| """Re-embed existing segment transcripts to a NEW versioned index; never overwrite legacy vectors. |
| Run from repository root: python scripts/reindex-remote.py --source data/index --output data/indexes/MODEL-VERSION |
| Set VRAG_INDEX_DIR to that output before restarting the API. No camera uploads or local inference. |
| """ |
| import argparse |
| import asyncio |
| import json |
| from pathlib import Path |
| import sys |
| sys.path.insert(0, str(Path(__file__).resolve().parent.parent)) |
| import numpy as np |
| from vrag.settings import store |
| from vrag.remote import space_id |
| from vrag.routing import route |
|
|
| async def build(source, output): |
| if output.exists(): |
| raise ValueError('output must be a new versioned directory') |
| _, cfg = store.snapshot() |
| rule = cfg.features.get('rag.text_embeddings') |
| if not rule or rule.strategy != 'single': |
| raise ValueError('configure one remote text embedding provider first') |
| p = cfg.providers[rule.providers[0]] |
| segments = json.loads((source / 'segments.json').read_text()) |
| if not segments: |
| raise ValueError('source has no segments') |
| vectors = [] |
| for s in segments: |
| out, status = await route(cfg, 'rag.text_embeddings', {'text':f'title: {s["title"]} | text: {s["text"]}'}) |
| if not out.embedding: |
| raise ValueError('remote embedding failed: '+str(status)) |
| vectors.append(out.embedding) |
| matrix = np.asarray(vectors, dtype=np.float32) |
| if matrix.ndim != 2 or not np.isfinite(matrix).all(): |
| raise ValueError('invalid embedding matrix') |
| matrix /= np.linalg.norm(matrix, axis=1, keepdims=True) |
| output.mkdir(parents=True) |
| np.save(output / 'text.npy', matrix) |
| (output / 'segments.json').write_text(json.dumps(segments)) |
| (output / 'manifest.json').write_text(json.dumps({'model':p.model, 'embedding_space':space_id(p), 'dimension':matrix.shape[1], 'mrl_dims':[matrix.shape[1]], 'views':{'text':{'count':len(segments)}}, 'segments':len(segments)})) |
| print(f'Created {output}: {len(segments)} segments, {matrix.shape[1]} dimensions. Set VRAG_INDEX_DIR and restart; legacy index unchanged.') |
|
|
| if __name__ == '__main__': |
| parser=argparse.ArgumentParser();parser.add_argument('--source',type=Path,required=True);parser.add_argument('--output',type=Path,required=True) |
| args=parser.parse_args();asyncio.run(build(args.source,args.output)) |
|
|
