pyr0ball
89a58ec9b0
Bi-encoder embeddings collapse a whole query into one vector, losing multi-part reasoning structure — queries like "the procedure for setting an IP on an AVC-X" or "what is the action economy for a fighter casting a spell while prone" lose nuance. Agent-ModernColBERT is a late-interaction retriever: per-token embeddings, scored via MaxSim at query time, built specifically for agentic/multi-hop queries. Implements Option A from the issue (in-process, via `pylate`) rather than Option B (managed cf-orch service) — cf-orch already has `agent-moderncolbert` registered in model_registry.yaml with a `pagepiper/retrieve` assignment in assignments.yaml pointing at it and referencing this issue directly, someone had already pre-wired that side. - app/services/colbert_index.py: new ColBERTIndex class, mirrors BM25Index's dirty-flag/rebuild-from-SQLite pattern exactly — no separate per-shelve indexing step needed, just mark_dirty() on the same callback that already marks BM25 dirty. - app/services/retriever.py: hybrid_search's semantic half now merges BM25 with ColBERT MaxSim scores (min-max normalized per-batch, since MaxSim is unbounded unlike the old sqlite-vec L2-distance path) instead of Ollama-embed + sqlite-vec cosine. BM25 merge/rank/per-doc-cap/ adjacent-chunk-window logic is unchanged. - app/main.py / app/deps.py: per-user ColBERTIndex registry, same pattern as the existing per-user BM25Index registry. - Existing BYOK tier gate preserved exactly (llm is None check) — this is a retrieval-technology swap, not a tier/licensing change. The ColBERT model runs locally via pylate with no Ollama dependency, but gating still follows product tiering. - 12 new tests. pylate is intentionally NOT installed in the dev/test env — see the cf-sysadmin skill's "Known Gotchas" for why (installing it directly into the shared `cf` conda env broke several other services' torch/transformers pins on 2026-07-10). Tests inject fake pylate modules via sys.modules instead. Known follow-up (not addressed here): shelve scripts still compute and store Ollama embeddings into `page_vecs` at shelve time — that table is no longer read by search/chat now that retrieval uses the ColBERT index. Removing the now-redundant embedding step is separate cleanup. Closes: #8
28 lines
650 B
TOML
28 lines
650 B
TOML
[build-system]
|
|
requires = ["setuptools>=68", "wheel"]
|
|
build-backend = "setuptools.build_meta"
|
|
|
|
[project]
|
|
name = "pagepiper"
|
|
version = "0.1.0"
|
|
description = "Self-hosted PDF library manager with RAG chat and page-level citations"
|
|
readme = "README.md"
|
|
requires-python = ">=3.11"
|
|
dependencies = [
|
|
"fastapi>=0.110",
|
|
"uvicorn[standard]>=0.29",
|
|
"python-multipart>=0.0.9",
|
|
"rank-bm25>=0.2",
|
|
"PyYAML>=6.0",
|
|
"httpx>=0.27",
|
|
"circuitforge-core[pdf,vector]>=0.19.0",
|
|
"pylate[voyager]>=1.6",
|
|
]
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["."]
|
|
include = ["app*"]
|
|
|
|
[tool.pytest.ini_options]
|
|
testpaths = ["tests"]
|
|
asyncio_mode = "auto"
|