Embed Dim Env Var (#988)

This commit is contained in:
Yuhong Sun 2024-01-23 19:32:51 -08:00 committed by GitHub
parent 5d26290c5d
commit bcc40224fa
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 3 additions and 1 deletions

View File

@ -14,7 +14,7 @@ DOCUMENT_ENCODER_MODEL = (
os.environ.get("DOCUMENT_ENCODER_MODEL") or "thenlper/gte-small"
)
# If the below is changed, Vespa deployment must also be changed
DOC_EMBEDDING_DIM = 384
DOC_EMBEDDING_DIM = int(os.environ.get("DOC_EMBEDDING_DIM") or 0)
# Model should be chosen with 512 context size, ideally don't change this
DOC_EMBEDDING_CONTEXT_SIZE = 512
NORMALIZE_EMBEDDINGS = (

View File

@ -54,6 +54,7 @@ services:
- WEB_DOMAIN=${WEB_DOMAIN:-} # For frontend redirect auth purpose
# Don't change the NLP model configs unless you know what you're doing
- DOCUMENT_ENCODER_MODEL=${DOCUMENT_ENCODER_MODEL:-}
- DOC_EMBEDDING_DIM=${DOC_EMBEDDING_DIM:-}
- NORMALIZE_EMBEDDINGS=${NORMALIZE_EMBEDDINGS:-}
- ASYM_QUERY_PREFIX=${ASYM_QUERY_PREFIX:-}
- ENABLE_RERANKING_REAL_TIME_FLOW=${ENABLE_RERANKING_REAL_TIME_FLOW:-}
@ -116,6 +117,7 @@ services:
- WEB_DOMAIN=${WEB_DOMAIN:-} # For frontend redirect auth purpose for OAuth2 connectors
# Don't change the NLP model configs unless you know what you're doing
- DOCUMENT_ENCODER_MODEL=${DOCUMENT_ENCODER_MODEL:-}
- DOC_EMBEDDING_DIM=${DOC_EMBEDDING_DIM:-}
- NORMALIZE_EMBEDDINGS=${NORMALIZE_EMBEDDINGS:-}
- ASYM_QUERY_PREFIX=${ASYM_QUERY_PREFIX:-} # Needed by DanswerBot
- ASYM_PASSAGE_PREFIX=${ASYM_PASSAGE_PREFIX:-}