dierk/vector-search-demo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
22 Commits 1 Branch 9 Tags
978c70e91ae9a730ace17fa0fc800a8acc9cc814
Commit Graph

9 Commits

Author SHA1 Message Date
dierk 4a82352391 Document CLIP model source in embedder.py and README 
Model downloads automatically from HuggingFace Hub on first use.
No manual download required.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-20 12:04:10 +02:00
dierk 3ef43019be Add in-DB indexing script, benchmark results, schema names in presentation 
- index_images_indb.py: new script indexing via VECTOR_EMBEDDING(CLIP_IMG)
  using a two-step INSERT+UPDATE to work around ORA-24816
- index_images_oracle.py / index_images.py: add timing output
- Presentation: schema names VECTORS_USER/VECTOR in diagram and comparison,
  ONNX expansion, HNSW index note on slide 11,
  indexing times updated from 3-run benchmark (avg: PG 12.1s, Ora 12.1s, InDB 13.6s)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-20 10:42:13 +02:00
dierk 26ce44e186 Add lightbox to all three frontends — click photo to view full size 
Click any result image to open it in a dark overlay. Click anywhere or
press Escape to close. Score colour matches each frontend's accent colour.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-19 15:15:52 +02:00
dierk 1c5e00d8e4 Add targeted comments explaining non-obvious behaviour 
- embedder.py: lazy model load rationale, RGB conversion, shared vector space
- main.py: why vec appears twice, ::vector cast, 1-distance score formula
- main_oracle.py: why array.array("f") is required instead of plain list
- main_oracle_indb.py: no embedder import — embedding done inside Oracle SQL
- index_images_oracle.py: same array.array requirement on indexing path

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-19 14:39:40 +02:00
dierk 3dcb98f82f Add requirements.txt for both backends 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-19 12:04:43 +02:00
dierk bc4b871cfb Add .env.example templates and document configuration in README 
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-19 12:03:53 +02:00
dierk d360ff1a78 Add SQL setup scripts for all three backends 
- pgvector-demo/sql/setup.sql: enable pgvector extension, create images table and HNSW index
- oravector-demo/sql/setup_vectors_user.sql: create vectors_user, images table and HNSW vector index
- oravector-demo/sql/setup_vector_schema.sql: create VECTOR user, load CLIP ONNX models, create FOTO_VEKTOR table

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-19 12:00:58 +02:00
dierk 4e68b2f226 Serve frontends via FastAPI static files to fix Brave browser file access block 
Each backend now mounts its frontend directory at /ui/ so the UIs are
accessible via http://localhost:800x/ui/ instead of file:// URLs.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-19 11:40:42 +02:00
dierk 66f7db40b0 Initial implementation of pgvector and Oracle 26ai vector search demo 
Three FastAPI backends comparing PostgreSQL/pgvector and Oracle 26ai for
semantic image search using CLIP embeddings: Python-side embedding for both
databases, plus Oracle in-database embedding via VECTOR_EMBEDDING(CLIP_TXT).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-05-19 11:33:16 +02:00