
|
|
If you switch `PAGEPIPER_EMBED_MODEL`, Pagepiper detects the dimension mismatch at startup, deletes the old vector database, and automatically re-embeds all indexed documents in the background. BM25 search remains available throughout.
|
|
|
|
!!! note
|
|
Re-embedding a large library can take 30-60 minutes depending on hardware.
|