Repository navigation
Make Docling dependencies optional #18
Description
Problem
The project requires heavyweight Docling dependencies for the whole environment, even when ingestion is not used. This slows setup, increases install size, and makes basic RAG usage unnecessarily heavy.
Goal
Decouple Docling (and related OCR/ML libs) so they are optional and only required for ingestion workflows. Core RAG/chat/search should run without Docling installed.
Ideas
- Move Docling-related deps into an optional dependency group (e.g.
dependency-groups.doclingorextrainpyproject.toml). - Gate Docling imports behind feature flags or lazy imports in ingestion module.
- Provide clear error message when ingestion is invoked without Docling extras.
- Document optional install in README (e.g.
uv sync --group docling).
Acceptance Criteria
- Base install does not pull Docling/ML/OCR deps.
- Ingestion works when optional deps are installed.
- Running chat/search without optional deps does not fail.
Activity
FullFran commentedon Jan 26, 2026
Plan de acción inmediato
Priorizamos velocidad. Los tests de RAG/Agent no necesitan Docling.
Paso 1: Separar dependencias
docling,docling-core,transformers,openai-whispera grupo opcionalingestion.pydantic,openai,supabase,pymongo,rich.Paso 2: Gate imports
src/infrastructure/ingestion/hacer lazy import con error claro si falta.Paso 3: Documentar
uv syncpara core,uv sync --group ingestionpara ingest.Esto nos permite correr tests sin esperar 2GB de CUDA/torch.
build: make Docling deps optional for lightweight installs
refactor(core)!: separar acceso destructivo, mover el umbral a la apl…