Mirrors/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2025-12-16 03:47:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

feat: move to native sentence_transformer

Browse Source
This commit is contained in:
Steven Kreitzer
2024-04-22 13:27:43 -05:00
parent 22c50f62cb
commit f3e5700d49
7 changed files with 153 additions and 268 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
backend/config.py
View File

@@ -411,18 +411,19 @@ if WEBUI_AUTH and WEBUI_SECRET_KEY == "":
####################################
CHROMA_DATA_PATH = f"{DATA_DIR}/vector_db"
# this uses the model defined in the Dockerfile ENV variable. If you dont use docker or docker based deployments such as k8s, the default embedding model will be used (all-MiniLM-L6-v2)
# this uses the model defined in the Dockerfile ENV variable. If you dont use docker or docker based deployments such as k8s, the default embedding model will be used (sentence-transformers/all-MiniLM-L6-v2)
RAG_EMBEDDING_ENGINE = os.environ.get("RAG_EMBEDDING_ENGINE", "")
RAG_EMBEDDING_MODEL = os.environ.get("RAG_EMBEDDING_MODEL", "all-MiniLM-L6-v2")
RAG_EMBEDDING_MODEL = os.environ.get(
"RAG_EMBEDDING_MODEL", "sentence-transformers/all-MiniLM-L6-v2"
)
log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL}"),
RAG_EMBEDDING_MODEL_AUTO_UPDATE = (
os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "").lower() == "true"
RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE = (
os.environ.get("RAG_EMBEDDING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
)
# device type embedding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
USE_CUDA = os.environ.get("USE_CUDA_DOCKER", "false")