diff --git a/Dockerfile b/Dockerfile index 00b0b10e5..5c157daee 100644 --- a/Dockerfile +++ b/Dockerfile @@ -2,12 +2,6 @@ FROM imbios/bun-node:alpine as build -ARG OLLAMA_API_BASE_URL='/ollama/api' -RUN echo $OLLAMA_API_BASE_URL - -ENV PUBLIC_API_BASE_URL $OLLAMA_API_BASE_URL -RUN echo $PUBLIC_API_BASE_URL - WORKDIR /app COPY package.json package-lock.json ./ diff --git a/README.md b/README.md index d77994c90..808740ff8 100644 --- a/README.md +++ b/README.md @@ -35,6 +35,8 @@ Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you c - πŸ“œ **Prompt Preset Support**: Instantly access preset prompts using the '/' command in the chat input. Load predefined conversation starters effortlessly and expedite your interactions. Effortlessly import prompts through [OllamaHub](https://ollamahub.com/) integration. +- πŸ‘πŸ‘Ž **RLHF Annotation**: Empower your messages by rating them with thumbs up and thumbs down, facilitating the creation of datasets for Reinforcement Learning from Human Feedback (RLHF). Utilize your messages to train or fine-tune models, all while ensuring the confidentiality of locally saved data. + - πŸ“₯πŸ—‘οΈ **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. diff --git a/TROUBLESHOOTING.md b/TROUBLESHOOTING.md index 339c230fd..f7976550d 100644 --- a/TROUBLESHOOTING.md +++ b/TROUBLESHOOTING.md @@ -4,7 +4,7 @@ The Ollama WebUI system is designed to streamline interactions between the client (your browser) and the Ollama API. At the heart of this design is a backend reverse proxy, enhancing security and resolving CORS issues. -- **How it Works**: When you make a request (like `/ollama/api/tags`) from the Ollama WebUI, it doesn’t go directly to the Ollama API. Instead, it first reaches the Ollama WebUI backend. The backend then forwards this request to the Ollama API via the route you define in the `OLLAMA_API_BASE_URL` environment variable. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_API_BASE_URL/tags` in the backend. +- **How it Works**: The Ollama WebUI is designed to interact with the Ollama API through a specific route. When a request is made from the WebUI to Ollama, it is not directly sent to the Ollama API. Initially, the request is sent to the Ollama WebUI backend via `/ollama/api` route. From there, the backend is responsible for forwarding the request to the Ollama API. This forwarding is accomplished by using the route specified in the `OLLAMA_API_BASE_URL` environment variable. Therefore, a request made to `/ollama/api` in the WebUI is effectively the same as making a request to `OLLAMA_API_BASE_URL` in the backend. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_API_BASE_URL/tags` in the backend. - **Security Benefits**: This design prevents direct exposure of the Ollama API to the frontend, safeguarding against potential CORS (Cross-Origin Resource Sharing) issues and unauthorized access. Requiring authentication to access the Ollama API further enhances this security layer. @@ -27,6 +27,6 @@ docker run -d --network=host -v ollama-webui:/app/backend/data -e OLLAMA_API_BAS 1. **Verify Ollama URL Format**: - When running the Web UI container, ensure the `OLLAMA_API_BASE_URL` is correctly set, including the `/api` suffix. (e.g., `http://192.168.1.1:11434/api` for different host setups). - In the Ollama WebUI, navigate to "Settings" > "General". - - Confirm that the Ollama Server URL is correctly set to `/ollama/api`, including the `/api` suffix. + - Confirm that the Ollama Server URL is correctly set to `[OLLAMA URL]/api` (e.g., `http://localhost:11434/api`), including the `/api` suffix. By following these enhanced troubleshooting steps, connection issues should be effectively resolved. For further assistance or queries, feel free to reach out to us on our community Discord. diff --git a/backend/apps/ollama/main.py b/backend/apps/ollama/main.py index 8101d2665..f77f7ea12 100644 --- a/backend/apps/ollama/main.py +++ b/backend/apps/ollama/main.py @@ -1,73 +1,68 @@ -from flask import Flask, request, Response, jsonify -from flask_cors import CORS +from fastapi import FastAPI, Request, Response, HTTPException, Depends +from fastapi.middleware.cors import CORSMiddleware +from fastapi.responses import StreamingResponse import requests import json +from pydantic import BaseModel from apps.web.models.users import Users from constants import ERROR_MESSAGES -from utils.utils import decode_token +from utils.utils import decode_token, get_current_user from config import OLLAMA_API_BASE_URL, WEBUI_AUTH -app = Flask(__name__) -CORS( - app -) # Enable Cross-Origin Resource Sharing (CORS) to allow requests from different domains +app = FastAPI() +app.add_middleware( + CORSMiddleware, + allow_origins=["*"], + allow_credentials=True, + allow_methods=["*"], + allow_headers=["*"], +) -# Define the target server URL -TARGET_SERVER_URL = OLLAMA_API_BASE_URL +app.state.OLLAMA_API_BASE_URL = OLLAMA_API_BASE_URL + +# TARGET_SERVER_URL = OLLAMA_API_BASE_URL -@app.route("/", - defaults={"path": ""}, - methods=["GET", "POST", "PUT", "DELETE"]) -@app.route("/", methods=["GET", "POST", "PUT", "DELETE"]) -def proxy(path): - # Combine the base URL of the target server with the requested path - target_url = f"{TARGET_SERVER_URL}/{path}" - print(target_url) +@app.get("/url") +async def get_ollama_api_url(user=Depends(get_current_user)): + if user and user.role == "admin": + return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL} + else: + raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED) - # Get data from the original request - data = request.get_data() + +class UrlUpdateForm(BaseModel): + url: str + + +@app.post("/url/update") +async def update_ollama_api_url( + form_data: UrlUpdateForm, user=Depends(get_current_user) +): + if user and user.role == "admin": + app.state.OLLAMA_API_BASE_URL = form_data.url + return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL} + else: + raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED) + + +@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"]) +async def proxy(path: str, request: Request, user=Depends(get_current_user)): + target_url = f"{app.state.OLLAMA_API_BASE_URL}/{path}" + + body = await request.body() headers = dict(request.headers) - # Basic RBAC support - if WEBUI_AUTH: - if "Authorization" in headers: - _, credentials = headers["Authorization"].split() - token_data = decode_token(credentials) - if token_data is None or "email" not in token_data: - return jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), 401 - - user = Users.get_user_by_email(token_data["email"]) - if user: - # Only user and admin roles can access - if user.role in ["user", "admin"]: - if path in ["pull", "delete", "push", "copy", "create"]: - # Only admin role can perform actions above - if user.role == "admin": - pass - else: - return ( - jsonify({ - "detail": - ERROR_MESSAGES.ACCESS_PROHIBITED - }), - 401, - ) - else: - pass - else: - return jsonify( - {"detail": ERROR_MESSAGES.ACCESS_PROHIBITED}), 401 - else: - return jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), 401 - else: - return jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), 401 + if user.role in ["user", "admin"]: + if path in ["pull", "delete", "push", "copy", "create"]: + if user.role != "admin": + raise HTTPException( + status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED + ) else: - pass - - r = None + raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED) headers.pop("Host", None) headers.pop("Authorization", None) @@ -75,47 +70,30 @@ def proxy(path): headers.pop("Referer", None) try: - # Make a request to the target server r = requests.request( method=request.method, url=target_url, - data=data, + data=body, headers=headers, - stream=True, # Enable streaming for server-sent events + stream=True, ) r.raise_for_status() - # Proxy the target server's response to the client - def generate(): - for chunk in r.iter_content(chunk_size=8192): - yield chunk - - response = Response(generate(), status=r.status_code) - - # Copy headers from the target server's response to the client's response - for key, value in r.headers.items(): - response.headers[key] = value - - return response + return StreamingResponse( + r.iter_content(chunk_size=8192), + status_code=r.status_code, + headers=dict(r.headers), + ) except Exception as e: print(e) error_detail = "Ollama WebUI: Server Connection Error" - if r != None: - print(r.text) - res = r.json() - if "error" in res: - error_detail = f"Ollama: {res['error']}" - print(res) + if r is not None: + try: + res = r.json() + if "error" in res: + error_detail = f"Ollama: {res['error']}" + except: + error_detail = f"Ollama: {e}" - return ( - jsonify({ - "detail": error_detail, - "message": str(e), - }), - 400, - ) - - -if __name__ == "__main__": - app.run(debug=True) + raise HTTPException(status_code=r.status_code, detail=error_detail) diff --git a/backend/apps/ollama/old_main.py b/backend/apps/ollama/old_main.py new file mode 100644 index 000000000..2e6800930 --- /dev/null +++ b/backend/apps/ollama/old_main.py @@ -0,0 +1,176 @@ +from flask import Flask, request, Response, jsonify +from flask_cors import CORS + + +import requests +import json + + +from apps.web.models.users import Users +from constants import ERROR_MESSAGES +from utils.utils import decode_token +from config import OLLAMA_API_BASE_URL, WEBUI_AUTH + +app = Flask(__name__) +CORS( + app +) # Enable Cross-Origin Resource Sharing (CORS) to allow requests from different domains + +# Define the target server URL +TARGET_SERVER_URL = OLLAMA_API_BASE_URL + + +@app.route("/url", methods=["GET"]) +def get_ollama_api_url(): + headers = dict(request.headers) + if "Authorization" in headers: + _, credentials = headers["Authorization"].split() + token_data = decode_token(credentials) + if token_data is None or "email" not in token_data: + return jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), 401 + + user = Users.get_user_by_email(token_data["email"]) + if user and user.role == "admin": + return ( + jsonify({"OLLAMA_API_BASE_URL": TARGET_SERVER_URL}), + 200, + ) + else: + return ( + jsonify({"detail": ERROR_MESSAGES.ACCESS_PROHIBITED}), + 401, + ) + else: + return ( + jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), + 401, + ) + + +@app.route("/url/update", methods=["POST"]) +def update_ollama_api_url(): + headers = dict(request.headers) + data = request.get_json(force=True) + + if "Authorization" in headers: + _, credentials = headers["Authorization"].split() + token_data = decode_token(credentials) + if token_data is None or "email" not in token_data: + return jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), 401 + + user = Users.get_user_by_email(token_data["email"]) + if user and user.role == "admin": + TARGET_SERVER_URL = data["url"] + return ( + jsonify({"OLLAMA_API_BASE_URL": TARGET_SERVER_URL}), + 200, + ) + else: + return ( + jsonify({"detail": ERROR_MESSAGES.ACCESS_PROHIBITED}), + 401, + ) + else: + return ( + jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), + 401, + ) + + +@app.route("/", defaults={"path": ""}, methods=["GET", "POST", "PUT", "DELETE"]) +@app.route("/", methods=["GET", "POST", "PUT", "DELETE"]) +def proxy(path): + # Combine the base URL of the target server with the requested path + target_url = f"{TARGET_SERVER_URL}/{path}" + print(target_url) + + # Get data from the original request + data = request.get_data() + headers = dict(request.headers) + + # Basic RBAC support + if WEBUI_AUTH: + if "Authorization" in headers: + _, credentials = headers["Authorization"].split() + token_data = decode_token(credentials) + if token_data is None or "email" not in token_data: + return jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), 401 + + user = Users.get_user_by_email(token_data["email"]) + if user: + # Only user and admin roles can access + if user.role in ["user", "admin"]: + if path in ["pull", "delete", "push", "copy", "create"]: + # Only admin role can perform actions above + if user.role == "admin": + pass + else: + return ( + jsonify({"detail": ERROR_MESSAGES.ACCESS_PROHIBITED}), + 401, + ) + else: + pass + else: + return jsonify({"detail": ERROR_MESSAGES.ACCESS_PROHIBITED}), 401 + else: + return jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), 401 + else: + return jsonify({"detail": ERROR_MESSAGES.UNAUTHORIZED}), 401 + else: + pass + + r = None + + headers.pop("Host", None) + headers.pop("Authorization", None) + headers.pop("Origin", None) + headers.pop("Referer", None) + + try: + # Make a request to the target server + r = requests.request( + method=request.method, + url=target_url, + data=data, + headers=headers, + stream=True, # Enable streaming for server-sent events + ) + + r.raise_for_status() + + # Proxy the target server's response to the client + def generate(): + for chunk in r.iter_content(chunk_size=8192): + yield chunk + + response = Response(generate(), status=r.status_code) + + # Copy headers from the target server's response to the client's response + for key, value in r.headers.items(): + response.headers[key] = value + + return response + except Exception as e: + print(e) + error_detail = "Ollama WebUI: Server Connection Error" + if r != None: + print(r.text) + res = r.json() + if "error" in res: + error_detail = f"Ollama: {res['error']}" + print(res) + + return ( + jsonify( + { + "detail": error_detail, + "message": str(e), + } + ), + 400, + ) + + +if __name__ == "__main__": + app.run(debug=True) diff --git a/backend/main.py b/backend/main.py index 1f4327826..704ece781 100644 --- a/backend/main.py +++ b/backend/main.py @@ -47,7 +47,7 @@ async def check_url(request: Request, call_next): app.mount("/api/v1", webui_app) -app.mount("/ollama/api", WSGIMiddleware(ollama_app)) -app.mount("/", - SPAStaticFiles(directory="../build", html=True), - name="spa-static-files") +# app.mount("/ollama/api", WSGIMiddleware(ollama_app)) +app.mount("/ollama/api", ollama_app) + +app.mount("/", SPAStaticFiles(directory="../build", html=True), name="spa-static-files") diff --git a/src/lib/apis/ollama/index.ts b/src/lib/apis/ollama/index.ts index 198ea4184..e0048fc6e 100644 --- a/src/lib/apis/ollama/index.ts +++ b/src/lib/apis/ollama/index.ts @@ -1,12 +1,76 @@ import { OLLAMA_API_BASE_URL } from '$lib/constants'; -export const getOllamaVersion = async ( - base_url: string = OLLAMA_API_BASE_URL, - token: string = '' -) => { +export const getOllamaAPIUrl = async (token: string = '') => { let error = null; - const res = await fetch(`${base_url}/version`, { + const res = await fetch(`${OLLAMA_API_BASE_URL}/url`, { + method: 'GET', + headers: { + Accept: 'application/json', + 'Content-Type': 'application/json', + ...(token && { authorization: `Bearer ${token}` }) + } + }) + .then(async (res) => { + if (!res.ok) throw await res.json(); + return res.json(); + }) + .catch((err) => { + console.log(err); + if ('detail' in err) { + error = err.detail; + } else { + error = 'Server connection failed'; + } + return null; + }); + + if (error) { + throw error; + } + + return res.OLLAMA_API_BASE_URL; +}; + +export const updateOllamaAPIUrl = async (token: string = '', url: string) => { + let error = null; + + const res = await fetch(`${OLLAMA_API_BASE_URL}/url/update`, { + method: 'POST', + headers: { + Accept: 'application/json', + 'Content-Type': 'application/json', + ...(token && { authorization: `Bearer ${token}` }) + }, + body: JSON.stringify({ + url: url + }) + }) + .then(async (res) => { + if (!res.ok) throw await res.json(); + return res.json(); + }) + .catch((err) => { + console.log(err); + if ('detail' in err) { + error = err.detail; + } else { + error = 'Server connection failed'; + } + return null; + }); + + if (error) { + throw error; + } + + return res.OLLAMA_API_BASE_URL; +}; + +export const getOllamaVersion = async (token: string = '') => { + let error = null; + + const res = await fetch(`${OLLAMA_API_BASE_URL}/version`, { method: 'GET', headers: { Accept: 'application/json', @@ -35,13 +99,10 @@ export const getOllamaVersion = async ( return res?.version ?? ''; }; -export const getOllamaModels = async ( - base_url: string = OLLAMA_API_BASE_URL, - token: string = '' -) => { +export const getOllamaModels = async (token: string = '') => { let error = null; - const res = await fetch(`${base_url}/tags`, { + const res = await fetch(`${OLLAMA_API_BASE_URL}/tags`, { method: 'GET', headers: { Accept: 'application/json', @@ -67,18 +128,15 @@ export const getOllamaModels = async ( throw error; } - return res?.models ?? []; + return (res?.models ?? []).sort((a, b) => { + return a.name.localeCompare(b.name); + }); }; -export const generateTitle = async ( - base_url: string = OLLAMA_API_BASE_URL, - token: string = '', - model: string, - prompt: string -) => { +export const generateTitle = async (token: string = '', model: string, prompt: string) => { let error = null; - const res = await fetch(`${base_url}/generate`, { + const res = await fetch(`${OLLAMA_API_BASE_URL}/generate`, { method: 'POST', headers: { 'Content-Type': 'text/event-stream', @@ -109,14 +167,10 @@ export const generateTitle = async ( return res?.response ?? 'New Chat'; }; -export const generateChatCompletion = async ( - base_url: string = OLLAMA_API_BASE_URL, - token: string = '', - body: object -) => { +export const generateChatCompletion = async (token: string = '', body: object) => { let error = null; - const res = await fetch(`${base_url}/chat`, { + const res = await fetch(`${OLLAMA_API_BASE_URL}/chat`, { method: 'POST', headers: { 'Content-Type': 'text/event-stream', @@ -135,15 +189,10 @@ export const generateChatCompletion = async ( return res; }; -export const createModel = async ( - base_url: string = OLLAMA_API_BASE_URL, - token: string, - tagName: string, - content: string -) => { +export const createModel = async (token: string, tagName: string, content: string) => { let error = null; - const res = await fetch(`${base_url}/create`, { + const res = await fetch(`${OLLAMA_API_BASE_URL}/create`, { method: 'POST', headers: { 'Content-Type': 'text/event-stream', @@ -165,14 +214,10 @@ export const createModel = async ( return res; }; -export const deleteModel = async ( - base_url: string = OLLAMA_API_BASE_URL, - token: string, - tagName: string -) => { +export const deleteModel = async (token: string, tagName: string) => { let error = null; - const res = await fetch(`${base_url}/delete`, { + const res = await fetch(`${OLLAMA_API_BASE_URL}/delete`, { method: 'DELETE', headers: { 'Content-Type': 'text/event-stream', @@ -202,3 +247,27 @@ export const deleteModel = async ( return res; }; + +export const pullModel = async (token: string, tagName: string) => { + let error = null; + + const res = await fetch(`${OLLAMA_API_BASE_URL}/pull`, { + method: 'POST', + headers: { + 'Content-Type': 'text/event-stream', + Authorization: `Bearer ${token}` + }, + body: JSON.stringify({ + name: tagName + }) + }).catch((err) => { + error = err; + return null; + }); + + if (error) { + throw error; + } + + return res; +}; diff --git a/src/lib/apis/openai/index.ts b/src/lib/apis/openai/index.ts index 292e1ce71..3170cbfff 100644 --- a/src/lib/apis/openai/index.ts +++ b/src/lib/apis/openai/index.ts @@ -29,5 +29,8 @@ export const getOpenAIModels = async ( return models .map((model) => ({ name: model.id, external: true })) - .filter((model) => (base_url.includes('openai') ? model.name.includes('gpt') : true)); + .filter((model) => (base_url.includes('openai') ? model.name.includes('gpt') : true)) + .sort((a, b) => { + return a.name.localeCompare(b.name); + }); }; diff --git a/src/lib/components/chat/SettingsModal.svelte b/src/lib/components/chat/SettingsModal.svelte index 8ba3b1e08..174ffc17e 100644 --- a/src/lib/components/chat/SettingsModal.svelte +++ b/src/lib/components/chat/SettingsModal.svelte @@ -7,19 +7,23 @@ import { config, models, settings, user, chats } from '$lib/stores'; import { splitStream, getGravatarURL } from '$lib/utils'; - import { getOllamaVersion } from '$lib/apis/ollama'; - import { createNewChat, deleteAllChats, getAllChats, getChatList } from '$lib/apis/chats'; import { - WEB_UI_VERSION, - OLLAMA_API_BASE_URL, - WEBUI_API_BASE_URL, - WEBUI_BASE_URL - } from '$lib/constants'; + getOllamaVersion, + getOllamaModels, + getOllamaAPIUrl, + updateOllamaAPIUrl, + pullModel, + createModel, + deleteModel + } from '$lib/apis/ollama'; + import { createNewChat, deleteAllChats, getAllChats, getChatList } from '$lib/apis/chats'; + import { WEB_UI_VERSION, WEBUI_API_BASE_URL } from '$lib/constants'; import Advanced from './Settings/Advanced.svelte'; import Modal from '../common/Modal.svelte'; import { updateUserPassword } from '$lib/apis/auths'; import { goto } from '$app/navigation'; + import Page from '../../../routes/(app)/+page.svelte'; export let show = false; @@ -33,7 +37,7 @@ let selectedTab = 'general'; // General - let API_BASE_URL = OLLAMA_API_BASE_URL; + let API_BASE_URL = ''; let themes = ['dark', 'light', 'rose-pine dark', 'rose-pine-dawn light']; let theme = 'dark'; let notificationEnabled = false; @@ -139,19 +143,13 @@ // About let ollamaVersion = ''; - const checkOllamaConnection = async () => { - if (API_BASE_URL === '') { - API_BASE_URL = OLLAMA_API_BASE_URL; - } - const _models = await getModels(API_BASE_URL, 'ollama'); + const updateOllamaAPIUrlHandler = async () => { + API_BASE_URL = await updateOllamaAPIUrl(localStorage.token, API_BASE_URL); + const _models = await getModels('ollama'); if (_models.length > 0) { toast.success('Server connection verified'); await models.set(_models); - - saveSettings({ - API_BASE_URL: API_BASE_URL - }); } }; @@ -229,67 +227,60 @@ const pullModelHandler = async () => { modelTransferring = true; - const res = await fetch(`${API_BASE_URL}/pull`, { - method: 'POST', - headers: { - 'Content-Type': 'text/event-stream', - ...($settings.authHeader && { Authorization: $settings.authHeader }), - ...($user && { Authorization: `Bearer ${localStorage.token}` }) - }, - body: JSON.stringify({ - name: modelTag - }) - }); - const reader = res.body - .pipeThrough(new TextDecoderStream()) - .pipeThrough(splitStream('\n')) - .getReader(); + const res = await pullModel(localStorage.token, modelTag); - while (true) { - const { value, done } = await reader.read(); - if (done) break; + if (res) { + const reader = res.body + .pipeThrough(new TextDecoderStream()) + .pipeThrough(splitStream('\n')) + .getReader(); - try { - let lines = value.split('\n'); + while (true) { + const { value, done } = await reader.read(); + if (done) break; - for (const line of lines) { - if (line !== '') { - console.log(line); - let data = JSON.parse(line); - console.log(data); + try { + let lines = value.split('\n'); - if (data.error) { - throw data.error; - } + for (const line of lines) { + if (line !== '') { + console.log(line); + let data = JSON.parse(line); + console.log(data); - if (data.detail) { - throw data.detail; - } - if (data.status) { - if (!data.digest) { - toast.success(data.status); + if (data.error) { + throw data.error; + } - if (data.status === 'success') { - const notification = new Notification(`Ollama`, { - body: `Model '${modelTag}' has been successfully downloaded.`, - icon: '/favicon.png' - }); - } - } else { - digest = data.digest; - if (data.completed) { - pullProgress = Math.round((data.completed / data.total) * 1000) / 10; + if (data.detail) { + throw data.detail; + } + if (data.status) { + if (!data.digest) { + toast.success(data.status); + + if (data.status === 'success') { + const notification = new Notification(`Ollama`, { + body: `Model '${modelTag}' has been successfully downloaded.`, + icon: '/favicon.png' + }); + } } else { - pullProgress = 100; + digest = data.digest; + if (data.completed) { + pullProgress = Math.round((data.completed / data.total) * 1000) / 10; + } else { + pullProgress = 100; + } } } } } + } catch (error) { + console.log(error); + toast.error(error); } - } catch (error) { - console.log(error); - toast.error(error); } } @@ -410,21 +401,11 @@ } if (uploaded) { - const res = await fetch(`${$settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL}/create`, { - method: 'POST', - headers: { - 'Content-Type': 'text/event-stream', - ...($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; - }); + const res = await createModel( + localStorage.token, + `${name}:latest`, + `FROM @${modelFileDigest}\n${modelFileContent}` + ); if (res && res.ok) { const reader = res.body @@ -490,92 +471,33 @@ }; const deleteModelHandler = async () => { - const res = await fetch(`${API_BASE_URL}/delete`, { - method: 'DELETE', - headers: { - 'Content-Type': 'text/event-stream', - ...($settings.authHeader && { Authorization: $settings.authHeader }), - ...($user && { Authorization: `Bearer ${localStorage.token}` }) - }, - body: JSON.stringify({ - name: deleteModelTag - }) + const res = await deleteModel(localStorage.token, deleteModelTag).catch((error) => { + toast.error(error); }); - 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 !== '' && line !== 'null') { - 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) { - } - } else { - toast.success(`Deleted ${deleteModelTag}`); - } - } - } catch (error) { - console.log(error); - toast.error(error); - } + if (res) { + toast.success(`Deleted ${deleteModelTag}`); } deleteModelTag = ''; models.set(await getModels()); }; - const getModels = async (url = '', type = 'all') => { + const getModels = async (type = 'all') => { let models = []; - const res = await fetch(`${url ? url : $settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL}/tags`, { - method: 'GET', - headers: { - Accept: 'application/json', - 'Content-Type': 'application/json', - ...($settings.authHeader && { Authorization: $settings.authHeader }), - ...($user && { Authorization: `Bearer ${localStorage.token}` }) - } - }) - .then(async (res) => { - if (!res.ok) throw await res.json(); - return res.json(); - }) - .catch((error) => { - console.log(error); - if ('detail' in error) { - toast.error(error.detail); - } else { - toast.error('Server connection failed'); - } - return null; - }); - console.log(res); - models.push(...(res?.models ?? [])); + models.push( + ...(await getOllamaModels(localStorage.token).catch((error) => { + toast.error(error); + return []; + })) + ); // 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'; + const OPENAI_API_BASE_URL = $settings.OPENAI_API_BASE_URL ?? 'https://api.openai.com/v1'; // Validate OPENAI_API_KEY - const openaiModelRes = await fetch(`${API_BASE_URL}/models`, { + const openaiModelRes = await fetch(`${OPENAI_API_BASE_URL}/models`, { method: 'GET', headers: { 'Content-Type': 'application/json', @@ -603,7 +525,7 @@ ...openAIModels .map((model) => ({ name: model.id, external: true })) .filter((model) => - API_BASE_URL.includes('openai') ? model.name.includes('gpt') : true + OPENAI_API_BASE_URL.includes('openai') ? model.name.includes('gpt') : true ) ] : []) @@ -639,15 +561,18 @@ }; onMount(async () => { + console.log('settings', $user.role === 'admin'); + if ($user.role === 'admin') { + API_BASE_URL = await getOllamaAPIUrl(localStorage.token); + } + let settings = JSON.parse(localStorage.getItem('settings') ?? '{}'); console.log(settings); theme = localStorage.theme ?? 'dark'; notificationEnabled = settings.notificationEnabled ?? false; - API_BASE_URL = settings.API_BASE_URL ?? OLLAMA_API_BASE_URL; system = settings.system ?? ''; - requestFormat = settings.requestFormat ?? ''; options.seed = settings.seed ?? 0; @@ -674,10 +599,7 @@ authContent = settings.authHeader.split(' ')[1]; } - ollamaVersion = await getOllamaVersion( - API_BASE_URL ?? OLLAMA_API_BASE_URL, - localStorage.token - ).catch((error) => { + ollamaVersion = await getOllamaVersion(localStorage.token).catch((error) => { return ''; }); }); @@ -1041,51 +963,51 @@ -
-
-
Ollama API URL
-
-
- -
- -
+
+ + -
- The field above should be set to '/ollama/api'; - - Click here for help. - +
+ Trouble accessing Ollama? + + Click here for help. + +
- + {/if}
@@ -1103,7 +1025,6 @@ class=" px-4 py-2 bg-emerald-600 hover:bg-emerald-700 text-gray-100 transition rounded" on:click={() => { saveSettings({ - API_BASE_URL: API_BASE_URL === '' ? OLLAMA_API_BASE_URL : API_BASE_URL, system: system !== '' ? system : undefined }); show = false; diff --git a/src/lib/constants.ts b/src/lib/constants.ts index 7d67c7a4b..c22ae207b 100644 --- a/src/lib/constants.ts +++ b/src/lib/constants.ts @@ -1,13 +1,8 @@ -import { dev, browser } from '$app/environment'; -import { PUBLIC_API_BASE_URL } from '$env/static/public'; +import { dev } from '$app/environment'; export const OLLAMA_API_BASE_URL = dev ? `http://${location.hostname}:8080/ollama/api` - : PUBLIC_API_BASE_URL === '' - ? browser - ? `http://${location.hostname}:11434/api` - : `http://localhost:11434/api` - : PUBLIC_API_BASE_URL; + : '/ollama/api'; export const WEBUI_BASE_URL = dev ? `http://${location.hostname}:8080` : ``; export const WEBUI_API_BASE_URL = `${WEBUI_BASE_URL}/api/v1`; diff --git a/src/routes/(app)/+layout.svelte b/src/routes/(app)/+layout.svelte index dca6912f5..013638cb0 100644 --- a/src/routes/(app)/+layout.svelte +++ b/src/routes/(app)/+layout.svelte @@ -14,7 +14,7 @@ import { getOpenAIModels } from '$lib/apis/openai'; import { user, showSettings, settings, models, modelfiles, prompts } from '$lib/stores'; - import { OLLAMA_API_BASE_URL, REQUIRED_OLLAMA_VERSION, WEBUI_API_BASE_URL } from '$lib/constants'; + import { REQUIRED_OLLAMA_VERSION, WEBUI_API_BASE_URL } from '$lib/constants'; import SettingsModal from '$lib/components/chat/SettingsModal.svelte'; import Sidebar from '$lib/components/layout/Sidebar.svelte'; @@ -32,10 +32,7 @@ const getModels = async () => { let models = []; models.push( - ...(await getOllamaModels( - $settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL, - localStorage.token - ).catch((error) => { + ...(await getOllamaModels(localStorage.token).catch((error) => { toast.error(error); return []; })) @@ -58,10 +55,7 @@ const setOllamaVersion = async (version: string = '') => { if (version === '') { - version = await getOllamaVersion( - $settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL, - localStorage.token - ).catch((error) => { + version = await getOllamaVersion(localStorage.token).catch((error) => { return ''; }); } diff --git a/src/routes/(app)/+page.svelte b/src/routes/(app)/+page.svelte index 9638861be..8fab09a2e 100644 --- a/src/routes/(app)/+page.svelte +++ b/src/routes/(app)/+page.svelte @@ -7,7 +7,6 @@ import { page } from '$app/stores'; import { models, modelfiles, user, settings, chats, chatId, config } from '$lib/stores'; - import { OLLAMA_API_BASE_URL } from '$lib/constants'; import { generateChatCompletion, generateTitle } from '$lib/apis/ollama'; import { copyToClipboard, splitStream } from '$lib/utils'; @@ -163,36 +162,32 @@ // Scroll down window.scrollTo({ top: document.body.scrollHeight }); - const res = await generateChatCompletion( - $settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL, - localStorage.token, - { - model: model, - messages: [ - $settings.system - ? { - role: 'system', - content: $settings.system - } - : undefined, - ...messages - ] - .filter((message) => message) - .map((message) => ({ - role: message.role, - content: message.content, - ...(message.files && { - images: message.files - .filter((file) => file.type === 'image') - .map((file) => file.url.slice(file.url.indexOf(',') + 1)) - }) - })), - options: { - ...($settings.options ?? {}) - }, - format: $settings.requestFormat ?? undefined - } - ); + const res = await generateChatCompletion(localStorage.token, { + model: model, + messages: [ + $settings.system + ? { + role: 'system', + content: $settings.system + } + : undefined, + ...messages + ] + .filter((message) => message) + .map((message) => ({ + role: message.role, + content: message.content, + ...(message.files && { + images: message.files + .filter((file) => file.type === 'image') + .map((file) => file.url.slice(file.url.indexOf(',') + 1)) + }) + })), + options: { + ...($settings.options ?? {}) + }, + format: $settings.requestFormat ?? undefined + }); if (res && res.ok) { const reader = res.body @@ -595,7 +590,6 @@ const generateChatTitle = async (_chatId, userPrompt) => { if ($settings.titleAutoGenerate ?? true) { const title = await generateTitle( - $settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL, localStorage.token, $settings?.titleAutoGenerateModel ?? selectedModels[0], userPrompt diff --git a/src/routes/(app)/c/[id]/+page.svelte b/src/routes/(app)/c/[id]/+page.svelte index e3a70ca25..61b1c7685 100644 --- a/src/routes/(app)/c/[id]/+page.svelte +++ b/src/routes/(app)/c/[id]/+page.svelte @@ -7,7 +7,6 @@ import { page } from '$app/stores'; import { models, modelfiles, user, settings, chats, chatId } from '$lib/stores'; - import { OLLAMA_API_BASE_URL } from '$lib/constants'; import { generateChatCompletion, generateTitle } from '$lib/apis/ollama'; import { copyToClipboard, splitStream } from '$lib/utils'; @@ -180,36 +179,32 @@ // Scroll down window.scrollTo({ top: document.body.scrollHeight }); - const res = await generateChatCompletion( - $settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL, - localStorage.token, - { - model: model, - messages: [ - $settings.system - ? { - role: 'system', - content: $settings.system - } - : undefined, - ...messages - ] - .filter((message) => message) - .map((message) => ({ - role: message.role, - content: message.content, - ...(message.files && { - images: message.files - .filter((file) => file.type === 'image') - .map((file) => file.url.slice(file.url.indexOf(',') + 1)) - }) - })), - options: { - ...($settings.options ?? {}) - }, - format: $settings.requestFormat ?? undefined - } - ); + const res = await generateChatCompletion(localStorage.token, { + model: model, + messages: [ + $settings.system + ? { + role: 'system', + content: $settings.system + } + : undefined, + ...messages + ] + .filter((message) => message) + .map((message) => ({ + role: message.role, + content: message.content, + ...(message.files && { + images: message.files + .filter((file) => file.type === 'image') + .map((file) => file.url.slice(file.url.indexOf(',') + 1)) + }) + })), + options: { + ...($settings.options ?? {}) + }, + format: $settings.requestFormat ?? undefined + }); if (res && res.ok) { const reader = res.body @@ -611,12 +606,7 @@ const generateChatTitle = async (_chatId, userPrompt) => { if ($settings.titleAutoGenerate ?? true) { - const title = await generateTitle( - $settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL, - localStorage.token, - selectedModels[0], - userPrompt - ); + const title = await generateTitle(localStorage.token, selectedModels[0], userPrompt); if (title) { await setChatTitle(_chatId, title); diff --git a/src/routes/(app)/modelfiles/+page.svelte b/src/routes/(app)/modelfiles/+page.svelte index 917908cd2..823782eef 100644 --- a/src/routes/(app)/modelfiles/+page.svelte +++ b/src/routes/(app)/modelfiles/+page.svelte @@ -6,7 +6,6 @@ import { onMount } from 'svelte'; import { modelfiles, settings, user } from '$lib/stores'; - import { OLLAMA_API_BASE_URL } from '$lib/constants'; import { createModel, deleteModel } from '$lib/apis/ollama'; import { createNewModelfile, @@ -20,11 +19,7 @@ const deleteModelHandler = async (tagName) => { let success = null; - success = await deleteModel( - $settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL, - localStorage.token, - tagName - ); + success = await deleteModel(localStorage.token, tagName); if (success) { toast.success(`Deleted ${tagName}`); diff --git a/src/routes/(app)/modelfiles/create/+page.svelte b/src/routes/(app)/modelfiles/create/+page.svelte index 4b23149c6..a59fb445a 100644 --- a/src/routes/(app)/modelfiles/create/+page.svelte +++ b/src/routes/(app)/modelfiles/create/+page.svelte @@ -2,7 +2,6 @@ import { v4 as uuidv4 } from 'uuid'; import { toast } from 'svelte-french-toast'; import { goto } from '$app/navigation'; - import { OLLAMA_API_BASE_URL } from '$lib/constants'; import { settings, user, config, modelfiles, models } from '$lib/stores'; import Advanced from '$lib/components/chat/Settings/Advanced.svelte'; @@ -132,12 +131,7 @@ SYSTEM """${system}"""`.replace(/^\s*\n/gm, ''); Object.keys(categories).filter((category) => categories[category]).length > 0 && !$models.includes(tagName) ) { - const res = await createModel( - $settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL, - localStorage.token, - tagName, - content - ); + const res = await createModel(localStorage.token, tagName, content); if (res) { const reader = res.body diff --git a/src/routes/(app)/modelfiles/edit/+page.svelte b/src/routes/(app)/modelfiles/edit/+page.svelte index 11dec1824..3139c8b28 100644 --- a/src/routes/(app)/modelfiles/edit/+page.svelte +++ b/src/routes/(app)/modelfiles/edit/+page.svelte @@ -7,8 +7,6 @@ import { page } from '$app/stores'; import { settings, user, config, modelfiles } from '$lib/stores'; - - import { OLLAMA_API_BASE_URL } from '$lib/constants'; import { splitStream } from '$lib/utils'; import { createModel } from '$lib/apis/ollama'; @@ -104,12 +102,7 @@ content !== '' && Object.keys(categories).filter((category) => categories[category]).length > 0 ) { - const res = await createModel( - $settings?.API_BASE_URL ?? OLLAMA_API_BASE_URL, - localStorage.token, - tagName, - content - ); + const res = await createModel(localStorage.token, tagName, content); if (res) { const reader = res.body