paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-05-23 12:58:18 -05:00
Code Issues Packages Projects Releases Wiki Activity

Create llmindex if doesnt exist on update run

Browse Source
This commit is contained in:
shamoon 2025-04-29 19:25:39 -07:00
parent c5f618d822
commit 51a7581860
No known key found for this signature in database
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
src/paperless_ai/indexing.py
View File

@ -1,5 +1,6 @@
import logging import logging
import shutil import shutil
from pathlib import Path
import faiss import faiss
import llama_index.core.settings as llama_settings import llama_index.core.settings as llama_settings
@ -125,11 +126,15 @@ def update_llm_index(*, progress_bar_disable=False, rebuild=False):
logger.warning("No documents found to index.") logger.warning("No documents found to index.")
return return
if rebuild: if (
rebuild
or not Path(settings.LLM_INDEX_DIR / "default__vector_store.json").exists()
):
# Rebuild index from scratch
logger.info("Rebuilding LLM index.")
embed_model = get_embedding_model() embed_model = get_embedding_model()
llama_settings.Settings.embed_model = embed_model llama_settings.Settings.embed_model = embed_model
storage_context = get_or_create_storage_context(rebuild=rebuild) storage_context = get_or_create_storage_context(rebuild=True)
# Rebuild index from scratch
for document in tqdm.tqdm(documents, disable=progress_bar_disable): for document in tqdm.tqdm(documents, disable=progress_bar_disable):
document_nodes = build_document_node(document) document_nodes = build_document_node(document)
nodes.extend(document_nodes) nodes.extend(document_nodes)