Merge pull request #2856 from open-webui/dev

0.2.5

.github/pull_request_template.md

@@ -11,7 +11,7 @@
 - [ ] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation?
 - [ ] **Testing:** Have you written and run sufficient tests for validating the changes?
 - [ ] **Code review:** Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
-- [ ] **Label:** To cleary categorize this pull request, assign a relevant label to the pull request title, using one of the following:
+- [ ] **Prefix:** To cleary categorize this pull request, prefix the pull request title, using one of the following:
   - **BREAKING CHANGE**: Significant changes that may affect compatibility
   - **build**: Changes that affect the build system or external dependencies
   - **ci**: Changes to our continuous integration processes or workflows

CHANGELOG.md

@@ -5,6 +5,19 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.5] - 2024-06-05
+
+### Added
+
+- **👥 Active Users Indicator**: Now you can see how many people are currently active and what they are running. This helps you gauge when performance might slow down due to a high number of users.
+- **🗂️ Create Ollama Modelfile**: The option to create a modelfile for Ollama has been reintroduced in the Settings > Models section, making it easier to manage your models.
+- **⚙️ Default Model Setting**: Added an option to set the default model from Settings > Interface. This feature is now easily accessible, especially convenient for mobile users as it was previously hidden.
+- **🌐 Enhanced Translations**: We've improved the Chinese translations and added support for Turkmen and Norwegian languages to make the interface more accessible globally.
+
+### Fixed
+
+- **📱 Mobile View Improvements**: The UI now uses dvh (dynamic viewport height) instead of vh (viewport height), providing a better and more responsive experience for mobile users.
+
 ## [0.2.4] - 2024-06-03
 
 ### Added

README.md

@@ -11,7 +11,7 @@
 [![Discord](https://img.shields.io/badge/Discord-Open_WebUI-blue?logo=discord&logoColor=white)](https://discord.gg/5rJgQTnV4s)
 [![](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86)](https://github.com/sponsors/tjbck)
 
-Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI designed to operate entirely offline. It supports various LLM runners, including Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
+Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-rich, and user-friendly self-hosted WebUI designed to operate entirely offline. It supports various LLM runners, including Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
 
 ![Open WebUI Demo](./demo.gif)
 

backend/apps/ollama/main.py

@@ -274,12 +274,13 @@ async def get_ollama_tags(
 @app.get("/api/version")
 @app.get("/api/version/{url_idx}")
 async def get_ollama_versions(url_idx: Optional[int] = None):
-
+    if app.state.config.ENABLE_OLLAMA_API:
         if url_idx == None:
 
             # returns lowest version
             tasks = [
-            fetch_url(f"{url}/api/version") for url in app.state.config.OLLAMA_BASE_URLS
+                fetch_url(f"{url}/api/version")
+                for url in app.state.config.OLLAMA_BASE_URLS
             ]
             responses = await asyncio.gather(*tasks)
             responses = list(filter(lambda x: x is not None, responses))
@@ -322,6 +323,8 @@ async def get_ollama_versions(url_idx: Optional[int] = None):
                     status_code=r.status_code if r else 500,
                     detail=error_detail,
                 )
+    else:
+        return {"version": False}
 
 
 class ModelNameForm(BaseModel):

backend/apps/rag/main.py

@@ -1164,6 +1164,30 @@ def reset_vector_db(user=Depends(get_admin_user)):
     CHROMA_CLIENT.reset()
 
 
+@app.get("/reset/uploads")
+def reset_upload_dir(user=Depends(get_admin_user)) -> bool:
+    folder = f"{UPLOAD_DIR}"
+    try:
+        # Check if the directory exists
+        if os.path.exists(folder):
+            # Iterate over all the files and directories in the specified directory
+            for filename in os.listdir(folder):
+                file_path = os.path.join(folder, filename)
+                try:
+                    if os.path.isfile(file_path) or os.path.islink(file_path):
+                        os.unlink(file_path)  # Remove the file or link
+                    elif os.path.isdir(file_path):
+                        shutil.rmtree(file_path)  # Remove the directory
+                except Exception as e:
+                    print(f"Failed to delete {file_path}. Reason: {e}")
+        else:
+            print(f"The directory {folder} does not exist")
+    except Exception as e:
+        print(f"Failed to process the directory {folder}. Reason: {e}")
+
+    return True
+
+
 @app.get("/reset")
 def reset(user=Depends(get_admin_user)) -> bool:
     folder = f"{UPLOAD_DIR}"

backend/apps/socket/main.py

+import socketio
+import asyncio
+
+
+from apps.webui.models.users import Users
+from utils.utils import decode_token
+
+sio = socketio.AsyncServer(cors_allowed_origins=[], async_mode="asgi")
+app = socketio.ASGIApp(sio, socketio_path="/ws/socket.io")
+
+# Dictionary to maintain the user pool
+
+
+USER_POOL = {}
+USAGE_POOL = {}
+# Timeout duration in seconds
+TIMEOUT_DURATION = 3
+
+
+@sio.event
+async def connect(sid, environ, auth):
+    print("connect ", sid)
+
+    user = None
+    if auth and "token" in auth:
+        data = decode_token(auth["token"])
+
+        if data is not None and "id" in data:
+            user = Users.get_user_by_id(data["id"])
+
+        if user:
+            USER_POOL[sid] = user.id
+            print(f"user {user.name}({user.id}) connected with session ID {sid}")
+
+            print(len(set(USER_POOL)))
+            await sio.emit("user-count", {"count": len(set(USER_POOL))})
+            await sio.emit("usage", {"models": get_models_in_use()})
+
+
+@sio.on("user-join")
+async def user_join(sid, data):
+    print("user-join", sid, data)
+
+    auth = data["auth"] if "auth" in data else None
+
+    if auth and "token" in auth:
+        data = decode_token(auth["token"])
+
+        if data is not None and "id" in data:
+            user = Users.get_user_by_id(data["id"])
+
+        if user:
+            USER_POOL[sid] = user.id
+            print(f"user {user.name}({user.id}) connected with session ID {sid}")
+
+            print(len(set(USER_POOL)))
+            await sio.emit("user-count", {"count": len(set(USER_POOL))})
+
+
+@sio.on("user-count")
+async def user_count(sid):
+    print("user-count", sid)
+    await sio.emit("user-count", {"count": len(set(USER_POOL))})
+
+
+def get_models_in_use():
+    # Aggregate all models in use
+    models_in_use = []
+    for model_id, data in USAGE_POOL.items():
+        models_in_use.append(model_id)
+    print(f"Models in use: {models_in_use}")
+
+    return models_in_use
+
+
+@sio.on("usage")
+async def usage(sid, data):
+    print(f'Received "usage" event from {sid}: {data}')
+
+    model_id = data["model"]
+
+    # Cancel previous callback if there is one
+    if model_id in USAGE_POOL:
+        USAGE_POOL[model_id]["callback"].cancel()
+
+    # Store the new usage data and task
+
+    if model_id in USAGE_POOL:
+        USAGE_POOL[model_id]["sids"].append(sid)
+        USAGE_POOL[model_id]["sids"] = list(set(USAGE_POOL[model_id]["sids"]))
+
+    else:
+        USAGE_POOL[model_id] = {"sids": [sid]}
+
+    # Schedule a task to remove the usage data after TIMEOUT_DURATION
+    USAGE_POOL[model_id]["callback"] = asyncio.create_task(
+        remove_after_timeout(sid, model_id)
+    )
+
+    # Broadcast the usage data to all clients
+    await sio.emit("usage", {"models": get_models_in_use()})
+
+
+async def remove_after_timeout(sid, model_id):
+    try:
+        print("remove_after_timeout", sid, model_id)
+        await asyncio.sleep(TIMEOUT_DURATION)
+        if model_id in USAGE_POOL:
+            print(USAGE_POOL[model_id]["sids"])
+            USAGE_POOL[model_id]["sids"].remove(sid)
+            USAGE_POOL[model_id]["sids"] = list(set(USAGE_POOL[model_id]["sids"]))
+
+            if len(USAGE_POOL[model_id]["sids"]) == 0:
+                del USAGE_POOL[model_id]
+
+            print(f"Removed usage data for {model_id} due to timeout")
+            # Broadcast the usage data to all clients
+            await sio.emit("usage", {"models": get_models_in_use()})
+    except asyncio.CancelledError:
+        # Task was cancelled due to new 'usage' event
+        pass
+
+
+@sio.event
+async def disconnect(sid):
+    if sid in USER_POOL:
+        disconnected_user = USER_POOL.pop(sid)
+        print(f"user {disconnected_user} disconnected with session ID {sid}")
+
+        await sio.emit("user-count", {"count": len(USER_POOL)})
+    else:
+        print(f"Unknown session ID {sid} disconnected")

backend/constants.py

@@ -84,3 +84,7 @@ class ERROR_MESSAGES(str, Enum):
     WEB_SEARCH_ERROR = (
         lambda err="": f"{err if err else 'Oops! Something went wrong while searching the web.'}"
     )
+
+    OLLAMA_API_DISABLED = (
+        "The Ollama API is disabled. Please enable it to use this feature."
+    )

backend/main.py

@@ -20,6 +20,8 @@ from starlette.exceptions import HTTPException as StarletteHTTPException
 from starlette.middleware.base import BaseHTTPMiddleware
 from starlette.responses import StreamingResponse, Response
 
+
+from apps.socket.main import app as socket_app
 from apps.ollama.main import app as ollama_app, get_all_models as get_ollama_models
 from apps.openai.main import app as openai_app, get_all_models as get_openai_models
 
@@ -376,6 +378,9 @@ async def update_embedding_function(request: Request, call_next):
     return response
 
 
+app.mount("/ws", socket_app)
+
+
 app.mount("/ollama", ollama_app)
 app.mount("/openai", openai_app)
 

package-lock.json

 {
 	"name": "open-webui",
-	"version": "0.2.4",
+	"version": "0.2.5",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "open-webui",
-			"version": "0.2.4",
+			"version": "0.2.5",
 			"dependencies": {
 				"@pyscript/core": "^0.4.32",
 				"@sveltejs/adapter-node": "^1.3.1",
@@ -25,6 +25,7 @@
 				"marked": "^9.1.0",
 				"mermaid": "^10.9.1",
 				"pyodide": "^0.26.0-alpha.4",
+				"socket.io-client": "^4.7.5",
 				"sortablejs": "^1.15.2",
 				"svelte-sonner": "^0.3.19",
 				"tippy.js": "^6.3.7",
@@ -1214,6 +1215,11 @@
 			"integrity": "sha512-+Fj43pSMwJs4KRrH/938Uf+uAELIgVBmQzg/q1YG10djyfA3TnrU8N8XzqCh/okZdszqBQTZf96idMfE5lnwTA==",
 			"dev": true
 		},
+		"node_modules/@socket.io/component-emitter": {
+			"version": "3.1.2",
+			"resolved": "https://registry.npmjs.org/@socket.io/component-emitter/-/component-emitter-3.1.2.tgz",
+			"integrity": "sha512-9BCxFwvbGg/RsZK9tjXd8s4UcwR0MWeFQ1XEKIQVVvAGJyINdrqKMcTRyLoK8Rse1GjzLV9cwjWV1olXRWEXVA=="
+		},
 		"node_modules/@sveltejs/adapter-auto": {
 			"version": "2.1.1",
 			"resolved": "https://registry.npmjs.org/@sveltejs/adapter-auto/-/adapter-auto-2.1.1.tgz",
@@ -3800,6 +3806,46 @@
 				"once": "^1.4.0"
 			}
 		},
+		"node_modules/engine.io-client": {
+			"version": "6.5.3",
+			"resolved": "https://registry.npmjs.org/engine.io-client/-/engine.io-client-6.5.3.tgz",
+			"integrity": "sha512-9Z0qLB0NIisTRt1DZ/8U2k12RJn8yls/nXMZLn+/N8hANT3TcYjKFKcwbw5zFQiN4NTde3TSY9zb79e1ij6j9Q==",
+			"dependencies": {
+				"@socket.io/component-emitter": "~3.1.0",
+				"debug": "~4.3.1",
+				"engine.io-parser": "~5.2.1",
+				"ws": "~8.11.0",
+				"xmlhttprequest-ssl": "~2.0.0"
+			}
+		},
+		"node_modules/engine.io-client/node_modules/ws": {
+			"version": "8.11.0",
+			"resolved": "https://registry.npmjs.org/ws/-/ws-8.11.0.tgz",
+			"integrity": "sha512-HPG3wQd9sNQoT9xHyNCXoDUa+Xw/VevmY9FoHyQ+g+rrMn4j6FB4np7Z0OhdTgjx6MgQLK7jwSy1YecU1+4Asg==",
+			"engines": {
+				"node": ">=10.0.0"
+			},
+			"peerDependencies": {
+				"bufferutil": "^4.0.1",
+				"utf-8-validate": "^5.0.2"
+			},
+			"peerDependenciesMeta": {
+				"bufferutil": {
+					"optional": true
+				},
+				"utf-8-validate": {
+					"optional": true
+				}
+			}
+		},
+		"node_modules/engine.io-parser": {
+			"version": "5.2.2",
+			"resolved": "https://registry.npmjs.org/engine.io-parser/-/engine.io-parser-5.2.2.tgz",
+			"integrity": "sha512-RcyUFKA93/CXH20l4SoVvzZfrSDMOTUS3bWVpTt2FuFP+XYrL8i8oonHP7WInRyVHXh0n/ORtoeiE1os+8qkSw==",
+			"engines": {
+				"node": ">=10.0.0"
+			}
+		},
 		"node_modules/enquirer": {
 			"version": "2.4.1",
 			"resolved": "https://registry.npmjs.org/enquirer/-/enquirer-2.4.1.tgz",
@@ -7949,6 +7995,32 @@
 				"node": ">=8"
 			}
 		},
+		"node_modules/socket.io-client": {
+			"version": "4.7.5",
+			"resolved": "https://registry.npmjs.org/socket.io-client/-/socket.io-client-4.7.5.tgz",
+			"integrity": "sha512-sJ/tqHOCe7Z50JCBCXrsY3I2k03iOiUe+tj1OmKeD2lXPiGH/RUCdTZFoqVyN7l1MnpIzPrGtLcijffmeouNlQ==",
+			"dependencies": {
+				"@socket.io/component-emitter": "~3.1.0",
+				"debug": "~4.3.2",
+				"engine.io-client": "~6.5.2",
+				"socket.io-parser": "~4.2.4"
+			},
+			"engines": {
+				"node": ">=10.0.0"
+			}
+		},
+		"node_modules/socket.io-parser": {
+			"version": "4.2.4",
+			"resolved": "https://registry.npmjs.org/socket.io-parser/-/socket.io-parser-4.2.4.tgz",
+			"integrity": "sha512-/GbIKmo8ioc+NIWIhwdecY0ge+qVBSMdgxGygevmdHj24bsfgtCmcUUcQ5ZzcylGFHsN3k4HB4Cgkl96KVnuew==",
+			"dependencies": {
+				"@socket.io/component-emitter": "~3.1.0",
+				"debug": "~4.3.1"
+			},
+			"engines": {
+				"node": ">=10.0.0"
+			}
+		},
 		"node_modules/sorcery": {
 			"version": "0.11.0",
 			"resolved": "https://registry.npmjs.org/sorcery/-/sorcery-0.11.0.tgz",
@@ -10142,6 +10214,14 @@
 				}
 			}
 		},
+		"node_modules/xmlhttprequest-ssl": {
+			"version": "2.0.0",
+			"resolved": "https://registry.npmjs.org/xmlhttprequest-ssl/-/xmlhttprequest-ssl-2.0.0.tgz",
+			"integrity": "sha512-QKxVRxiRACQcVuQEYFsI1hhkrMlrXHPegbbd1yn9UHOmRxY+si12nQYzri3vbzt8VdTTRviqcKxcyllFas5z2A==",
+			"engines": {
+				"node": ">=0.4.0"
+			}
+		},
 		"node_modules/xtend": {
 			"version": "4.0.2",
 			"resolved": "https://registry.npmjs.org/xtend/-/xtend-4.0.2.tgz",

package.json

 {
 	"name": "open-webui",
-	"version": "0.2.4",
+	"version": "0.2.5",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
@@ -65,6 +65,7 @@
 		"marked": "^9.1.0",
 		"mermaid": "^10.9.1",
 		"pyodide": "^0.26.0-alpha.4",
+		"socket.io-client": "^4.7.5",
 		"sortablejs": "^1.15.2",
 		"svelte-sonner": "^0.3.19",
 		"tippy.js": "^6.3.7",

src/lib/apis/ollama/index.ts

@@ -369,10 +369,17 @@ export const generateChatCompletion = async (token: string = '', body: object) =
 	return [res, controller];
 };
 
-export const createModel = async (token: string, tagName: string, content: string) => {
+export const createModel = async (
+	token: string,
+	tagName: string,
+	content: string,
+	urlIdx: string | null = null
+) => {
 	let error = null;
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/create`, {
+	const res = await fetch(
+		`${OLLAMA_API_BASE_URL}/api/create${urlIdx !== null ? `/${urlIdx}` : ''}`,
+		{
 			method: 'POST',
 			headers: {
 				Accept: 'application/json',
@@ -383,7 +390,8 @@ export const createModel = async (token: string, tagName: string, content: strin
 				name: tagName,
 				modelfile: content
 			})
-	}).catch((err) => {
+		}
+	).catch((err) => {
 		error = err;
 		return null;
 	});

src/lib/apis/rag/index.ts

@@ -359,6 +359,32 @@ export const scanDocs = async (token: string) => {
 	return res;
 };
 
+export const resetUploadDir = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/reset/uploads`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const resetVectorDB = async (token: string) => {
 	let error = null;
 

src/lib/components/chat/Chat.svelte

@@ -18,7 +18,8 @@
 		tags as _tags,
 		WEBUI_NAME,
 		banners,
-		user
+		user,
+		socket
 	} from '$lib/stores';
 	import {
 		convertMessagesToHistory,
@@ -280,6 +281,16 @@
 		}
 	};
 
+	const getChatEventEmitter = async (modelId: string, chatId: string = '') => {
+		return setInterval(() => {
+			$socket?.emit('usage', {
+				action: 'chat',
+				model: modelId,
+				chat_id: chatId
+			});
+		}, 1000);
+	};
+
 	//////////////////////////
 	// Ollama functions
 	//////////////////////////
@@ -451,6 +462,8 @@
 					}
 					responseMessage.userContext = userContext;
 
+					const chatEventEmitter = await getChatEventEmitter(model.id, _chatId);
+
 					if (webSearchEnabled) {
 						await getWebSearchResults(model.id, parentId, responseMessageId);
 					}
@@ -460,6 +473,10 @@
 					} else if (model) {
 						await sendPromptOllama(model, prompt, responseMessageId, _chatId);
 					}
+
+					console.log('chatEventEmitter', chatEventEmitter);
+
+					if (chatEventEmitter) clearInterval(chatEventEmitter);
 				} else {
 					toast.error($i18n.t(`Model {{modelId}} not found`, { modelId }));
 				}
@@ -542,6 +559,7 @@
 
 	const sendPromptOllama = async (model, userPrompt, responseMessageId, _chatId) => {
 		model = model.id;
+
 		const responseMessage = history.messages[responseMessageId];
 
 		// Wait until history/message have been updated
@@ -1177,7 +1195,7 @@
 
 {#if !chatIdProp || (loaded && chatIdProp)}
 	<div
-		class="min-h-screen max-h-screen {$showSidebar
+		class="h-screen max-h-[100dvh] {$showSidebar
 			? 'md:max-w-[calc(100%-260px)]'
 			: ''} w-full max-w-full flex flex-col"
 	>

src/lib/components/chat/Messages.svelte

@@ -286,7 +286,7 @@
 				{#each messages as message, messageIdx}
 					<div class=" w-full {messageIdx === messages.length - 1 ? ' pb-12' : ''}">
 						<div
-							class="flex flex-col justify-between px-5 mb-3 {$settings?.fullScreenMode ?? null
+							class="flex flex-col justify-between px-5 mb-3 {$settings?.widescreenMode ?? null
 								? 'max-w-full'
 								: 'max-w-5xl'} mx-auto rounded-lg group"
 						>

src/lib/components/chat/Settings/Audio.svelte

@@ -315,8 +315,8 @@
 						</select>
 					</div>
 				</div>
-				<div class="flex items-center justify-between mb-1">
-					<div class="text-sm">
+				<div class="flex items-center justify-between my-1.5">
+					<div class="text-xs">
 						{$i18n.t('Allow non-local voices')}
 					</div>
 

src/lib/components/chat/Settings/Interface.svelte

@@ -16,11 +16,12 @@
 	let responseAutoCopy = false;
 	let titleAutoGenerateModel = '';
 	let titleAutoGenerateModelExternal = '';
-	let fullScreenMode = false;
+	let widescreenMode = false;
 	let titleGenerationPrompt = '';
 	let splitLargeChunks = false;
 
 	// Interface
+	let defaultModelId = '';
 	let promptSuggestions = [];
 	let showUsername = false;
 	let chatBubble = true;
@@ -31,9 +32,9 @@
 		saveSettings({ splitLargeChunks: splitLargeChunks });
 	};
 
-	const toggleFullScreenMode = async () => {
-		fullScreenMode = !fullScreenMode;
-		saveSettings({ fullScreenMode: fullScreenMode });
+	const togglewidescreenMode = async () => {
+		widescreenMode = !widescreenMode;
+		saveSettings({ widescreenMode: widescreenMode });
 	};
 
 	const toggleChatBubble = async () => {
@@ -96,7 +97,8 @@
 				modelExternal:
 					titleAutoGenerateModelExternal !== '' ? titleAutoGenerateModelExternal : undefined,
 				prompt: titleGenerationPrompt ? titleGenerationPrompt : undefined
-			}
+			},
+			models: [defaultModelId]
 		});
 	};
 
@@ -114,9 +116,11 @@
 		responseAutoCopy = $settings.responseAutoCopy ?? false;
 		showUsername = $settings.showUsername ?? false;
 		chatBubble = $settings.chatBubble ?? true;
-		fullScreenMode = $settings.fullScreenMode ?? false;
+		widescreenMode = $settings.widescreenMode ?? false;
 		splitLargeChunks = $settings.splitLargeChunks ?? false;
 		chatDirection = $settings.chatDirection ?? 'LTR';
+
+		defaultModelId = ($settings?.models ?? ['']).at(0);
 	});
 </script>
 
@@ -195,16 +199,16 @@
 
 			<div>
 				<div class=" py-0.5 flex w-full justify-between">
-					<div class=" self-center text-xs font-medium">{$i18n.t('Full Screen Mode')}</div>
+					<div class=" self-center text-xs font-medium">{$i18n.t('Widescreen Mode')}</div>
 
 					<button
 						class="p-1 px-3 text-xs flex rounded transition"
 						on:click={() => {
-							toggleFullScreenMode();
+							togglewidescreenMode();
 						}}
 						type="button"
 					>
-						{#if fullScreenMode === true}
+						{#if widescreenMode === true}
 							<span class="ml-2 self-center">{$i18n.t('On')}</span>
 						{:else}
 							<span class="ml-2 self-center">{$i18n.t('Off')}</span>
@@ -278,7 +282,30 @@
 			</div>
 		</div>
 
-		<hr class=" dark:border-gray-700" />
+		<hr class=" dark:border-gray-850" />
+
+		<div class=" space-y-1 mb-3">
+			<div class="mb-2">
+				<div class="flex justify-between items-center text-xs">
+					<div class=" text-xs font-medium">{$i18n.t('Default Model')}</div>
+				</div>
+			</div>
+
+			<div class="flex-1 mr-2">
+				<select
+					class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+					bind:value={defaultModelId}
+					placeholder="Select a model"
+				>
+					<option value="" disabled selected>{$i18n.t('Select a model')}</option>
+					{#each $models.filter((model) => model.id) as model}
+						<option value={model.id} class="bg-gray-100 dark:bg-gray-700">{model.name}</option>
+					{/each}
+				</select>
+			</div>
+		</div>
+
+		<hr class=" dark:border-gray-850" />
 
 		<div>
 			<div class=" mb-2.5 text-sm font-medium flex">

src/lib/components/chat/Settings/Models.svelte

@@ -43,6 +43,13 @@
 
 	let modelTransferring = false;
 	let modelTag = '';
+
+	let createModelLoading = false;
+	let createModelTag = '';
+	let createModelContent = '';
+	let createModelDigest = '';
+	let createModelPullProgress = null;
+
 	let digest = '';
 	let pullProgress = null;
 
@@ -434,6 +441,83 @@
 		}
 	};
 
+	const createModelHandler = async () => {
+		createModelLoading = true;
+		const res = await createModel(
+			localStorage.token,
+			createModelTag,
+			createModelContent,
+			selectedOllamaUrlIdx
+		).catch((error) => {
+			toast.error(error);
+			return null;
+		});
+
+		if (res && res.ok) {
+			const reader = res.body
+				.pipeThrough(new TextDecoderStream())
+				.pipeThrough(splitStream('\n'))
+				.getReader();
+
+			while (true) {
+				const { value, done } = await reader.read();
+				if (done) break;
+
+				try {
+					let lines = value.split('\n');
+
+					for (const line of lines) {
+						if (line !== '') {
+							console.log(line);
+							let data = JSON.parse(line);
+							console.log(data);
+
+							if (data.error) {
+								throw data.error;
+							}
+							if (data.detail) {
+								throw data.detail;
+							}
+
+							if (data.status) {
+								if (
+									!data.digest &&
+									!data.status.includes('writing') &&
+									!data.status.includes('sha256')
+								) {
+									toast.success(data.status);
+								} else {
+									if (data.digest) {
+										createModelDigest = data.digest;
+
+										if (data.completed) {
+											createModelPullProgress =
+												Math.round((data.completed / data.total) * 1000) / 10;
+										} else {
+											createModelPullProgress = 100;
+										}
+									}
+								}
+							}
+						}
+					}
+				} catch (error) {
+					console.log(error);
+					toast.error(error);
+				}
+			}
+		}
+
+		models.set(await getModels());
+
+		createModelLoading = false;
+
+		createModelTag = '';
+		createModelContent = '';
+		createModelDigest = '';
+		createModelPullProgress = null;
+	};
+
 	onMount(async () => {
 		const ollamaConfig = await getOllamaConfig(localStorage.token);
 
@@ -695,6 +779,77 @@
 							</div>
 						</div>
 
+						<div>
+							<div class=" mb-2 text-sm font-medium">{$i18n.t('Create a model')}</div>
+							<div class="flex w-full">
+								<div class="flex-1 mr-2 flex flex-col gap-2">
+									<input
+										class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+										placeholder={$i18n.t('Enter model tag (e.g. {{modelTag}})', {
+											modelTag: 'my-modelfile'
+										})}
+										bind:value={createModelTag}
+										disabled={createModelLoading}
+									/>
+
+									<textarea
+										bind:value={createModelContent}
+										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-100 dark:text-gray-100 dark:bg-gray-850 outline-none resize-none scrollbar-hidden"
+										rows="6"
+										placeholder={`TEMPLATE """{{ .System }}\nUSER: {{ .Prompt }}\nASSISTANT: """\nPARAMETER num_ctx 4096\nPARAMETER stop "</s>"\nPARAMETER stop "USER:"\nPARAMETER stop "ASSISTANT:"`}
+										disabled={createModelLoading}
+									/>
+								</div>
+
+								<div class="flex self-start">
+									<button
+										class="px-2.5 py-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-850 dark:hover:bg-gray-800 dark:text-gray-100 rounded-lg transition disabled:cursor-not-allowed"
+										on:click={() => {
+											createModelHandler();
+										}}
+										disabled={createModelLoading}
+									>
+										<svg
+											xmlns="http://www.w3.org/2000/svg"
+											viewBox="0 0 16 16"
+											fill="currentColor"
+											class="size-4"
+										>
+											<path
+												d="M7.25 10.25a.75.75 0 0 0 1.5 0V4.56l2.22 2.22a.75.75 0 1 0 1.06-1.06l-3.5-3.5a.75.75 0 0 0-1.06 0l-3.5 3.5a.75.75 0 0 0 1.06 1.06l2.22-2.22v5.69Z"
+											/>
+											<path
+												d="M3.5 9.75a.75.75 0 0 0-1.5 0v1.5A2.75 2.75 0 0 0 4.75 14h6.5A2.75 2.75 0 0 0 14 11.25v-1.5a.75.75 0 0 0-1.5 0v1.5c0 .69-.56 1.25-1.25 1.25h-6.5c-.69 0-1.25-.56-1.25-1.25v-1.5Z"
+											/>
+										</svg>
+									</button>
+								</div>
+							</div>
+
+							{#if createModelDigest !== ''}
+								<div class="flex flex-col mt-1">
+									<div class="font-medium mb-1">{createModelTag}</div>
+									<div class="">
+										<div class="flex flex-row justify-between space-x-4 pr-2">
+											<div class=" flex-1">
+												<div
+													class="dark:bg-gray-600 bg-gray-500 text-xs font-medium text-gray-100 text-center p-0.5 leading-none rounded-full"
+													style="width: {Math.max(15, createModelPullProgress ?? 0)}%"
+												>
+													{createModelPullProgress ?? 0}%
+												</div>
+											</div>
+										</div>
+										{#if createModelDigest}
+											<div class="mt-1 text-xs dark:text-gray-500" style="font-size: 0.5rem;">
+												{createModelDigest}
+											</div>
+										{/if}
+									</div>
+								</div>
+							{/if}
+						</div>
+
 						<div class="pt-1">
 							<div class="flex justify-between items-center text-xs">
 								<div class=" text-sm font-medium">{$i18n.t('Experimental')}</div>

src/lib/components/common/Banner.svelte

@@ -39,7 +39,7 @@
 {#if !dismissed}
 	{#if mounted}
 		<div
-			class=" top-0 left-0 right-0 p-2 mx-4 px-3 flex justify-center items-center relative rounded-xl border border-gray-50 dark:border-gray-850 text-gray-800 dark:text-gary-100 bg-white dark:bg-gray-900 backdrop-blur-xl z-40"
+			class=" top-0 left-0 right-0 p-2 mx-4 px-3 flex justify-center items-center relative rounded-xl border border-gray-50 dark:border-gray-850 text-gray-800 dark:text-gary-100 bg-white dark:bg-gray-900 backdrop-blur-xl z-30"
 			transition:fade={{ delay: 100, duration: 300 }}
 		>
 			<div class=" flex flex-col md:flex-row md:items-center flex-1 text-sm w-fit gap-1.5">

src/lib/components/common/Tooltip.svelte

@@ -21,6 +21,10 @@
 				touch: touch
 			});
 		}
+	} else if (tooltipInstance && content === '') {
+		if (tooltipInstance) {
+			tooltipInstance.destroy();
+		}
 	}
 
 	onDestroy(() => {

src/lib/components/documents/Settings/General.svelte

@@ -8,7 +8,8 @@
 		getEmbeddingConfig,
 		updateEmbeddingConfig,
 		getRerankingConfig,
-		updateRerankingConfig
+		updateRerankingConfig,
+		resetUploadDir
 	} from '$lib/apis/rag';
 
 	import { documents, models } from '$lib/stores';
@@ -24,6 +25,7 @@
 	let updateRerankingModelLoading = false;
 
 	let showResetConfirm = false;
+	let showResetUploadDirConfirm = false;
 
 	let embeddingEngine = '';
 	let embeddingModel = '';
@@ -496,7 +498,108 @@
 			{/if}
 		</div>
 
-		<hr class=" dark:border-gray-700" />
+		<hr class=" dark:border-gray-850" />
+
+		<div>
+			{#if showResetUploadDirConfirm}
+				<div class="flex justify-between rounded-md items-center py-2 px-3.5 w-full transition">
+					<div class="flex items-center space-x-3">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 24 24"
+							fill="currentColor"
+							class="size-4"
+						>
+							<path
+								fill-rule="evenodd"
+								d="M5.625 1.5H9a3.75 3.75 0 0 1 3.75 3.75v1.875c0 1.036.84 1.875 1.875 1.875H16.5a3.75 3.75 0 0 1 3.75 3.75v7.875c0 1.035-.84 1.875-1.875 1.875H5.625a1.875 1.875 0 0 1-1.875-1.875V3.375c0-1.036.84-1.875 1.875-1.875ZM9.75 14.25a.75.75 0 0 0 0 1.5H15a.75.75 0 0 0 0-1.5H9.75Z"
+								clip-rule="evenodd"
+							/>
+							<path
+								d="M14.25 5.25a5.23 5.23 0 0 0-1.279-3.434 9.768 9.768 0 0 1 6.963 6.963A5.23 5.23 0 0 0 16.5 7.5h-1.875a.375.375 0 0 1-.375-.375V5.25Z"
+							/>
+						</svg>
+						<span>{$i18n.t('Are you sure?')}</span>
+					</div>
+
+					<div class="flex space-x-1.5 items-center">
+						<button
+							class="hover:text-white transition"
+							on:click={() => {
+								const res = resetUploadDir(localStorage.token).catch((error) => {
+									toast.error(error);
+									return null;
+								});
+
+								if (res) {
+									toast.success($i18n.t('Success'));
+								}
+
+								showResetUploadDirConfirm = false;
+							}}
+							type="button"
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									fill-rule="evenodd"
+									d="M16.704 4.153a.75.75 0 01.143 1.052l-8 10.5a.75.75 0 01-1.127.075l-4.5-4.5a.75.75 0 011.06-1.06l3.894 3.893 7.48-9.817a.75.75 0 011.05-.143z"
+									clip-rule="evenodd"
+								/>
+							</svg>
+						</button>
+						<button
+							class="hover:text-white transition"
+							type="button"
+							on:click={() => {
+								showResetUploadDirConfirm = false;
+							}}
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+								/>
+							</svg>
+						</button>
+					</div>
+				</div>
+			{:else}
+				<button
+					class=" flex rounded-xl py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
+					on:click={() => {
+						showResetUploadDirConfirm = true;
+					}}
+					type="button"
+				>
+					<div class=" self-center mr-3">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 24 24"
+							fill="currentColor"
+							class="size-4"
+						>
+							<path
+								fill-rule="evenodd"
+								d="M5.625 1.5H9a3.75 3.75 0 0 1 3.75 3.75v1.875c0 1.036.84 1.875 1.875 1.875H16.5a3.75 3.75 0 0 1 3.75 3.75v7.875c0 1.035-.84 1.875-1.875 1.875H5.625a1.875 1.875 0 0 1-1.875-1.875V3.375c0-1.036.84-1.875 1.875-1.875ZM9.75 14.25a.75.75 0 0 0 0 1.5H15a.75.75 0 0 0 0-1.5H9.75Z"
+								clip-rule="evenodd"
+							/>
+							<path
+								d="M14.25 5.25a5.23 5.23 0 0 0-1.279-3.434 9.768 9.768 0 0 1 6.963 6.963A5.23 5.23 0 0 0 16.5 7.5h-1.875a.375.375 0 0 1-.375-.375V5.25Z"
+							/>
+						</svg>
+					</div>
+					<div class=" self-center text-sm font-medium">{$i18n.t('Reset Upload Directory')}</div>
+				</button>
+			{/if}
 
 			{#if showResetConfirm}
 				<div class="flex justify-between rounded-md items-center py-2 px-3.5 w-full transition">
@@ -507,10 +610,9 @@
 							fill="currentColor"
 							class="w-4 h-4"
 						>
-						<path d="M2 3a1 1 0 0 1 1-1h10a1 1 0 0 1 1 1v1a1 1 0 0 1-1 1H3a1 1 0 0 1-1-1V3Z" />
 							<path
 								fill-rule="evenodd"
-							d="M13 6H3v6a2 2 0 0 0 2 2h6a2 2 0 0 0 2-2V6ZM5.72 7.47a.75.75 0 0 1 1.06 0L8 8.69l1.22-1.22a.75.75 0 1 1 1.06 1.06L9.06 9.75l1.22 1.22a.75.75 0 1 1-1.06 1.06L8 10.81l-1.22 1.22a.75.75 0 0 1-1.06-1.06l1.22-1.22-1.22-1.22a.75.75 0 0 1 0-1.06Z"
+								d="M3.5 2A1.5 1.5 0 0 0 2 3.5v9A1.5 1.5 0 0 0 3.5 14h9a1.5 1.5 0 0 0 1.5-1.5v-7A1.5 1.5 0 0 0 12.5 4H9.621a1.5 1.5 0 0 1-1.06-.44L7.439 2.44A1.5 1.5 0 0 0 6.38 2H3.5Zm6.75 7.75a.75.75 0 0 0 0-1.5h-4.5a.75.75 0 0 0 0 1.5h4.5Z"
 								clip-rule="evenodd"
 							/>
 						</svg>
@@ -532,6 +634,7 @@
 
 								showResetConfirm = false;
 							}}
+							type="button"
 						>
 							<svg
 								xmlns="http://www.w3.org/2000/svg"
@@ -551,6 +654,7 @@
 							on:click={() => {
 								showResetConfirm = false;
 							}}
+							type="button"
 						>
 							<svg
 								xmlns="http://www.w3.org/2000/svg"
@@ -567,10 +671,11 @@
 				</div>
 			{:else}
 				<button
-				class=" flex rounded-md py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
+					class=" flex rounded-xl py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
 					on:click={() => {
 						showResetConfirm = true;
 					}}
+					type="button"
 				>
 					<div class=" self-center mr-3">
 						<svg
@@ -590,6 +695,7 @@
 				</button>
 			{/if}
 		</div>
+	</div>
 	<div class="flex justify-end pt-3 text-sm font-medium">
 		<button
 			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"