Merge branch 'ollama-webui:main' into general-logistic-improvements

README.md

@@ -13,7 +13,7 @@
 
 ChatGPT-Style Web Interface for Ollama 🦙
 
-**Disclaimer:** *ollama-webui is a community-driven project and is not affiliated with the Ollama team in any way. This initiative is independent, and any inquiries or feedback should be directed to [our community on Discord](https://discord.gg/5rJgQTnV4s). We kindly request users to refrain from contacting or harassing the Ollama team regarding this project.*
+**Disclaimer:** _ollama-webui is a community-driven project and is not affiliated with the Ollama team in any way. This initiative is independent, and any inquiries or feedback should be directed to [our community on Discord](https://discord.gg/5rJgQTnV4s). We kindly request users to refrain from contacting or harassing the Ollama team regarding this project._
 
 ![Ollama Web UI Demo](./demo.gif)
 
@@ -35,6 +35,8 @@ Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you c
 
 - 📥🗑️ **Download/Delete Models**: Easily download or remove models directly from the web UI.
 
+- ⬆️ **GGUF File Model Creation**: Effortlessly create Ollama models by uploading GGUF files directly from the web UI. Streamlined process with options to upload from your machine or download GGUF files from Hugging Face.
+
 - 🤖 **Multiple Model Support**: Seamlessly switch between different chat models for diverse interactions.
 
 - 🔄 **Multi-Modal Support**: Seamlessly engage with models that support multimodal interactions, including images (e.g., LLava).
@@ -43,7 +45,7 @@ Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you c
 
 - ⚙️ **Many Models Conversations**: Effortlessly engage with various models simultaneously, harnessing their unique strengths for optimal responses. Enhance your experience by leveraging a diverse set of models in parallel.
 
-- 🤝 **OpenAI Model Integration**: Seamlessly utilize OpenAI models alongside Ollama models for a versatile conversational experience.
+- 🤝 **OpenAI API Integration**: Effortlessly integrate OpenAI-compatible API for versatile conversations alongside Ollama models. Customize the API Base URL to link with **LMStudio, Mistral, OpenRouter, and more**.
 
 - 🔄 **Regeneration History Access**: Easily revisit and explore your entire regeneration history.
 

backend/.gitignore

@@ -1,2 +1,4 @@
 __pycache__
 .env
+_old
+uploads

backend/apps/web/main.py

@@ -1,7 +1,7 @@
 from fastapi import FastAPI, Request, Depends, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
 
-from apps.web.routers import auths, users
+from apps.web.routers import auths, users, utils
 from config import WEBUI_VERSION, WEBUI_AUTH
 
 app = FastAPI()
@@ -19,6 +19,7 @@ app.add_middleware(
 
 app.include_router(auths.router, prefix="/auths", tags=["auths"])
 app.include_router(users.router, prefix="/users", tags=["users"])
+app.include_router(utils.router, prefix="/utils", tags=["utils"])
 
 
 @app.get("/")

backend/apps/web/routers/utils.py

@@ -0,0 +1,164 @@
+from fastapi import APIRouter, UploadFile, File, BackgroundTasks
+from fastapi import Depends, HTTPException, status
+from starlette.responses import StreamingResponse
+
+from pydantic import BaseModel
+
+import requests
+import os
+import aiohttp
+import json
+
+
+from utils.misc import calculate_sha256
+
+from config import OLLAMA_API_BASE_URL
+
+
+router = APIRouter()
+
+
+class UploadBlobForm(BaseModel):
+    filename: str
+
+
+from urllib.parse import urlparse
+
+
+def parse_huggingface_url(hf_url):
+    try:
+        # Parse the URL
+        parsed_url = urlparse(hf_url)
+
+        # Get the path and split it into components
+        path_components = parsed_url.path.split("/")
+
+        # Extract the desired output
+        user_repo = "/".join(path_components[1:3])
+        model_file = path_components[-1]
+
+        return model_file
+    except ValueError:
+        return None
+
+
+async def download_file_stream(url, file_path, file_name, chunk_size=1024 * 1024):
+    done = False
+
+    if os.path.exists(file_path):
+        current_size = os.path.getsize(file_path)
+    else:
+        current_size = 0
+
+    headers = {"Range": f"bytes={current_size}-"} if current_size > 0 else {}
+
+    timeout = aiohttp.ClientTimeout(total=600)  # Set the timeout
+
+    async with aiohttp.ClientSession(timeout=timeout) as session:
+        async with session.get(url, headers=headers) as response:
+            total_size = int(response.headers.get("content-length", 0)) + current_size
+
+            with open(file_path, "ab+") as file:
+                async for data in response.content.iter_chunked(chunk_size):
+                    current_size += len(data)
+                    file.write(data)
+
+                    done = current_size == total_size
+                    progress = round((current_size / total_size) * 100, 2)
+                    yield f'data: {{"progress": {progress}, "completed": {current_size}, "total": {total_size}}}\n\n'
+
+                if done:
+                    file.seek(0)
+                    hashed = calculate_sha256(file)
+                    file.seek(0)
+
+                    url = f"{OLLAMA_API_BASE_URL}/blobs/sha256:{hashed}"
+                    response = requests.post(url, data=file)
+
+                    if response.ok:
+                        res = {
+                            "done": done,
+                            "blob": f"sha256:{hashed}",
+                            "name": file_name,
+                        }
+                        os.remove(file_path)
+
+                        yield f"data: {json.dumps(res)}\n\n"
+                    else:
+                        raise "Ollama: Could not create blob, Please try again."
+
+
+@router.get("/download")
+async def download(
+    url: str,
+):
+    # url = "https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q2_K.gguf"
+    file_name = parse_huggingface_url(url)
+
+    if file_name:
+        os.makedirs("./uploads", exist_ok=True)
+        file_path = os.path.join("./uploads", f"{file_name}")
+
+        return StreamingResponse(
+            download_file_stream(url, file_path, file_name),
+            media_type="text/event-stream",
+        )
+    else:
+        return None
+
+
+@router.post("/upload")
+async def upload(file: UploadFile = File(...)):
+    os.makedirs("./uploads", exist_ok=True)
+    file_path = os.path.join("./uploads", file.filename)
+
+    async def file_write_stream():
+        total = 0
+        total_size = file.size
+        chunk_size = 1024 * 1024
+
+        done = False
+        try:
+            with open(file_path, "wb+") as f:
+                while True:
+                    chunk = file.file.read(chunk_size)
+                    if not chunk:
+                        break
+                    f.write(chunk)
+                    total += len(chunk)
+                    done = total_size == total
+                    progress = round((total / total_size) * 100, 2)
+
+                    res = {
+                        "progress": progress,
+                        "total": total_size,
+                        "completed": total,
+                    }
+
+                    yield f"data: {json.dumps(res)}\n\n"
+
+                if done:
+                    f.seek(0)
+                    hashed = calculate_sha256(f)
+                    f.seek(0)
+
+                    url = f"{OLLAMA_API_BASE_URL}/blobs/sha256:{hashed}"
+                    response = requests.post(url, data=f)
+
+                    if response.ok:
+                        res = {
+                            "done": done,
+                            "blob": f"sha256:{hashed}",
+                            "name": file.filename,
+                        }
+                        os.remove(file_path)
+
+                        yield f"data: {json.dumps(res)}\n\n"
+                    else:
+                        raise "Ollama: Could not create blob, Please try again."
+
+        except Exception as e:
+            res = {"error": str(e)}
+            yield f"data: {json.dumps(res)}\n\n"
+
+    return StreamingResponse(file_write_stream(), media_type="text/event-stream")

backend/config.py

@@ -30,7 +30,7 @@ if ENV == "prod":
 # WEBUI_VERSION
 ####################################
 
-WEBUI_VERSION = os.environ.get("WEBUI_VERSION", "v1.0.0-alpha.34")
+WEBUI_VERSION = os.environ.get("WEBUI_VERSION", "v1.0.0-alpha.40")
 
 ####################################
 # WEBUI_AUTH

backend/requirements.txt

@@ -12,6 +12,7 @@ passlib[bcrypt]
 uuid
 
 requests
+aiohttp
 pymongo
 bcrypt
 

backend/utils/misc.py

@@ -13,3 +13,11 @@ def get_gravatar_url(email):
 
     # Grab the actual image URL
     return f"https://www.gravatar.com/avatar/{hash_hex}?d=mp"
+
+
+def calculate_sha256(file):
+    sha256 = hashlib.sha256()
+    # Read the file in chunks to efficiently handle large files
+    for chunk in iter(lambda: file.read(8192), b""):
+        sha256.update(chunk)
+    return sha256.hexdigest()

src/lib/components/chat/MessageInput.svelte

@@ -155,7 +155,7 @@
 <div class="fixed bottom-0 w-full">
 	<div class="px-2.5 pt-2.5 -mb-0.5 mx-auto inset-x-0 bg-transparent flex justify-center">
 		{#if messages.length == 0 && suggestionPrompts.length !== 0}
-			<div class="max-w-3xl">
+			<div class="max-w-3xl w-full">
 				<Suggestions {suggestionPrompts} {submitPrompt} />
 			</div>
 		{/if}

src/lib/components/chat/MessageInput/Suggestions.svelte

@@ -3,7 +3,7 @@
 	export let suggestionPrompts = [];
 </script>
 
-<div class=" flex flex-wrap-reverse mb-3 md:p-1 text-left">
+<div class=" flex flex-wrap-reverse mb-3 md:p-1 text-left w-full">
 	{#each suggestionPrompts as prompt, promptIdx}
 		<div class="{promptIdx > 1 ? 'hidden sm:inline-flex' : ''} basis-full sm:basis-1/2 p-[5px]">
 			<button

src/lib/components/chat/SettingsModal.svelte

@@ -1,12 +1,18 @@
 <script lang="ts">
 	import Modal from '../common/Modal.svelte';
 
-	import { WEB_UI_VERSION, OLLAMA_API_BASE_URL } from '$lib/constants';
+	import {
+		WEB_UI_VERSION,
+		OLLAMA_API_BASE_URL,
+		WEBUI_API_BASE_URL,
+		WEBUI_BASE_URL
+	} from '$lib/constants';
 	import toast from 'svelte-french-toast';
 	import { onMount } from 'svelte';
 	import { config, info, models, settings, user } from '$lib/stores';
 	import { splitStream, getGravatarURL } from '$lib/utils';
 	import Advanced from './Settings/Advanced.svelte';
+	import { stringify } from 'postcss';
 
 	export let show = false;
 
@@ -44,11 +50,21 @@
 	};
 
 	// Models
+	let modelTransferring = false;
+
 	let modelTag = '';
-	let deleteModelTag = '';
 	let digest = '';
 	let pullProgress = null;
 
+	let modelUploadMode = 'file';
+	let modelInputFile = '';
+	let modelFileUrl = '';
+	let modelFileContent = `TEMPLATE """{{ .System }}\nUSER: {{ .Prompt }}\nASSSISTANT: """\nPARAMETER num_ctx 4096\nPARAMETER stop "</s>"\nPARAMETER stop "USER:"\nPARAMETER stop "ASSSISTANT:"`;
+	let modelFileDigest = '';
+	let uploadProgress = null;
+
+	let deleteModelTag = '';
+
 	// Addons
 	let titleAutoGenerate = true;
 	let speechAutoSend = false;
@@ -56,6 +72,7 @@
 
 	let gravatarEmail = '';
 	let OPENAI_API_KEY = '';
+	let OPENAI_API_BASE_URL = '';
 
 	// Auth
 	let authEnabled = false;
@@ -151,6 +168,7 @@
 	};
 
 	const pullModelHandler = async () => {
+		modelTransferring = true;
 		const res = await fetch(`${API_BASE_URL}/pull`, {
 			method: 'POST',
 			headers: {
@@ -216,6 +234,198 @@
 		}
 
 		modelTag = '';
+		modelTransferring = false;
+
+		models.set(await getModels());
+	};
+
+	const calculateSHA256 = async (file) => {
+		console.log(file);
+		// Create a FileReader to read the file asynchronously
+		const reader = new FileReader();
+
+		// Define a promise to handle the file reading
+		const readFile = new Promise((resolve, reject) => {
+			reader.onload = () => resolve(reader.result);
+			reader.onerror = reject;
+		});
+
+		// Read the file as an ArrayBuffer
+		reader.readAsArrayBuffer(file);
+
+		try {
+			// Wait for the FileReader to finish reading the file
+			const buffer = await readFile;
+
+			// Convert the ArrayBuffer to a Uint8Array
+			const uint8Array = new Uint8Array(buffer);
+
+			// Calculate the SHA-256 hash using Web Crypto API
+			const hashBuffer = await crypto.subtle.digest('SHA-256', uint8Array);
+
+			// Convert the hash to a hexadecimal string
+			const hashArray = Array.from(new Uint8Array(hashBuffer));
+			const hashHex = hashArray.map((byte) => byte.toString(16).padStart(2, '0')).join('');
+
+			return `sha256:${hashHex}`;
+		} catch (error) {
+			console.error('Error calculating SHA-256 hash:', error);
+			throw error;
+		}
+	};
+
+	const uploadModelHandler = async () => {
+		modelTransferring = true;
+		uploadProgress = 0;
+
+		let uploaded = false;
+		let fileResponse = null;
+		let name = '';
+
+		if (modelUploadMode === 'file') {
+			const file = modelInputFile[0];
+			const formData = new FormData();
+			formData.append('file', file);
+
+			fileResponse = await fetch(`${WEBUI_API_BASE_URL}/utils/upload`, {
+				method: 'POST',
+				headers: {
+					...($settings.authHeader && { Authorization: $settings.authHeader }),
+					...($user && { Authorization: `Bearer ${localStorage.token}` })
+				},
+				body: formData
+			}).catch((error) => {
+				console.log(error);
+				return null;
+			});
+		} else {
+			fileResponse = await fetch(`${WEBUI_API_BASE_URL}/utils/download?url=${modelFileUrl}`, {
+				method: 'GET',
+				headers: {
+					...($settings.authHeader && { Authorization: $settings.authHeader }),
+					...($user && { Authorization: `Bearer ${localStorage.token}` })
+				}
+			}).catch((error) => {
+				console.log(error);
+				return null;
+			});
+		}
+
+		if (fileResponse && fileResponse.ok) {
+			const reader = fileResponse.body
+				.pipeThrough(new TextDecoderStream())
+				.pipeThrough(splitStream('\n'))
+				.getReader();
+
+			while (true) {
+				const { value, done } = await reader.read();
+				if (done) break;
+
+				try {
+					let lines = value.split('\n');
+
+					for (const line of lines) {
+						if (line !== '') {
+							let data = JSON.parse(line.replace(/^data: /, ''));
+
+							if (data.progress) {
+								uploadProgress = data.progress;
+							}
+
+							if (data.error) {
+								throw data.error;
+							}
+
+							if (data.done) {
+								modelFileDigest = data.blob;
+								name = data.name;
+								uploaded = true;
+							}
+						}
+					}
+				} catch (error) {
+					console.log(error);
+				}
+			}
+		}
+
+		if (uploaded) {
+			const res = await fetch(`${$settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL}/create`, {
+				method: 'POST',
+				headers: {
+					'Content-Type': 'text/event-stream',
+					...($settings.authHeader && { Authorization: $settings.authHeader }),
+					...($user && { Authorization: `Bearer ${localStorage.token}` })
+				},
+				body: JSON.stringify({
+					name: `${name}:latest`,
+					modelfile: `FROM @${modelFileDigest}\n${modelFileContent}`
+				})
+			}).catch((err) => {
+				console.log(err);
+				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) {
+											digest = data.digest;
+
+											if (data.completed) {
+												pullProgress = Math.round((data.completed / data.total) * 1000) / 10;
+											} else {
+												pullProgress = 100;
+											}
+										}
+									}
+								}
+							}
+						}
+					} catch (error) {
+						console.log(error);
+						toast.error(error);
+					}
+				}
+			}
+		}
+
+		modelFileUrl = '';
+		modelInputFile = '';
+		modelTransferring = false;
+		uploadProgress = null;
+
 		models.set(await getModels());
 	};
 
@@ -302,8 +512,10 @@
 
 		// If OpenAI API Key exists
 		if (type === 'all' && $settings.OPENAI_API_KEY) {
+			const API_BASE_URL = $settings.OPENAI_API_BASE_URL ?? 'https://api.openai.com/v1';
+
 			// Validate OPENAI_API_KEY
-			const openaiModelRes = await fetch(`https://api.openai.com/v1/models`, {
+			const openaiModelRes = await fetch(`${API_BASE_URL}/models`, {
 				method: 'GET',
 				headers: {
 					'Content-Type': 'application/json',
@@ -320,15 +532,19 @@
 					return null;
 				});
 
-			const openAIModels = openaiModelRes?.data ?? null;
+			const openAIModels = Array.isArray(openaiModelRes)
+				? openaiModelRes
+				: openaiModelRes?.data ?? null;
 
 			models.push(
 				...(openAIModels
 					? [
 							{ name: 'hr' },
 							...openAIModels
-								.map((model) => ({ name: model.id, label: 'OpenAI' }))
+								.map((model) => ({ name: model.id, external: true }))
-								.filter((model) => model.name.includes('gpt'))
+								.filter((model) =>
+									API_BASE_URL.includes('openai') ? model.name.includes('gpt') : true
+								)
 					  ]
 					: [])
 			);
@@ -363,6 +579,7 @@
 
 		gravatarEmail = settings.gravatarEmail ?? '';
 		OPENAI_API_KEY = settings.OPENAI_API_KEY ?? '';
+		OPENAI_API_BASE_URL = settings.OPENAI_API_BASE_URL ?? 'https://api.openai.com/v1';
 
 		authEnabled = settings.authHeader !== undefined ? true : false;
 		if (authEnabled) {
@@ -476,6 +693,30 @@
 					<div class=" self-center">Models</div>
 				</button>
 
+				<button
+					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+					'external'
+						? 'bg-gray-200 dark:bg-gray-700'
+						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
+					on:click={() => {
+						selectedTab = 'external';
+					}}
+				>
+					<div class=" self-center mr-2">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 16 16"
+							fill="currentColor"
+							class="w-4 h-4"
+						>
+							<path
+								d="M1 9.5A3.5 3.5 0 0 0 4.5 13H12a3 3 0 0 0 .917-5.857 2.503 2.503 0 0 0-3.198-3.019 3.5 3.5 0 0 0-6.628 2.171A3.5 3.5 0 0 0 1 9.5Z"
+							/>
+						</svg>
+					</div>
+					<div class=" self-center">External</div>
+				</button>
+
 				<button
 					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
 					'addons'
@@ -758,9 +999,10 @@
 						</div>
 					</div>
 				{:else if selectedTab === 'models'}
-					<div class="flex flex-col space-y-3 text-sm mb-10">
+					<div class="flex flex-col h-full justify-between text-sm">
+						<div class=" space-y-3 pr-1.5 overflow-y-scroll h-80">
 							<div>
-							<div class=" mb-2.5 text-sm font-medium">Pull a model</div>
+								<div class=" mb-2.5 text-sm font-medium">Pull a model from Ollama.ai</div>
 								<div class="flex w-full">
 									<div class="flex-1 mr-2">
 										<input
@@ -770,24 +1012,53 @@
 										/>
 									</div>
 									<button
-									class="px-3 text-gray-100 bg-emerald-600 hover:bg-emerald-700 rounded transition"
+										class="px-3 text-gray-100 bg-emerald-600 hover:bg-emerald-700 disabled:bg-gray-700 disabled:cursor-not-allowed rounded transition"
 										on:click={() => {
 											pullModelHandler();
 										}}
+										disabled={modelTransferring}
 									>
+										{#if modelTransferring}
+											<div class="self-center">
+												<svg
+													class=" w-4 h-4"
+													viewBox="0 0 24 24"
+													fill="currentColor"
+													xmlns="http://www.w3.org/2000/svg"
+													><style>
+														.spinner_ajPY {
+															transform-origin: center;
+															animation: spinner_AtaB 0.75s infinite linear;
+														}
+														@keyframes spinner_AtaB {
+															100% {
+																transform: rotate(360deg);
+															}
+														}
+													</style><path
+														d="M12,1A11,11,0,1,0,23,12,11,11,0,0,0,12,1Zm0,19a8,8,0,1,1,8-8A8,8,0,0,1,12,20Z"
+														opacity=".25"
+													/><path
+														d="M10.14,1.16a11,11,0,0,0-9,8.92A1.59,1.59,0,0,0,2.46,12,1.52,1.52,0,0,0,4.11,10.7a8,8,0,0,1,6.66-6.61A1.42,1.42,0,0,0,12,2.69h0A1.57,1.57,0,0,0,10.14,1.16Z"
+														class="spinner_ajPY"
+													/></svg
+												>
+											</div>
+										{:else}
 											<svg
 												xmlns="http://www.w3.org/2000/svg"
-										viewBox="0 0 20 20"
+												viewBox="0 0 16 16"
 												fill="currentColor"
 												class="w-4 h-4"
 											>
 												<path
-											d="M10.75 2.75a.75.75 0 00-1.5 0v8.614L6.295 8.235a.75.75 0 10-1.09 1.03l4.25 4.5a.75.75 0 001.09 0l4.25-4.5a.75.75 0 00-1.09-1.03l-2.955 3.129V2.75z"
+													d="M8.75 2.75a.75.75 0 0 0-1.5 0v5.69L5.03 6.22a.75.75 0 0 0-1.06 1.06l3.5 3.5a.75.75 0 0 0 1.06 0l3.5-3.5a.75.75 0 0 0-1.06-1.06L8.75 8.44V2.75Z"
 												/>
 												<path
-											d="M3.5 12.75a.75.75 0 00-1.5 0v2.5A2.75 2.75 0 004.75 18h10.5A2.75 2.75 0 0018 15.25v-2.5a.75.75 0 00-1.5 0v2.5c0 .69-.56 1.25-1.25 1.25H4.75c-.69 0-1.25-.56-1.25-1.25v-2.5z"
+													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>
+										{/if}
 									</button>
 								</div>
 
@@ -818,6 +1089,171 @@
 							</div>
 							<hr class=" dark:border-gray-700" />
 
+							<form
+								on:submit|preventDefault={() => {
+									uploadModelHandler();
+								}}
+							>
+								<div class=" mb-2 flex w-full justify-between">
+									<div class="  text-sm font-medium">Upload a GGUF model</div>
+
+									<button
+										class="p-1 px-3 text-xs flex rounded transition"
+										on:click={() => {
+											if (modelUploadMode === 'file') {
+												modelUploadMode = 'url';
+											} else {
+												modelUploadMode = 'file';
+											}
+										}}
+										type="button"
+									>
+										{#if modelUploadMode === 'file'}
+											<span class="ml-2 self-center">File Mode</span>
+										{:else}
+											<span class="ml-2 self-center">URL Mode</span>
+										{/if}
+									</button>
+								</div>
+
+								<div class="flex w-full mb-1.5">
+									<div class="flex flex-col w-full">
+										{#if modelUploadMode === 'file'}
+											<div
+												class="flex-1 {modelInputFile && modelInputFile.length > 0 ? 'mr-2' : ''}"
+											>
+												<input
+													id="model-upload-input"
+													type="file"
+													bind:files={modelInputFile}
+													on:change={() => {
+														console.log(modelInputFile);
+													}}
+													accept=".gguf"
+													required
+													hidden
+												/>
+
+												<button
+													type="button"
+													class="w-full rounded text-left py-2 px-4 dark:text-gray-300 dark:bg-gray-800"
+													on:click={() => {
+														document.getElementById('model-upload-input').click();
+													}}
+												>
+													{#if modelInputFile && modelInputFile.length > 0}
+														{modelInputFile[0].name}
+													{:else}
+														Click here to select
+													{/if}
+												</button>
+											</div>
+										{:else}
+											<div class="flex-1 {modelFileUrl !== '' ? 'mr-2' : ''}">
+												<input
+													class="w-full rounded text-left py-2 px-4 dark:text-gray-300 dark:bg-gray-800 outline-none {modelFileUrl !==
+													''
+														? 'mr-2'
+														: ''}"
+													type="url"
+													required
+													bind:value={modelFileUrl}
+													placeholder="Type HuggingFace Resolve (Download) URL"
+												/>
+											</div>
+										{/if}
+									</div>
+
+									{#if (modelUploadMode === 'file' && modelInputFile && modelInputFile.length > 0) || (modelUploadMode === 'url' && modelFileUrl !== '')}
+										<button
+											class="px-3 text-gray-100 bg-emerald-600 hover:bg-emerald-700 disabled:bg-gray-700 disabled:cursor-not-allowed rounded transition"
+											type="submit"
+											disabled={modelTransferring}
+										>
+											{#if modelTransferring}
+												<div class="self-center">
+													<svg
+														class=" w-4 h-4"
+														viewBox="0 0 24 24"
+														fill="currentColor"
+														xmlns="http://www.w3.org/2000/svg"
+														><style>
+															.spinner_ajPY {
+																transform-origin: center;
+																animation: spinner_AtaB 0.75s infinite linear;
+															}
+															@keyframes spinner_AtaB {
+																100% {
+																	transform: rotate(360deg);
+																}
+															}
+														</style><path
+															d="M12,1A11,11,0,1,0,23,12,11,11,0,0,0,12,1Zm0,19a8,8,0,1,1,8-8A8,8,0,0,1,12,20Z"
+															opacity=".25"
+														/><path
+															d="M10.14,1.16a11,11,0,0,0-9,8.92A1.59,1.59,0,0,0,2.46,12,1.52,1.52,0,0,0,4.11,10.7a8,8,0,0,1,6.66-6.61A1.42,1.42,0,0,0,12,2.69h0A1.57,1.57,0,0,0,10.14,1.16Z"
+															class="spinner_ajPY"
+														/></svg
+													>
+												</div>
+											{:else}
+												<svg
+													xmlns="http://www.w3.org/2000/svg"
+													viewBox="0 0 16 16"
+													fill="currentColor"
+													class="w-4 h-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>
+											{/if}
+										</button>
+									{/if}
+								</div>
+
+								{#if (modelUploadMode === 'file' && modelInputFile && modelInputFile.length > 0) || (modelUploadMode === 'url' && modelFileUrl !== '')}
+									<div>
+										<div>
+											<div class=" my-2.5 text-sm font-medium">Modelfile Content</div>
+											<textarea
+												bind:value={modelFileContent}
+												class="w-full rounded py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none resize-none"
+												rows="6"
+											/>
+										</div>
+									</div>
+								{/if}
+								<div class=" mt-1 text-xs text-gray-400 dark:text-gray-500">
+									To access the GGUF models available for downloading, <a
+										class=" text-gray-500 dark:text-gray-300 font-medium"
+										href="https://huggingface.co/models?search=gguf"
+										target="_blank">click here.</a
+									>
+								</div>
+
+								{#if uploadProgress !== null}
+									<div class="mt-2">
+										<div class=" mb-2 text-xs">Upload Progress</div>
+										<div class="w-full rounded-full dark:bg-gray-800">
+											<div
+												class="dark:bg-gray-600 text-xs font-medium text-blue-100 text-center p-0.5 leading-none rounded-full"
+												style="width: {Math.max(15, uploadProgress ?? 0)}%"
+											>
+												{uploadProgress ?? 0}%
+											</div>
+										</div>
+										<div class="mt-1 text-xs dark:text-gray-500" style="font-size: 0.5rem;">
+											{modelFileDigest}
+										</div>
+									</div>
+								{/if}
+							</form>
+							<hr class=" dark:border-gray-700" />
+
 							<div>
 								<div class=" mb-2.5 text-sm font-medium">Delete a model</div>
 								<div class="flex w-full">
@@ -832,7 +1268,10 @@
 											{/if}
 											{#each $models.filter((m) => m.size != null) as model}
 												<option value={model.name} class="bg-gray-100 dark:bg-gray-700"
-												>{model.name + ' (' + (model.size / 1024 ** 3).toFixed(1) + ' GB)'}</option
+													>{model.name +
+														' (' +
+														(model.size / 1024 ** 3).toFixed(1) +
+														' GB)'}</option
 												>
 											{/each}
 										</select>
@@ -845,13 +1284,13 @@
 									>
 										<svg
 											xmlns="http://www.w3.org/2000/svg"
-										viewBox="0 0 20 20"
+											viewBox="0 0 16 16"
 											fill="currentColor"
 											class="w-4 h-4"
 										>
 											<path
 												fill-rule="evenodd"
-											d="M8.75 1A2.75 2.75 0 006 3.75v.443c-.795.077-1.584.176-2.365.298a.75.75 0 10.23 1.482l.149-.022.841 10.518A2.75 2.75 0 007.596 19h4.807a2.75 2.75 0 002.742-2.53l.841-10.52.149.023a.75.75 0 00.23-1.482A41.03 41.03 0 0014 4.193V3.75A2.75 2.75 0 0011.25 1h-2.5zM10 4c.84 0 1.673.025 2.5.075V3.75c0-.69-.56-1.25-1.25-1.25h-2.5c-.69 0-1.25.56-1.25 1.25v.325C8.327 4.025 9.16 4 10 4zM8.58 7.72a.75.75 0 00-1.5.06l.3 7.5a.75.75 0 101.5-.06l-.3-7.5zm4.34.06a.75.75 0 10-1.5-.06l-.3 7.5a.75.75 0 101.5.06l.3-7.5z"
+												d="M5 3.25V4H2.75a.75.75 0 0 0 0 1.5h.3l.815 8.15A1.5 1.5 0 0 0 5.357 15h5.285a1.5 1.5 0 0 0 1.493-1.35l.815-8.15h.3a.75.75 0 0 0 0-1.5H11v-.75A2.25 2.25 0 0 0 8.75 1h-1.5A2.25 2.25 0 0 0 5 3.25Zm2.25-.75a.75.75 0 0 0-.75.75V4h3v-.75a.75.75 0 0 0-.75-.75h-1.5ZM6.05 6a.75.75 0 0 1 .787.713l.275 5.5a.75.75 0 0 1-1.498.075l-.275-5.5A.75.75 0 0 1 6.05 6Zm3.9 0a.75.75 0 0 1 .712.787l-.275 5.5a.75.75 0 0 1-1.498-.075l.275-5.5a.75.75 0 0 1 .786-.711Z"
 												clip-rule="evenodd"
 											/>
 										</svg>
@@ -859,14 +1298,74 @@
 								</div>
 							</div>
 						</div>
+					</div>
+				{:else if selectedTab === 'external'}
+					<form
+						class="flex flex-col h-full justify-between space-y-3 text-sm"
+						on:submit|preventDefault={() => {
+							saveSettings({
+								OPENAI_API_KEY: OPENAI_API_KEY !== '' ? OPENAI_API_KEY : undefined,
+								OPENAI_API_BASE_URL: OPENAI_API_BASE_URL !== '' ? OPENAI_API_BASE_URL : undefined
+							});
+							show = false;
+						}}
+					>
+						<div class=" space-y-3">
+							<div>
+								<div class=" mb-2.5 text-sm font-medium">OpenAI API Key</div>
+								<div class="flex w-full">
+									<div class="flex-1">
+										<input
+											class="w-full rounded py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none"
+											placeholder="Enter OpenAI API Key"
+											bind:value={OPENAI_API_KEY}
+											autocomplete="off"
+										/>
+									</div>
+								</div>
+								<div class="mt-2 text-xs text-gray-400 dark:text-gray-500">
+									Adds optional support for online models.
+								</div>
+							</div>
+
+							<hr class=" dark:border-gray-700" />
+
+							<div>
+								<div class=" mb-2.5 text-sm font-medium">OpenAI API Base URL</div>
+								<div class="flex w-full">
+									<div class="flex-1">
+										<input
+											class="w-full rounded py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none"
+											placeholder="Enter OpenAI API Key"
+											bind:value={OPENAI_API_BASE_URL}
+											autocomplete="off"
+										/>
+									</div>
+								</div>
+								<div class="mt-2 text-xs text-gray-400 dark:text-gray-500">
+									WebUI will make requests to <span class=" text-gray-200"
+										>'{OPENAI_API_BASE_URL}/chat'</span
+									>
+								</div>
+							</div>
+						</div>
+
+						<div class="flex justify-end pt-3 text-sm font-medium">
+							<button
+								class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded"
+								type="submit"
+							>
+								Save
+							</button>
+						</div>
+					</form>
 				{:else if selectedTab === 'addons'}
 					<form
 						class="flex flex-col h-full justify-between space-y-3 text-sm"
 						on:submit|preventDefault={() => {
 							saveSettings({
 								gravatarEmail: gravatarEmail !== '' ? gravatarEmail : undefined,
-								gravatarUrl: gravatarEmail !== '' ? getGravatarURL(gravatarEmail) : undefined,
+								gravatarUrl: gravatarEmail !== '' ? getGravatarURL(gravatarEmail) : undefined
-								OPENAI_API_KEY: OPENAI_API_KEY !== '' ? OPENAI_API_KEY : undefined
 							});
 							show = false;
 						}}
@@ -962,26 +1461,6 @@
 									>
 								</div>
 							</div>
-
-							<hr class=" dark:border-gray-700" />
-							<div>
-								<div class=" mb-2.5 text-sm font-medium">
-									OpenAI API Key <span class=" text-gray-400 text-sm">(optional)</span>
-								</div>
-								<div class="flex w-full">
-									<div class="flex-1">
-										<input
-											class="w-full rounded py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-800 outline-none"
-											placeholder="Enter OpenAI API Key"
-											bind:value={OPENAI_API_KEY}
-											autocomplete="off"
-										/>
-									</div>
-								</div>
-								<div class="mt-2 text-xs text-gray-400 dark:text-gray-500">
-									Adds optional support for 'gpt-*' models available.
-								</div>
-							</div>
 						</div>
 
 						<div class="flex justify-end pt-3 text-sm font-medium">

src/lib/constants.ts

@@ -8,7 +8,8 @@ export const OLLAMA_API_BASE_URL =
 			: `http://localhost:11434/api`
 		: PUBLIC_API_BASE_URL;
 
-export const WEBUI_API_BASE_URL = dev ? `http://${location.hostname}:8080/api/v1` : `/api/v1`;
+export const WEBUI_BASE_URL = dev ? `http://${location.hostname}:8080` : ``;
+export const WEBUI_API_BASE_URL = `${WEBUI_BASE_URL}/api/v1`;
 
 export const WEB_UI_VERSION = 'v1.0.0-alpha-static';
 

src/routes/(app)/+layout.svelte

@@ -55,7 +55,9 @@
 		// If OpenAI API Key exists
 		if ($settings.OPENAI_API_KEY) {
 			// Validate OPENAI_API_KEY
-			const openaiModelRes = await fetch(`https://api.openai.com/v1/models`, {
+
+			const API_BASE_URL = $settings.OPENAI_API_BASE_URL ?? 'https://api.openai.com/v1';
+			const openaiModelRes = await fetch(`${API_BASE_URL}/models`, {
 				method: 'GET',
 				headers: {
 					'Content-Type': 'application/json',
@@ -72,15 +74,19 @@
 					return null;
 				});
 
-			const openAIModels = openaiModelRes?.data ?? null;
+			const openAIModels = Array.isArray(openaiModelRes)
+				? openaiModelRes
+				: openaiModelRes?.data ?? null;
 
 			models.push(
 				...(openAIModels
 					? [
 							{ name: 'hr' },
 							...openAIModels
-								.map((model) => ({ name: model.id, label: 'OpenAI' }))
+								.map((model) => ({ name: model.id, external: true }))
-								.filter((model) => model.name.includes('gpt'))
+								.filter((model) =>
+									API_BASE_URL.includes('openai') ? model.name.includes('gpt') : true
+								)
 					  ]
 					: [])
 			);

src/routes/(app)/+page.svelte

@@ -7,7 +7,7 @@
 	import { splitStream } from '$lib/utils';
 	import { goto } from '$app/navigation';
 
-	import { config, modelfiles, user, settings, db, chats, chatId } from '$lib/stores';
+	import { config, models, modelfiles, user, settings, db, chats, chatId } from '$lib/stores';
 
 	import MessageInput from '$lib/components/chat/MessageInput.svelte';
 	import Messages from '$lib/components/chat/Messages.svelte';
@@ -130,7 +130,8 @@
 	const sendPrompt = async (userPrompt, parentId, _chatId) => {
 		await Promise.all(
 			selectedModels.map(async (model) => {
-				if (model.includes('gpt-')) {
+				console.log(model);
+				if ($models.filter((m) => m.name === model)[0].external) {
 					await sendPromptOpenAI(model, userPrompt, parentId, _chatId);
 				} else {
 					await sendPromptOllama(model, userPrompt, parentId, _chatId);
@@ -244,6 +245,13 @@
 								}
 							} else {
 								responseMessage.done = true;
+
+								if (responseMessage.content == '') {
+									responseMessage.error = true;
+									responseMessage.content =
+										'Oops! No text generated from Ollama, Please try again.';
+								}
+
 								responseMessage.context = data.context ?? null;
 								responseMessage.info = {
 									total_duration: data.total_duration,
@@ -364,15 +372,15 @@
 					];
 				}
 
-				await tick();
-
 				window.scrollTo({ top: document.body.scrollHeight });
 
-				const res = await fetch(`https://api.openai.com/v1/chat/completions`, {
+				const res = await fetch(
+					`${$settings.OPENAI_API_BASE_URL ?? 'https://api.openai.com/v1'}/chat/completions`,
+					{
 						method: 'POST',
 						headers: {
-						'Content-Type': 'application/json',
+							Authorization: `Bearer ${$settings.OPENAI_API_KEY}`,
-						Authorization: `Bearer ${$settings.OPENAI_API_KEY}`
+							'Content-Type': 'application/json'
 						},
 						body: JSON.stringify({
 							model: model,
@@ -413,8 +421,13 @@
 							num_ctx: $settings.num_ctx ?? undefined,
 							frequency_penalty: $settings.repeat_penalty ?? undefined
 						})
+					}
+				).catch((err) => {
+					console.log(err);
+					return null;
 				});
 
+				if (res && res.ok) {
 					const reader = res.body
 						.pipeThrough(new TextDecoderStream())
 						.pipeThrough(splitStream('\n'))
@@ -454,6 +467,17 @@
 							console.log(error);
 						}
 
+						if ($settings.notificationEnabled && !document.hasFocus()) {
+							const notification = new Notification(`OpenAI ${model}`, {
+								body: responseMessage.content,
+								icon: '/favicon.png'
+							});
+						}
+
+						if ($settings.responseAutoCopy) {
+							copyToClipboard(responseMessage.content);
+						}
+
 						if (autoScroll) {
 							window.scrollTo({ top: document.body.scrollHeight });
 						}
@@ -475,22 +499,36 @@
 							history: history
 						});
 					}
+				} else {
+					if (res !== null) {
+						const error = await res.json();
+						console.log(error);
+						if ('detail' in error) {
+							toast.error(error.detail);
+							responseMessage.content = error.detail;
+						} else {
+							if ('message' in error.error) {
+								toast.error(error.error.message);
+								responseMessage.content = error.error.message;
+							} else {
+								toast.error(error.error);
+								responseMessage.content = error.error;
+							}
+						}
+					} else {
+						toast.error(`Uh-oh! There was an issue connecting to ${model}.`);
+						responseMessage.content = `Uh-oh! There was an issue connecting to ${model}.`;
+					}
+
+					responseMessage.error = true;
+					responseMessage.content = `Uh-oh! There was an issue connecting to ${model}.`;
+					responseMessage.done = true;
+					messages = messages;
+				}
 
 				stopResponseFlag = false;
-
 				await tick();
 
-				if ($settings.notificationEnabled && !document.hasFocus()) {
-					const notification = new Notification(`OpenAI ${model}`, {
-						body: responseMessage.content,
-						icon: '/favicon.png'
-					});
-				}
-
-				if ($settings.responseAutoCopy) {
-					copyToClipboard(responseMessage.content);
-				}
-
 				if (autoScroll) {
 					window.scrollTo({ top: document.body.scrollHeight });
 				}

src/routes/(app)/c/[id]/+page.svelte

@@ -6,7 +6,7 @@
 	import { onMount, tick } from 'svelte';
 	import { convertMessagesToHistory, splitStream } from '$lib/utils';
 	import { goto } from '$app/navigation';
-	import { config, modelfiles, user, settings, db, chats, chatId } from '$lib/stores';
+	import { config, models, modelfiles, user, settings, db, chats, chatId } from '$lib/stores';
 
 	import MessageInput from '$lib/components/chat/MessageInput.svelte';
 	import Messages from '$lib/components/chat/Messages.svelte';
@@ -144,7 +144,8 @@
 	const sendPrompt = async (userPrompt, parentId, _chatId) => {
 		await Promise.all(
 			selectedModels.map(async (model) => {
-				if (model.includes('gpt-')) {
+				console.log(model);
+				if ($models.filter((m) => m.name === model)[0].external) {
 					await sendPromptOpenAI(model, userPrompt, parentId, _chatId);
 				} else {
 					await sendPromptOllama(model, userPrompt, parentId, _chatId);
@@ -258,6 +259,13 @@
 								}
 							} else {
 								responseMessage.done = true;
+
+								if (responseMessage.content == '') {
+									responseMessage.error = true;
+									responseMessage.content =
+										'Oops! No text generated from Ollama, Please try again.';
+								}
+
 								responseMessage.context = data.context ?? null;
 								responseMessage.info = {
 									total_duration: data.total_duration,
@@ -378,15 +386,15 @@
 					];
 				}
 
-				await tick();
-
 				window.scrollTo({ top: document.body.scrollHeight });
 
-				const res = await fetch(`https://api.openai.com/v1/chat/completions`, {
+				const res = await fetch(
+					`${$settings.OPENAI_API_BASE_URL ?? 'https://api.openai.com/v1'}/chat/completions`,
+					{
 						method: 'POST',
 						headers: {
-						'Content-Type': 'application/json',
+							Authorization: `Bearer ${$settings.OPENAI_API_KEY}`,
-						Authorization: `Bearer ${$settings.OPENAI_API_KEY}`
+							'Content-Type': 'application/json'
 						},
 						body: JSON.stringify({
 							model: model,
@@ -427,8 +435,13 @@
 							num_ctx: $settings.num_ctx ?? undefined,
 							frequency_penalty: $settings.repeat_penalty ?? undefined
 						})
+					}
+				).catch((err) => {
+					console.log(err);
+					return null;
 				});
 
+				if (res && res.ok) {
 					const reader = res.body
 						.pipeThrough(new TextDecoderStream())
 						.pipeThrough(splitStream('\n'))
@@ -468,6 +481,17 @@
 							console.log(error);
 						}
 
+						if ($settings.notificationEnabled && !document.hasFocus()) {
+							const notification = new Notification(`OpenAI ${model}`, {
+								body: responseMessage.content,
+								icon: '/favicon.png'
+							});
+						}
+
+						if ($settings.responseAutoCopy) {
+							copyToClipboard(responseMessage.content);
+						}
+
 						if (autoScroll) {
 							window.scrollTo({ top: document.body.scrollHeight });
 						}
@@ -489,22 +513,36 @@
 							history: history
 						});
 					}
+				} else {
+					if (res !== null) {
+						const error = await res.json();
+						console.log(error);
+						if ('detail' in error) {
+							toast.error(error.detail);
+							responseMessage.content = error.detail;
+						} else {
+							if ('message' in error.error) {
+								toast.error(error.error.message);
+								responseMessage.content = error.error.message;
+							} else {
+								toast.error(error.error);
+								responseMessage.content = error.error;
+							}
+						}
+					} else {
+						toast.error(`Uh-oh! There was an issue connecting to ${model}.`);
+						responseMessage.content = `Uh-oh! There was an issue connecting to ${model}.`;
+					}
+
+					responseMessage.error = true;
+					responseMessage.content = `Uh-oh! There was an issue connecting to ${model}.`;
+					responseMessage.done = true;
+					messages = messages;
+				}
 
 				stopResponseFlag = false;
-
 				await tick();
 
-				if ($settings.notificationEnabled && !document.hasFocus()) {
-					const notification = new Notification(`OpenAI ${model}`, {
-						body: responseMessage.content,
-						icon: '/favicon.png'
-					});
-				}
-
-				if ($settings.responseAutoCopy) {
-					copyToClipboard(responseMessage.content);
-				}
-
 				if (autoScroll) {
 					window.scrollTo({ top: document.body.scrollHeight });
 				}