Merge pull request #5311 from open-webui/dev

dev

backend/open_webui/apps/audio/main.py

@@ -21,14 +21,14 @@ from open_webui.config import (
     AUDIO_TTS_VOICE,
     CACHE_DIR,
     CORS_ALLOW_ORIGIN,
-    DEVICE_TYPE,
     WHISPER_MODEL,
     WHISPER_MODEL_AUTO_UPDATE,
     WHISPER_MODEL_DIR,
     AppConfig,
 )
+
 from open_webui.constants import ERROR_MESSAGES
-from open_webui.env import SRC_LOG_LEVELS
+from open_webui.env import SRC_LOG_LEVELS, DEVICE_TYPE
 from fastapi import Depends, FastAPI, File, HTTPException, Request, UploadFile, status
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import FileResponse

backend/open_webui/apps/rag/main.py

@@ -44,7 +44,6 @@ from open_webui.config import (
     CHUNK_SIZE,
     CONTENT_EXTRACTION_ENGINE,
     CORS_ALLOW_ORIGIN,
-    DEVICE_TYPE,
     DOCS_DIR,
     ENABLE_RAG_HYBRID_SEARCH,
     ENABLE_RAG_LOCAL_WEB_FETCH,

backend/open_webui/config.py

@@ -539,40 +539,6 @@ Path(TOOLS_DIR).mkdir(parents=True, exist_ok=True)
 FUNCTIONS_DIR = os.getenv("FUNCTIONS_DIR", f"{DATA_DIR}/functions")
 Path(FUNCTIONS_DIR).mkdir(parents=True, exist_ok=True)
 
-
-####################################
-# LITELLM_CONFIG
-####################################
-
-
-def create_config_file(file_path):
-    directory = os.path.dirname(file_path)
-
-    # Check if directory exists, if not, create it
-    if not os.path.exists(directory):
-        os.makedirs(directory)
-
-    # Data to write into the YAML file
-    config_data = {
-        "general_settings": {},
-        "litellm_settings": {},
-        "model_list": [],
-        "router_settings": {},
-    }
-
-    # Write data to YAML file
-    with open(file_path, "w") as file:
-        yaml.dump(config_data, file)
-
-
-LITELLM_CONFIG_PATH = f"{DATA_DIR}/litellm/config.yaml"
-
-# if not os.path.exists(LITELLM_CONFIG_PATH):
-#     log.info("Config file doesn't exist. Creating...")
-#     create_config_file(LITELLM_CONFIG_PATH)
-#     log.info("Config file created successfully.")
-
-
 ####################################
 # OLLAMA_BASE_URL
 ####################################
@@ -922,7 +888,7 @@ TOOLS_FUNCTION_CALLING_PROMPT_TEMPLATE = PersistentConfig(
 
 
 ####################################
-# RAG document content extraction
+# Vector Database
 ####################################
 
 VECTOR_DB = os.environ.get("VECTOR_DB", "chroma")
@@ -1051,34 +1017,6 @@ RAG_RERANKING_MODEL_TRUST_REMOTE_CODE = (
     os.environ.get("RAG_RERANKING_MODEL_TRUST_REMOTE_CODE", "").lower() == "true"
 )
 
-
-if CHROMA_HTTP_HOST != "":
-    CHROMA_CLIENT = chromadb.HttpClient(
-        host=CHROMA_HTTP_HOST,
-        port=CHROMA_HTTP_PORT,
-        headers=CHROMA_HTTP_HEADERS,
-        ssl=CHROMA_HTTP_SSL,
-        tenant=CHROMA_TENANT,
-        database=CHROMA_DATABASE,
-        settings=Settings(allow_reset=True, anonymized_telemetry=False),
-    )
-else:
-    CHROMA_CLIENT = chromadb.PersistentClient(
-        path=CHROMA_DATA_PATH,
-        settings=Settings(allow_reset=True, anonymized_telemetry=False),
-        tenant=CHROMA_TENANT,
-        database=CHROMA_DATABASE,
-    )
-
-
-# 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")
-
-if USE_CUDA.lower() == "true":
-    DEVICE_TYPE = "cuda"
-else:
-    DEVICE_TYPE = "cpu"
-
 CHUNK_SIZE = PersistentConfig(
     "CHUNK_SIZE", "rag.chunk_size", int(os.environ.get("CHUNK_SIZE", "1500"))
 )

backend/open_webui/env.py

@@ -32,6 +32,15 @@ except ImportError:
     print("dotenv not installed, skipping...")
 
 
+# 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")
+
+if USE_CUDA.lower() == "true":
+    DEVICE_TYPE = "cuda"
+else:
+    DEVICE_TYPE = "cpu"
+
+
 ####################################
 # LOGGING
 ####################################