diff --git a/.gitignore b/.gitignore index 247d3bd..af82761 100644 --- a/.gitignore +++ b/.gitignore @@ -8,7 +8,7 @@ models/ # Vector stores (large, rebuild with build scripts) store/ -storage_clippings/ +clippings_search/store_clippings/ # Data (symlinks to private files) data diff --git a/README.md b/README.md index 2552be2..8e4ff30 100644 --- a/README.md +++ b/README.md @@ -24,11 +24,11 @@ ssearch/ ├── run_query.sh # Interactive shell wrapper with timing and logging ├── clippings_search/ │ ├── build_clippings.py # Build/update clippings vector store (ChromaDB) -│ └── retrieve_clippings.py # Verbatim clippings chunk retrieval +│ ├── retrieve_clippings.py # Verbatim clippings chunk retrieval +│ └── store_clippings/ # Persisted clippings vector store (ChromaDB) ├── data/ # Symlink to journal .txt files ├── clippings/ # Symlink to clippings (PDFs, TXT, webarchive, RTF) ├── store/ # Persisted journal vector store -├── storage_clippings/ # Persisted clippings vector store (ChromaDB) ├── models/ # Cached HuggingFace models (offline) ├── archived/ # Superseded script versions ├── saved_output/ # Saved query results and model comparisons diff --git a/clippings_search/build_clippings.py b/clippings_search/build_clippings.py index b808e92..a12c869 100644 --- a/clippings_search/build_clippings.py +++ b/clippings_search/build_clippings.py @@ -37,7 +37,7 @@ import time # Shared constants DATA_DIR = Path("./clippings") -PERSIST_DIR = "./storage_clippings" +PERSIST_DIR = "./clippings_search/store_clippings" COLLECTION_NAME = "clippings" EMBED_MODEL_NAME = "BAAI/bge-large-en-v1.5" CHUNK_SIZE = 256 diff --git a/clippings_search/retrieve_clippings.py b/clippings_search/retrieve_clippings.py index 2cb0c9e..a96995c 100644 --- a/clippings_search/retrieve_clippings.py +++ b/clippings_search/retrieve_clippings.py @@ -27,7 +27,7 @@ import textwrap # Globals # -PERSIST_DIR = "./storage_clippings" +PERSIST_DIR = "./clippings_search/store_clippings" COLLECTION_NAME = "clippings" # Embedding model (must match build_clippings.py)