diff --git a/backend/apps/web/routers/chats.py b/backend/apps/web/routers/chats.py index f061b145b..e97e14730 100644 --- a/backend/apps/web/routers/chats.py +++ b/backend/apps/web/routers/chats.py @@ -17,7 +17,8 @@ from apps.web.models.chats import ( ) from utils.utils import ( - bearer_scheme, ) + bearer_scheme, +) from constants import ERROR_MESSAGES router = APIRouter() @@ -29,7 +30,8 @@ router = APIRouter() @router.get("/", response_model=List[ChatTitleIdResponse]) async def get_user_chats( - user=Depends(get_current_user), skip: int = 0, limit: int = 50): + user=Depends(get_current_user), skip: int = 0, limit: int = 50 +): return Chats.get_chat_lists_by_user_id(user.id, skip, limit) @@ -41,9 +43,8 @@ async def get_user_chats( @router.get("/all", response_model=List[ChatResponse]) async def get_all_user_chats(user=Depends(get_current_user)): return [ - ChatResponse(**{ - **chat.model_dump(), "chat": json.loads(chat.chat) - }) for chat in Chats.get_all_chats_by_user_id(user.id) + ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)}) + for chat in Chats.get_all_chats_by_user_id(user.id) ] @@ -54,8 +55,14 @@ async def get_all_user_chats(user=Depends(get_current_user)): @router.post("/new", response_model=Optional[ChatResponse]) async def create_new_chat(form_data: ChatForm, user=Depends(get_current_user)): - chat = Chats.insert_new_chat(user.id, form_data) - return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)}) + try: + chat = Chats.insert_new_chat(user.id, form_data) + return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)}) + except Exception as e: + print(e) + raise HTTPException( + status_code=status.HTTP_400_BAD_REQUEST, detail=ERROR_MESSAGES.DEFAULT() + ) ############################ @@ -68,12 +75,11 @@ async def get_chat_by_id(id: str, user=Depends(get_current_user)): chat = Chats.get_chat_by_id_and_user_id(id, user.id) if chat: - return ChatResponse(**{ - **chat.model_dump(), "chat": json.loads(chat.chat) - }) + return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)}) else: - raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, - detail=ERROR_MESSAGES.NOT_FOUND) + raise HTTPException( + status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND + ) ############################ @@ -82,17 +88,15 @@ async def get_chat_by_id(id: str, user=Depends(get_current_user)): @router.post("/{id}", response_model=Optional[ChatResponse]) -async def update_chat_by_id(id: str, - form_data: ChatForm, - user=Depends(get_current_user)): +async def update_chat_by_id( + id: str, form_data: ChatForm, user=Depends(get_current_user) +): chat = Chats.get_chat_by_id_and_user_id(id, user.id) if chat: updated_chat = {**json.loads(chat.chat), **form_data.chat} chat = Chats.update_chat_by_id(id, updated_chat) - return ChatResponse(**{ - **chat.model_dump(), "chat": json.loads(chat.chat) - }) + return ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)}) else: raise HTTPException( status_code=status.HTTP_401_UNAUTHORIZED, diff --git a/backend/start.sh b/backend/start.sh index 44e0c5810..e6d09364e 100755 --- a/backend/start.sh +++ b/backend/start.sh @@ -1,4 +1,7 @@ #!/usr/bin/env bash +SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd ) +cd "$SCRIPT_DIR" || exit + PORT="${PORT:-8080}" -uvicorn main:app --host 0.0.0.0 --port $PORT --forwarded-allow-ips '*' +uvicorn main:app --host 0.0.0.0 --port "$PORT" --forwarded-allow-ips '*' diff --git a/docs/apache.md b/docs/apache.md new file mode 100644 index 000000000..481fc7468 --- /dev/null +++ b/docs/apache.md @@ -0,0 +1,204 @@ +# Hosting UI and Models separately + +Sometimes, its beneficial to host Ollama, separate from the UI, but retain the RAG and RBAC support features shared across users: + +# Ollama WebUI Configuration + +## UI Configuration + +For the UI configuration, you can set up the Apache VirtualHost as follows: + +``` +# Assuming you have a website hosting this UI at "server.com" + + ServerName server.com + DocumentRoot /home/server/public_html + + ProxyPass / http://server.com:3000/ nocanon + ProxyPassReverse / http://server.com:3000/ + + +``` + +Enable the site first before you can request SSL: + +`a2ensite server.com.conf` # this will enable the site. a2ensite is short for "Apache 2 Enable Site" + + +``` +# For SSL + + ServerName server.com + DocumentRoot /home/server/public_html + + ProxyPass / http://server.com:3000/ nocanon + ProxyPassReverse / http://server.com:3000/ + + SSLEngine on + SSLCertificateFile /etc/ssl/virtualmin/170514456861234/ssl.cert + SSLCertificateKeyFile /etc/ssl/virtualmin/170514456861234/ssl.key + SSLProtocol all -SSLv2 -SSLv3 -TLSv1 -TLSv1.1 + + SSLProxyEngine on + SSLCACertificateFile /etc/ssl/virtualmin/170514456865864/ssl.ca + + +``` + +I'm using virtualmin here for my SSL clusters, but you can also use certbot directly or your preferred SSL method. To use SSL: + +### Prerequisites. + +Run the following commands: + +`snap install certbot --classic` +`snap apt install python3-certbot-apache` (this will install the apache plugin). + +Navigate to the apache sites-available directory: + +`cd /etc/apache2/sites-available/` + +Create server.com.conf if it is not yet already created, containing the above `` configuration (it should match your case. Modify as necessary). Use the one without the SSL: + +Once it's created, run `certbot --apache -d server.com`, this will request and add/create an SSL keys for you as well as create the server.com.le-ssl.conf + + +# Configuring Ollama Server + +On your latest installation of Ollama, make sure that you have setup your api server from the official Ollama reference: + +[Ollama FAQ](https://github.com/jmorganca/ollama/blob/main/docs/faq.md) + + +### TL;DR + +The guide doesn't seem to match the current updated service file on linux. So, we will address it here: + +Unless when you're compiling Ollama from source, installing with the standard install `curl https://ollama.ai/install.sh | sh` creates a file called `ollama.service` in /etc/systemd/system. You can use nano to edit the file: + +``` +sudo nano /etc/systemd/system/ollama.service +``` + +Add the following lines: +``` +Environment="OLLAMA_HOST=0.0.0.0:11434" # this line is mandatory. You can also specify +``` + +For instance: + +``` +[Unit] +Description=Ollama Service +After=network-online.target + +[Service] +ExecStart=/usr/local/bin/ollama serve +Environment="OLLAMA_HOST=0.0.0.0:11434" # this line is mandatory. You can also specify 192.168.254.109:DIFFERENT_PORT, format +Environment="OLLAMA_ORIGINS=http://192.168.254.106:11434,https://models.server.city" # this line is optional +User=ollama +Group=ollama +Restart=always +RestartSec=3 +Environment="PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/s> + +[Install] +WantedBy=default.target +``` + + +Save the file by pressing CTRL+S, then press CTRL+X + +When your computer restarts, the Ollama server will now be listening on the IP:PORT you specified, in this case 0.0.0.0:11434, or 192.168.254.106:11434 (whatever your local IP address is). Make sure that your router is correctly configured to serve pages from that local IP by forwarding 11434 to your local IP server. + + +# Ollama Model Configuration +## For the Ollama model configuration, use the following Apache VirtualHost setup: + + +Navigate to the apache sites-available directory: + +`cd /etc/apache2/sites-available/` + +`nano models.server.city.conf` # match this with your ollama server domain + +Add the folloing virtualhost containing this example (modify as needed): + +``` + +# Assuming you have a website hosting this UI at "models.server.city" + + + DocumentRoot "/var/www/html/" + ServerName models.server.city + + Options None + Require all granted + + + ProxyRequests Off + ProxyPreserveHost On + ProxyAddHeaders On + SSLProxyEngine on + + ProxyPass / http://server.city:1000/ nocanon # or port 11434 + ProxyPassReverse / http://server.city:1000/ # or port 11434 + + SSLCertificateFile /etc/letsencrypt/live/models.server.city/fullchain.pem + SSLCertificateKeyFile /etc/letsencrypt/live/models.server.city/privkey.pem + Include /etc/letsencrypt/options-ssl-apache.conf + + +``` + +You may need to enable the site first (if you haven't done so yet) before you can request SSL: + +`a2ensite models.server.city.conf` + +#### For the SSL part of Ollama server + +Run the following commands: + +Navigate to the apache sites-available directory: + +`cd /etc/apache2/sites-available/` +`certbot --apache -d server.com` + +``` + + DocumentRoot "/var/www/html/" + ServerName models.server.city + + Options None + Require all granted + + + ProxyRequests Off + ProxyPreserveHost On + ProxyAddHeaders On + SSLProxyEngine on + + ProxyPass / http://server.city:1000/ nocanon # or port 11434 + ProxyPassReverse / http://server.city:1000/ # or port 11434 + + RewriteEngine on + RewriteCond %{SERVER_NAME} =models.server.city + RewriteRule ^ https://%{SERVER_NAME}%{REQUEST_URI} [END,NE,R=permanent] + + +``` + +Don't forget to restart/reload Apache with `systemctl reload apache2` + +Open your site at https://server.com! + +**Congratulations**, your _**Open-AI-like Chat-GPT style UI**_ is now serving AI with RAG, RBAC and multimodal features! Download Ollama models if you haven't yet done so! + +If you encounter any misconfiguration or errors, please file an issue or engage with our discussion. There are a lot of friendly developers here to assist you. + +Let's make this UI much more user friendly for everyone! + +Thanks for making ollama-webui your UI Choice for AI! + + +This doc is made by **Bob Reyes**, your **Ollama-Web-UI** fan from the Philippines. diff --git a/src/lib/components/chat/MessageInput.svelte b/src/lib/components/chat/MessageInput.svelte index 3fae5a764..4830b98c7 100644 --- a/src/lib/components/chat/MessageInput.svelte +++ b/src/lib/components/chat/MessageInput.svelte @@ -301,7 +301,10 @@ const file = inputFiles[0]; if (['image/gif', 'image/jpeg', 'image/png'].includes(file['type'])) { reader.readAsDataURL(file); - } else if (SUPPORTED_FILE_TYPE.includes(file['type'])) { + } else if ( + SUPPORTED_FILE_TYPE.includes(file['type']) || + ['md'].includes(file.name.split('.').at(-1)) + ) { uploadDoc(file); filesInputElement.value = ''; } else { @@ -461,8 +464,8 @@ placeholder={chatInputPlaceholder !== '' ? chatInputPlaceholder : speechRecognitionListening - ? 'Listening...' - : 'Send a message'} + ? 'Listening...' + : 'Send a message'} bind:value={prompt} on:keypress={(e) => { if (e.keyCode == 13 && !e.shiftKey) { diff --git a/src/lib/components/chat/SettingsModal.svelte b/src/lib/components/chat/SettingsModal.svelte index 35ad9f1aa..c79fe1068 100644 --- a/src/lib/components/chat/SettingsModal.svelte +++ b/src/lib/components/chat/SettingsModal.svelte @@ -21,7 +21,7 @@ import { WEB_UI_VERSION, WEBUI_API_BASE_URL } from '$lib/constants'; import { config, models, settings, user, chats } from '$lib/stores'; - import { splitStream, getGravatarURL } from '$lib/utils'; + import { splitStream, getGravatarURL, getImportOrigin, convertOpenAIChats } from '$lib/utils'; import Advanced from './Settings/Advanced.svelte'; import Modal from '../common/Modal.svelte'; @@ -132,6 +132,13 @@ reader.onload = (event) => { let chats = JSON.parse(event.target.result); console.log(chats); + if (getImportOrigin(chats) == 'openai') { + try { + chats = convertOpenAIChats(chats); + } catch (error) { + console.log('Unable to import chats:', error); + } + } importChats(chats); }; diff --git a/src/lib/utils/index.ts b/src/lib/utils/index.ts index 129a1d12c..e7dfba2c7 100644 --- a/src/lib/utils/index.ts +++ b/src/lib/utils/index.ts @@ -192,3 +192,74 @@ export const calculateSHA256 = async (file) => { throw error; } }; + +export const getImportOrigin = (_chats) => { + // Check what external service chat imports are from + if ('mapping' in _chats[0]) { + return 'openai'; + } + return 'webui'; +}; + +const convertOpenAIMessages = (convo) => { + // Parse OpenAI chat messages and create chat dictionary for creating new chats + const mapping = convo['mapping']; + const messages = []; + let currentId = ''; + + for (let message_id in mapping) { + const message = mapping[message_id]; + currentId = message_id; + if (message['message'] == null || message['message']['content']['parts'][0] == '') { + // Skip chat messages with no content + continue; + } else { + const new_chat = { + id: message_id, + parentId: messages.length > 0 && message['parent'] in mapping ? message['parent'] : null, + childrenIds: message['children'] || [], + role: message['message']?.['author']?.['role'] !== 'user' ? 'assistant' : 'user', + content: message['message']?.['content']?.['parts']?.[0] || '', + model: 'gpt-3.5-turbo', + done: true, + context: null + }; + messages.push(new_chat); + } + } + + let history = {}; + messages.forEach((obj) => (history[obj.id] = obj)); + + const chat = { + history: { + currentId: currentId, + messages: history // Need to convert this to not a list and instead a json object + }, + models: ['gpt-3.5-turbo'], + messages: messages, + options: {}, + timestamp: convo['create_time'], + title: convo['title'] ?? 'New Chat' + }; + return chat; +}; + +export const convertOpenAIChats = (_chats) => { + // Create a list of dictionaries with each conversation from import + const chats = []; + for (let convo of _chats) { + const chat = convertOpenAIMessages(convo); + + if (Object.keys(chat.history.messages).length > 0) { + chats.push({ + id: convo['id'], + user_id: '', + title: convo['title'], + chat: chat, + timestamp: convo['timestamp'] + }); + } + } + return chats; +}; diff --git a/src/routes/(app)/c/[id]/+page.svelte b/src/routes/(app)/c/[id]/+page.svelte index c0db9c5f3..c4774aaae 100644 --- a/src/routes/(app)/c/[id]/+page.svelte +++ b/src/routes/(app)/c/[id]/+page.svelte @@ -200,8 +200,15 @@ await chatId.set('local'); } await tick(); - } + } else if (chat.chat["models"] != selectedModels) { + // If model is not saved in DB, then save selectedmodel when message is sent + chat = await updateChatById(localStorage.token, $chatId, { + models: selectedModels + }); + await chats.set(await getChatList(localStorage.token)); + } + // Reset chat input textarea prompt = ''; files = []; @@ -696,7 +703,7 @@
- 0} /> + 0 && !selectedModels.includes('')} />
diff --git a/src/routes/(app)/documents/+page.svelte b/src/routes/(app)/documents/+page.svelte index d79056e24..9a0aa1301 100644 --- a/src/routes/(app)/documents/+page.svelte +++ b/src/routes/(app)/documents/+page.svelte @@ -67,7 +67,10 @@ if (inputFiles && inputFiles.length > 0) { const file = inputFiles[0]; - if (SUPPORTED_FILE_TYPE.includes(file['type'])) { + if ( + SUPPORTED_FILE_TYPE.includes(file['type']) || + ['md'].includes(file.name.split('.').at(-1)) + ) { uploadDoc(file); } else { toast.error(`Unsupported File Type '${file['type']}'.`); @@ -144,7 +147,10 @@ on:change={async (e) => { if (inputFiles && inputFiles.length > 0) { const file = inputFiles[0]; - if (SUPPORTED_FILE_TYPE.includes(file['type'])) { + if ( + SUPPORTED_FILE_TYPE.includes(file['type']) || + ['md'].includes(file.name.split('.').at(-1)) + ) { uploadDoc(file); } else { toast.error(`Unsupported File Type '${file['type']}'.`);