Mirrors/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui.git synced 2025-12-16 20:07:49 +01:00
Code Issues Packages Projects Releases Wiki Activity

fixes and updates

Browse Source
This commit is contained in:
Jannik Streidl
2024-04-02 14:47:52 +02:00
parent 5558514ff1 099b1d066b
commit 9bcb37ea10
6 changed files with 150 additions and 81 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
backend/config.py
View File

@@ -253,6 +253,8 @@ OLLAMA_API_BASE_URL = os.environ.get(
OLLAMA_BASE_URL = os.environ.get("OLLAMA_BASE_URL", "")
K8S_FLAG = os.environ.get("K8S_FLAG", "")
USE_OLLAMA_DOCKER = os.environ.get("USE_OLLAMA_DOCKER", "false")
if OLLAMA_BASE_URL == "" and OLLAMA_API_BASE_URL != "":
OLLAMA_BASE_URL = (
@@ -263,7 +265,12 @@ if OLLAMA_BASE_URL == "" and OLLAMA_API_BASE_URL != "":
if ENV == "prod":
if OLLAMA_BASE_URL == "/ollama":
OLLAMA_BASE_URL = "http://host.docker.internal:11434"
if USE_OLLAMA_DOCKER.lower() == "true":
# if you use all-in-one docker container (Open WebUI + Ollama)
# with the docker build arg USE_OLLAMA=true (--build-arg="USE_OLLAMA=true") this only works with http://localhost:11434
OLLAMA_BASE_URL = "http://localhost:11434"
else:
OLLAMA_BASE_URL = "http://host.docker.internal:11434"
elif K8S_FLAG:
OLLAMA_BASE_URL = "http://ollama-service.open-webui.svc.cluster.local:11434"
@@ -384,10 +391,16 @@ 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)
RAG_EMBEDDING_MODEL = os.environ.get("RAG_EMBEDDING_MODEL", "all-MiniLM-L6-v2")
log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL}"),
# device type ebbeding models - "cpu" (default), "cuda" (nvidia gpu required) or "mps" (apple silicon) - choosing this right can lead to better performance
RAG_EMBEDDING_MODEL_DEVICE_TYPE = os.environ.get(
"RAG_EMBEDDING_MODEL_DEVICE_TYPE", "cpu"
)
USE_CUDA = os.environ.get("USE_CUDA_DOCKER", "false")
if USE_CUDA.lower() == "true":
DEVICE_TYPE = "cuda"
else:
DEVICE_TYPE = "cpu"
CHROMA_CLIENT = chromadb.PersistentClient(
path=CHROMA_DATA_PATH,
settings=Settings(allow_reset=True, anonymized_telemetry=False),