knowledge/__init__.py

"""EvoLLM knowledge layer — RAG + LoRA-on-upload.

Components:
- parser             : PDF / TXT / MD / DOCX → clean text
- chunker            : long text → overlapping ~400-token chunks
- embedder           : fastembed wrapper (no torch dependency)
- store              : SQLite + numpy vector store
- pipeline           : high-level ingest / query API
- dataset_builder    : doc chunks → training JSONL
- notebook_generator : produce a Colab notebook with the dataset baked in
- adapter_importer   : accept uploaded GGUF + manifest, register an adapter

Local persistence at data/knowledge.sqlite + data/adapters/. On HF Spaces
the path is the container's ephemeral disk, so uploads vanish on rebuild
— there's a visible notice in the UI explaining that.
"""

from .adapter_importer import import_adapter
from .dataset_builder import build_dataset, write_jsonl
from .notebook_generator import generate_training_notebook
from .pipeline import KnowledgePipeline
from .store import KnowledgeStore

__all__ = [
    "KnowledgePipeline",
    "KnowledgeStore",
    "build_dataset",
    "write_jsonl",
    "generate_training_notebook",
    "import_adapter",
]