diff --git a/.dockerignore b/.dockerignore index 58cf1f0f8..e28863bf6 100644 --- a/.dockerignore +++ b/.dockerignore @@ -7,7 +7,6 @@ node_modules /package .env .env.* -!.env.example vite.config.js.timestamp-* vite.config.ts.timestamp-* __pycache__ diff --git a/.env.example b/.env.example index de763f31c..3d2aafc09 100644 --- a/.env.example +++ b/.env.example @@ -1,6 +1,6 @@ # Ollama URL for the backend to connect -# The path '/ollama/api' will be redirected to the specified backend URL -OLLAMA_API_BASE_URL='http://localhost:11434/api' +# The path '/ollama' will be redirected to the specified backend URL +OLLAMA_BASE_URL='http://localhost:11434' OPENAI_API_BASE_URL='' OPENAI_API_KEY='' diff --git a/.github/workflows/build-release.yml b/.github/workflows/build-release.yml index fa3fa296d..e45a83164 100644 --- a/.github/workflows/build-release.yml +++ b/.github/workflows/build-release.yml @@ -19,24 +19,34 @@ jobs: echo "No changes to package.json" exit 1 } - + - name: Get version number from package.json id: get_version run: | VERSION=$(jq -r '.version' package.json) echo "::set-output name=version::$VERSION" + - name: Extract latest CHANGELOG entry + id: changelog + run: | + CHANGELOG_CONTENT=$(awk '/^## \[/{n++} n==1' CHANGELOG.md) + echo "CHANGELOG_CONTENT< "General". - - Confirm that the Ollama Server URL is correctly set to `[OLLAMA URL]/api` (e.g., `http://localhost:11434/api`), including the `/api` suffix. + - Confirm that the Ollama Server URL is correctly set to `[OLLAMA URL]` (e.g., `http://localhost:11434`). 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 d4d1e91a6..f8f166d01 100644 --- a/backend/apps/ollama/main.py +++ b/backend/apps/ollama/main.py @@ -15,7 +15,7 @@ import asyncio from apps.web.models.users import Users from constants import ERROR_MESSAGES from utils.utils import decode_token, get_current_user, get_admin_user -from config import OLLAMA_BASE_URL, WEBUI_AUTH +from config import OLLAMA_BASE_URLS from typing import Optional, List, Union @@ -29,8 +29,7 @@ app.add_middleware( allow_headers=["*"], ) -app.state.OLLAMA_BASE_URL = OLLAMA_BASE_URL -app.state.OLLAMA_BASE_URLS = [OLLAMA_BASE_URL] +app.state.OLLAMA_BASE_URLS = OLLAMA_BASE_URLS app.state.MODELS = {} @@ -223,7 +222,7 @@ async def pull_model( r = requests.request( method="POST", url=f"{url}/api/pull", - data=form_data.model_dump_json(exclude_none=True), + data=form_data.model_dump_json(exclude_none=True).encode(), stream=True, ) @@ -295,7 +294,7 @@ async def push_model( r = requests.request( method="POST", url=f"{url}/api/push", - data=form_data.model_dump_json(exclude_none=True), + data=form_data.model_dump_json(exclude_none=True).encode(), ) r.raise_for_status() @@ -357,7 +356,7 @@ async def create_model( r = requests.request( method="POST", url=f"{url}/api/create", - data=form_data.model_dump_json(exclude_none=True), + data=form_data.model_dump_json(exclude_none=True).encode(), stream=True, ) @@ -420,7 +419,7 @@ async def copy_model( r = requests.request( method="POST", url=f"{url}/api/copy", - data=form_data.model_dump_json(exclude_none=True), + data=form_data.model_dump_json(exclude_none=True).encode(), ) r.raise_for_status() @@ -467,7 +466,7 @@ async def delete_model( r = requests.request( method="DELETE", url=f"{url}/api/delete", - data=form_data.model_dump_json(exclude_none=True), + data=form_data.model_dump_json(exclude_none=True).encode(), ) r.raise_for_status() @@ -507,7 +506,7 @@ async def show_model_info(form_data: ModelNameForm, user=Depends(get_current_use r = requests.request( method="POST", url=f"{url}/api/show", - data=form_data.model_dump_json(exclude_none=True), + data=form_data.model_dump_json(exclude_none=True).encode(), ) r.raise_for_status() @@ -559,7 +558,7 @@ async def generate_embeddings( r = requests.request( method="POST", url=f"{url}/api/embeddings", - data=form_data.model_dump_json(exclude_none=True), + data=form_data.model_dump_json(exclude_none=True).encode(), ) r.raise_for_status() @@ -645,7 +644,7 @@ async def generate_completion( r = requests.request( method="POST", url=f"{url}/api/generate", - data=form_data.model_dump_json(exclude_none=True), + data=form_data.model_dump_json(exclude_none=True).encode(), stream=True, ) @@ -715,7 +714,7 @@ async def generate_chat_completion( r = None - print(form_data.model_dump_json(exclude_none=True)) + print(form_data.model_dump_json(exclude_none=True).encode()) def get_request(): nonlocal form_data @@ -745,7 +744,7 @@ async def generate_chat_completion( r = requests.request( method="POST", url=f"{url}/api/chat", - data=form_data.model_dump_json(exclude_none=True), + data=form_data.model_dump_json(exclude_none=True).encode(), stream=True, ) @@ -757,6 +756,7 @@ async def generate_chat_completion( headers=dict(r.headers), ) except Exception as e: + print(e) raise e try: @@ -844,7 +844,7 @@ async def generate_openai_chat_completion( r = requests.request( method="POST", url=f"{url}/v1/chat/completions", - data=form_data.model_dump_json(exclude_none=True), + data=form_data.model_dump_json(exclude_none=True).encode(), stream=True, ) diff --git a/backend/apps/openai/main.py b/backend/apps/openai/main.py index 8d6fdb509..6b9c542ee 100644 --- a/backend/apps/openai/main.py +++ b/backend/apps/openai/main.py @@ -3,7 +3,10 @@ from fastapi.middleware.cors import CORSMiddleware from fastapi.responses import StreamingResponse, JSONResponse, FileResponse import requests +import aiohttp +import asyncio import json + from pydantic import BaseModel @@ -15,7 +18,9 @@ from utils.utils import ( get_verified_user, get_admin_user, ) -from config import OPENAI_API_BASE_URL, OPENAI_API_KEY, CACHE_DIR +from config import OPENAI_API_BASE_URLS, OPENAI_API_KEYS, CACHE_DIR +from typing import List, Optional + import hashlib from pathlib import Path @@ -29,116 +34,207 @@ app.add_middleware( allow_headers=["*"], ) -app.state.OPENAI_API_BASE_URL = OPENAI_API_BASE_URL -app.state.OPENAI_API_KEY = OPENAI_API_KEY +app.state.OPENAI_API_BASE_URLS = OPENAI_API_BASE_URLS +app.state.OPENAI_API_KEYS = OPENAI_API_KEYS + +app.state.MODELS = {} -class UrlUpdateForm(BaseModel): - url: str +@app.middleware("http") +async def check_url(request: Request, call_next): + if len(app.state.MODELS) == 0: + await get_all_models() + else: + pass + + response = await call_next(request) + return response -class KeyUpdateForm(BaseModel): - key: str +class UrlsUpdateForm(BaseModel): + urls: List[str] -@app.get("/url") -async def get_openai_url(user=Depends(get_admin_user)): - return {"OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL} +class KeysUpdateForm(BaseModel): + keys: List[str] -@app.post("/url/update") -async def update_openai_url(form_data: UrlUpdateForm, user=Depends(get_admin_user)): - app.state.OPENAI_API_BASE_URL = form_data.url - return {"OPENAI_API_BASE_URL": app.state.OPENAI_API_BASE_URL} +@app.get("/urls") +async def get_openai_urls(user=Depends(get_admin_user)): + return {"OPENAI_API_BASE_URLS": app.state.OPENAI_API_BASE_URLS} -@app.get("/key") -async def get_openai_key(user=Depends(get_admin_user)): - return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY} +@app.post("/urls/update") +async def update_openai_urls(form_data: UrlsUpdateForm, user=Depends(get_admin_user)): + app.state.OPENAI_API_BASE_URLS = form_data.urls + return {"OPENAI_API_BASE_URLS": app.state.OPENAI_API_BASE_URLS} -@app.post("/key/update") -async def update_openai_key(form_data: KeyUpdateForm, user=Depends(get_admin_user)): - app.state.OPENAI_API_KEY = form_data.key - return {"OPENAI_API_KEY": app.state.OPENAI_API_KEY} +@app.get("/keys") +async def get_openai_keys(user=Depends(get_admin_user)): + return {"OPENAI_API_KEYS": app.state.OPENAI_API_KEYS} + + +@app.post("/keys/update") +async def update_openai_key(form_data: KeysUpdateForm, user=Depends(get_admin_user)): + app.state.OPENAI_API_KEYS = form_data.keys + return {"OPENAI_API_KEYS": app.state.OPENAI_API_KEYS} @app.post("/audio/speech") async def speech(request: Request, user=Depends(get_verified_user)): - target_url = f"{app.state.OPENAI_API_BASE_URL}/audio/speech" - - if app.state.OPENAI_API_KEY == "": - raise HTTPException(status_code=401, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND) - - body = await request.body() - - name = hashlib.sha256(body).hexdigest() - - SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/") - SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True) - file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3") - file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json") - - # Check if the file already exists in the cache - if file_path.is_file(): - return FileResponse(file_path) - - headers = {} - headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}" - headers["Content-Type"] = "application/json" - + idx = None try: - print("openai") - r = requests.post( - url=target_url, - data=body, - headers=headers, - stream=True, + idx = app.state.OPENAI_API_BASE_URLS.index("https://api.openai.com/v1") + body = await request.body() + name = hashlib.sha256(body).hexdigest() + + SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/") + SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True) + file_path = SPEECH_CACHE_DIR.joinpath(f"{name}.mp3") + file_body_path = SPEECH_CACHE_DIR.joinpath(f"{name}.json") + + # Check if the file already exists in the cache + if file_path.is_file(): + return FileResponse(file_path) + + headers = {} + headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEYS[idx]}" + headers["Content-Type"] = "application/json" + + try: + r = requests.post( + url=f"{app.state.OPENAI_API_BASE_URLS[idx]}/audio/speech", + data=body, + headers=headers, + stream=True, + ) + + r.raise_for_status() + + # Save the streaming content to a file + with open(file_path, "wb") as f: + for chunk in r.iter_content(chunk_size=8192): + f.write(chunk) + + with open(file_body_path, "w") as f: + json.dump(json.loads(body.decode("utf-8")), f) + + # Return the saved file + return FileResponse(file_path) + + except Exception as e: + print(e) + error_detail = "Open WebUI: Server Connection Error" + if r is not None: + try: + res = r.json() + if "error" in res: + error_detail = f"External: {res['error']}" + except: + error_detail = f"External: {e}" + + raise HTTPException(status_code=r.status_code, detail=error_detail) + + except ValueError: + raise HTTPException(status_code=401, detail=ERROR_MESSAGES.OPENAI_NOT_FOUND) + + +async def fetch_url(url, key): + try: + headers = {"Authorization": f"Bearer {key}"} + async with aiohttp.ClientSession() as session: + async with session.get(url, headers=headers) as response: + return await response.json() + except Exception as e: + # Handle connection error here + print(f"Connection error: {e}") + return None + + +def merge_models_lists(model_lists): + merged_list = [] + + for idx, models in enumerate(model_lists): + merged_list.extend( + [ + {**model, "urlIdx": idx} + for model in models + if "api.openai.com" not in app.state.OPENAI_API_BASE_URLS[idx] + or "gpt" in model["id"] + ] ) - r.raise_for_status() + return merged_list - # Save the streaming content to a file - with open(file_path, "wb") as f: - for chunk in r.iter_content(chunk_size=8192): - f.write(chunk) - with open(file_body_path, "w") as f: - json.dump(json.loads(body.decode("utf-8")), f) +async def get_all_models(): + print("get_all_models") + tasks = [ + fetch_url(f"{url}/models", app.state.OPENAI_API_KEYS[idx]) + for idx, url in enumerate(app.state.OPENAI_API_BASE_URLS) + ] + responses = await asyncio.gather(*tasks) + responses = list(filter(lambda x: x is not None and "error" not in x, responses)) + models = { + "data": merge_models_lists( + list(map(lambda response: response["data"], responses)) + ) + } + app.state.MODELS = {model["id"]: model for model in models["data"]} - # Return the saved file - return FileResponse(file_path) + return models - except Exception as e: - print(e) - error_detail = "Open WebUI: Server Connection Error" - if r is not None: - try: - res = r.json() - if "error" in res: - error_detail = f"External: {res['error']}" - except: - error_detail = f"External: {e}" - raise HTTPException(status_code=r.status_code, detail=error_detail) +# , user=Depends(get_current_user) +@app.get("/models") +@app.get("/models/{url_idx}") +async def get_models(url_idx: Optional[int] = None): + if url_idx == None: + return await get_all_models() + else: + url = app.state.OPENAI_API_BASE_URLS[url_idx] + try: + r = requests.request(method="GET", url=f"{url}/models") + r.raise_for_status() + + response_data = r.json() + if "api.openai.com" in url: + response_data["data"] = list( + filter(lambda model: "gpt" in model["id"], response_data["data"]) + ) + + return response_data + except Exception as e: + print(e) + error_detail = "Open WebUI: Server Connection Error" + if r is not None: + try: + res = r.json() + if "error" in res: + error_detail = f"External: {res['error']}" + except: + error_detail = f"External: {e}" + + raise HTTPException( + status_code=r.status_code if r else 500, + detail=error_detail, + ) @app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"]) async def proxy(path: str, request: Request, user=Depends(get_verified_user)): - target_url = f"{app.state.OPENAI_API_BASE_URL}/{path}" - print(target_url, app.state.OPENAI_API_KEY) - - if app.state.OPENAI_API_KEY == "": - raise HTTPException(status_code=401, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND) + idx = 0 body = await request.body() - # TODO: Remove below after gpt-4-vision fix from Open AI # Try to decode the body of the request from bytes to a UTF-8 string (Require add max_token to fix gpt-4-vision) try: body = body.decode("utf-8") body = json.loads(body) + idx = app.state.MODELS[body.get("model")]["urlIdx"] + # Check if the model is "gpt-4-vision-preview" and set "max_tokens" to 4000 # This is a workaround until OpenAI fixes the issue with this model if body.get("model") == "gpt-4-vision-preview": @@ -158,8 +254,16 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)): except json.JSONDecodeError as e: print("Error loading request body into a dictionary:", e) + url = app.state.OPENAI_API_BASE_URLS[idx] + key = app.state.OPENAI_API_KEYS[idx] + + target_url = f"{url}/{path}" + + if key == "": + raise HTTPException(status_code=401, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND) + headers = {} - headers["Authorization"] = f"Bearer {app.state.OPENAI_API_KEY}" + headers["Authorization"] = f"Bearer {key}" headers["Content-Type"] = "application/json" try: @@ -181,21 +285,7 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)): headers=dict(r.headers), ) else: - # For non-SSE, read the response and return it - # response_data = ( - # r.json() - # if r.headers.get("Content-Type", "") - # == "application/json" - # else r.text - # ) - response_data = r.json() - - if "api.openai.com" in app.state.OPENAI_API_BASE_URL and path == "models": - response_data["data"] = list( - filter(lambda model: "gpt" in model["id"], response_data["data"]) - ) - return response_data except Exception as e: print(e) diff --git a/backend/apps/rag/main.py b/backend/apps/rag/main.py index 99aa69594..45ad69707 100644 --- a/backend/apps/rag/main.py +++ b/backend/apps/rag/main.py @@ -425,7 +425,7 @@ def get_loader(filename: str, file_content_type: str, file_path: str): ] if file_ext == "pdf": - loader = PyPDFLoader(file_path) + loader = PyPDFLoader(file_path, extract_images=True) elif file_ext == "csv": loader = CSVLoader(file_path) elif file_ext == "rst": diff --git a/backend/apps/web/routers/utils.py b/backend/apps/web/routers/utils.py index 6356bf452..fbb350cf2 100644 --- a/backend/apps/web/routers/utils.py +++ b/backend/apps/web/routers/utils.py @@ -14,7 +14,7 @@ import json from utils.utils import get_admin_user from utils.misc import calculate_sha256, get_gravatar_url -from config import OLLAMA_API_BASE_URL, DATA_DIR, UPLOAD_DIR +from config import OLLAMA_BASE_URLS, DATA_DIR, UPLOAD_DIR from constants import ERROR_MESSAGES @@ -75,7 +75,7 @@ async def download_file_stream(url, file_path, file_name, chunk_size=1024 * 1024 hashed = calculate_sha256(file) file.seek(0) - url = f"{OLLAMA_API_BASE_URL}/blobs/sha256:{hashed}" + url = f"{OLLAMA_BASE_URLS[0]}/blobs/sha256:{hashed}" response = requests.post(url, data=file) if response.ok: @@ -147,7 +147,7 @@ def upload(file: UploadFile = File(...)): hashed = calculate_sha256(f) f.seek(0) - url = f"{OLLAMA_API_BASE_URL}/blobs/sha256:{hashed}" + url = f"{OLLAMA_BASE_URLS[0]}/blobs/sha256:{hashed}" response = requests.post(url, data=f) if response.ok: diff --git a/backend/config.py b/backend/config.py index cd1a27023..2cd016539 100644 --- a/backend/config.py +++ b/backend/config.py @@ -200,27 +200,32 @@ if not os.path.exists(LITELLM_CONFIG_PATH): #################################### -# OLLAMA_API_BASE_URL +# OLLAMA_BASE_URL #################################### OLLAMA_API_BASE_URL = os.environ.get( "OLLAMA_API_BASE_URL", "http://localhost:11434/api" ) -if ENV == "prod": - if OLLAMA_API_BASE_URL == "/ollama/api": - OLLAMA_API_BASE_URL = "http://host.docker.internal:11434/api" - - OLLAMA_BASE_URL = os.environ.get("OLLAMA_BASE_URL", "") -if OLLAMA_BASE_URL == "": +if ENV == "prod": + if OLLAMA_BASE_URL == "/ollama": + OLLAMA_BASE_URL = "http://host.docker.internal:11434" + + +if OLLAMA_BASE_URL == "" and OLLAMA_API_BASE_URL != "": OLLAMA_BASE_URL = ( OLLAMA_API_BASE_URL[:-4] if OLLAMA_API_BASE_URL.endswith("/api") else OLLAMA_API_BASE_URL ) +OLLAMA_BASE_URLS = os.environ.get("OLLAMA_BASE_URLS", "") +OLLAMA_BASE_URLS = OLLAMA_BASE_URLS if OLLAMA_BASE_URLS != "" else OLLAMA_BASE_URL + +OLLAMA_BASE_URLS = [url.strip() for url in OLLAMA_BASE_URLS.split(";")] + #################################### # OPENAI_API @@ -229,9 +234,25 @@ if OLLAMA_BASE_URL == "": OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "") OPENAI_API_BASE_URL = os.environ.get("OPENAI_API_BASE_URL", "") +if OPENAI_API_KEY == "": + OPENAI_API_KEY = "none" + if OPENAI_API_BASE_URL == "": OPENAI_API_BASE_URL = "https://api.openai.com/v1" +OPENAI_API_KEYS = os.environ.get("OPENAI_API_KEYS", "") +OPENAI_API_KEYS = OPENAI_API_KEYS if OPENAI_API_KEYS != "" else OPENAI_API_KEY + +OPENAI_API_KEYS = [url.strip() for url in OPENAI_API_KEYS.split(";")] + + +OPENAI_API_BASE_URLS = os.environ.get("OPENAI_API_BASE_URLS", "") +OPENAI_API_BASE_URLS = ( + OPENAI_API_BASE_URLS if OPENAI_API_BASE_URLS != "" else OPENAI_API_BASE_URL +) + +OPENAI_API_BASE_URLS = [url.strip() for url in OPENAI_API_BASE_URL.split(";")] + #################################### # WEBUI diff --git a/backend/constants.py b/backend/constants.py index b2bbe9aae..eacf8a20f 100644 --- a/backend/constants.py +++ b/backend/constants.py @@ -41,6 +41,7 @@ class ERROR_MESSAGES(str, Enum): NOT_FOUND = "We could not find what you're looking for :/" USER_NOT_FOUND = "We could not find what you're looking for :/" API_KEY_NOT_FOUND = "Oops! It looks like there's a hiccup. The API key is missing. Please make sure to provide a valid API key to access this feature." + MALICIOUS = "Unusual activities detected, please try again in a few minutes." PANDOC_NOT_INSTALLED = "Pandoc is not installed on the server. Please contact your administrator for assistance." @@ -50,3 +51,4 @@ class ERROR_MESSAGES(str, Enum): RATE_LIMIT_EXCEEDED = "API rate limit exceeded" MODEL_NOT_FOUND = lambda name="": f"Model '{name}' was not found" + OPENAI_NOT_FOUND = lambda name="": f"OpenAI API was not found" diff --git a/backend/requirements.txt b/backend/requirements.txt index 6d3d044dc..41527a78c 100644 --- a/backend/requirements.txt +++ b/backend/requirements.txt @@ -35,6 +35,9 @@ openpyxl pyxlsb xlrd +opencv-python-headless +rapidocr-onnxruntime + faster-whisper PyJWT diff --git a/docker-compose.yaml b/docker-compose.yaml index c41c56d8e..f69084b8a 100644 --- a/docker-compose.yaml +++ b/docker-compose.yaml @@ -14,7 +14,7 @@ services: build: context: . args: - OLLAMA_API_BASE_URL: '/ollama/api' + OLLAMA_BASE_URL: '/ollama' dockerfile: Dockerfile image: ghcr.io/open-webui/open-webui:main container_name: open-webui @@ -25,7 +25,7 @@ services: ports: - ${OPEN_WEBUI_PORT-3000}:8080 environment: - - 'OLLAMA_API_BASE_URL=http://ollama:11434/api' + - 'OLLAMA_BASE_URL=http://ollama:11434' - 'WEBUI_SECRET_KEY=' extra_hosts: - host.docker.internal:host-gateway diff --git a/kubernetes/helm/templates/webui-deployment.yaml b/kubernetes/helm/templates/webui-deployment.yaml index df13a14b6..bbd5706de 100644 --- a/kubernetes/helm/templates/webui-deployment.yaml +++ b/kubernetes/helm/templates/webui-deployment.yaml @@ -40,7 +40,7 @@ spec: - name: data mountPath: /app/backend/data env: - - name: OLLAMA_API_BASE_URL + - name: OLLAMA_BASE_URL value: {{ include "ollama.url" . | quote }} tty: true {{- with .Values.webui.nodeSelector }} diff --git a/kubernetes/manifest/base/webui-deployment.yaml b/kubernetes/manifest/base/webui-deployment.yaml index 174025a94..38efd5549 100644 --- a/kubernetes/manifest/base/webui-deployment.yaml +++ b/kubernetes/manifest/base/webui-deployment.yaml @@ -26,8 +26,8 @@ spec: cpu: "1000m" memory: "1Gi" env: - - name: OLLAMA_API_BASE_URL - value: "http://ollama-service.open-webui.svc.cluster.local:11434/api" + - name: OLLAMA_BASE_URL + value: "http://ollama-service.open-webui.svc.cluster.local:11434" tty: true volumeMounts: - name: webui-volume diff --git a/package.json b/package.json index 46f7f4e77..56889c8b5 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "open-webui", - "version": "0.1.108", + "version": "0.1.110", "private": true, "scripts": { "dev": "vite dev --host", diff --git a/src/app.css b/src/app.css index 63b34465c..82b3caa37 100644 --- a/src/app.css +++ b/src/app.css @@ -43,6 +43,10 @@ ol > li { font-weight: 400; } +li p { + display: inline; +} + ::-webkit-scrollbar-thumb { --tw-border-opacity: 1; background-color: rgba(217, 217, 227, 0.8); diff --git a/src/lib/apis/openai/index.ts b/src/lib/apis/openai/index.ts index 3a629eb31..e38314a55 100644 --- a/src/lib/apis/openai/index.ts +++ b/src/lib/apis/openai/index.ts @@ -1,9 +1,9 @@ import { OPENAI_API_BASE_URL } from '$lib/constants'; -export const getOpenAIUrl = async (token: string = '') => { +export const getOpenAIUrls = async (token: string = '') => { let error = null; - const res = await fetch(`${OPENAI_API_BASE_URL}/url`, { + const res = await fetch(`${OPENAI_API_BASE_URL}/urls`, { method: 'GET', headers: { Accept: 'application/json', @@ -29,13 +29,13 @@ export const getOpenAIUrl = async (token: string = '') => { throw error; } - return res.OPENAI_API_BASE_URL; + return res.OPENAI_API_BASE_URLS; }; -export const updateOpenAIUrl = async (token: string = '', url: string) => { +export const updateOpenAIUrls = async (token: string = '', urls: string[]) => { let error = null; - const res = await fetch(`${OPENAI_API_BASE_URL}/url/update`, { + const res = await fetch(`${OPENAI_API_BASE_URL}/urls/update`, { method: 'POST', headers: { Accept: 'application/json', @@ -43,7 +43,7 @@ export const updateOpenAIUrl = async (token: string = '', url: string) => { ...(token && { authorization: `Bearer ${token}` }) }, body: JSON.stringify({ - url: url + urls: urls }) }) .then(async (res) => { @@ -64,13 +64,13 @@ export const updateOpenAIUrl = async (token: string = '', url: string) => { throw error; } - return res.OPENAI_API_BASE_URL; + return res.OPENAI_API_BASE_URLS; }; -export const getOpenAIKey = async (token: string = '') => { +export const getOpenAIKeys = async (token: string = '') => { let error = null; - const res = await fetch(`${OPENAI_API_BASE_URL}/key`, { + const res = await fetch(`${OPENAI_API_BASE_URL}/keys`, { method: 'GET', headers: { Accept: 'application/json', @@ -96,13 +96,13 @@ export const getOpenAIKey = async (token: string = '') => { throw error; } - return res.OPENAI_API_KEY; + return res.OPENAI_API_KEYS; }; -export const updateOpenAIKey = async (token: string = '', key: string) => { +export const updateOpenAIKeys = async (token: string = '', keys: string[]) => { let error = null; - const res = await fetch(`${OPENAI_API_BASE_URL}/key/update`, { + const res = await fetch(`${OPENAI_API_BASE_URL}/keys/update`, { method: 'POST', headers: { Accept: 'application/json', @@ -110,7 +110,7 @@ export const updateOpenAIKey = async (token: string = '', key: string) => { ...(token && { authorization: `Bearer ${token}` }) }, body: JSON.stringify({ - key: key + keys: keys }) }) .then(async (res) => { @@ -131,7 +131,7 @@ export const updateOpenAIKey = async (token: string = '', key: string) => { throw error; } - return res.OPENAI_API_KEY; + return res.OPENAI_API_KEYS; }; export const getOpenAIModels = async (token: string = '') => { diff --git a/src/lib/components/chat/Messages.svelte b/src/lib/components/chat/Messages.svelte index 7ef4b5c52..7afb5c376 100644 --- a/src/lib/components/chat/Messages.svelte +++ b/src/lib/components/chat/Messages.svelte @@ -225,33 +225,80 @@ }, 100); }; - // TODO: change delete behaviour - // const deleteMessageAndDescendants = async (messageId: string) => { - // if (history.messages[messageId]) { - // history.messages[messageId].deleted = true; - - // for (const childId of history.messages[messageId].childrenIds) { - // await deleteMessageAndDescendants(childId); - // } - // } - // }; - - // const triggerDeleteMessageRecursive = async (messageId: string) => { - // await deleteMessageAndDescendants(messageId); - // await updateChatById(localStorage.token, chatId, { history }); - // await chats.set(await getChatList(localStorage.token)); - // }; - const messageDeleteHandler = async (messageId) => { - if (history.messages[messageId]) { - history.messages[messageId].deleted = true; - - for (const childId of history.messages[messageId].childrenIds) { - history.messages[childId].deleted = true; + const messageToDelete = history.messages[messageId]; + const messageParentId = messageToDelete.parentId; + const messageChildrenIds = messageToDelete.childrenIds ?? []; + const hasSibling = messageChildrenIds.some( + (childId) => history.messages[childId]?.childrenIds?.length > 0 + ); + messageChildrenIds.forEach((childId) => { + const child = history.messages[childId]; + if (child && child.childrenIds) { + if (child.childrenIds.length === 0 && !hasSibling) { + // if last prompt/response pair + history.messages[messageParentId].childrenIds = []; + history.currentId = messageParentId; + } else { + child.childrenIds.forEach((grandChildId) => { + if (history.messages[grandChildId]) { + history.messages[grandChildId].parentId = messageParentId; + history.messages[messageParentId].childrenIds.push(grandChildId); + } + }); + } } - } - await updateChatById(localStorage.token, chatId, { history }); + // remove response + history.messages[messageParentId].childrenIds = history.messages[ + messageParentId + ].childrenIds.filter((id) => id !== childId); + }); + // remove prompt + history.messages[messageParentId].childrenIds = history.messages[ + messageParentId + ].childrenIds.filter((id) => id !== messageId); + await updateChatById(localStorage.token, chatId, { + messages: messages, + history: history + }); }; + + // const messageDeleteHandler = async (messageId) => { + // const message = history.messages[messageId]; + // const parentId = message.parentId; + // const childrenIds = message.childrenIds ?? []; + // const grandchildrenIds = []; + + // // Iterate through childrenIds to find grandchildrenIds + // for (const childId of childrenIds) { + // const childMessage = history.messages[childId]; + // const grandChildrenIds = childMessage.childrenIds ?? []; + + // for (const grandchildId of grandchildrenIds) { + // const childMessage = history.messages[grandchildId]; + // childMessage.parentId = parentId; + // } + // grandchildrenIds.push(...grandChildrenIds); + // } + + // history.messages[parentId].childrenIds.push(...grandchildrenIds); + // history.messages[parentId].childrenIds = history.messages[parentId].childrenIds.filter( + // (id) => id !== messageId + // ); + + // // Select latest message + // let currentMessageId = grandchildrenIds.at(-1); + // if (currentMessageId) { + // let messageChildrenIds = history.messages[currentMessageId].childrenIds; + // while (messageChildrenIds.length !== 0) { + // currentMessageId = messageChildrenIds.at(-1); + // messageChildrenIds = history.messages[currentMessageId].childrenIds; + // } + // history.currentId = currentMessageId; + // } + + // await updateChatById(localStorage.token, chatId, { messages, history }); + // }; {#if messages.length == 0} @@ -260,57 +307,55 @@
{#key chatId} {#each messages as message, messageIdx} - {#if !message.deleted} -
-
- {#if message.role === 'user'} - messageDeleteHandler(message.id)} - user={$user} - {message} - isFirstMessage={messageIdx === 0} - siblings={message.parentId !== null - ? history.messages[message.parentId]?.childrenIds ?? [] - : Object.values(history.messages) - .filter((message) => message.parentId === null) - .map((message) => message.id) ?? []} - {confirmEditMessage} - {showPreviousMessage} - {showNextMessage} - {copyToClipboard} - /> - {:else} - { - console.log('save', e); +
+
+ {#if message.role === 'user'} + messageDeleteHandler(message.id)} + user={$user} + {message} + isFirstMessage={messageIdx === 0} + siblings={message.parentId !== null + ? history.messages[message.parentId]?.childrenIds ?? [] + : Object.values(history.messages) + .filter((message) => message.parentId === null) + .map((message) => message.id) ?? []} + {confirmEditMessage} + {showPreviousMessage} + {showNextMessage} + {copyToClipboard} + /> + {:else} + { + console.log('save', e); - const message = e.detail; - history.messages[message.id] = message; - await updateChatById(localStorage.token, chatId, { - messages: messages, - history: history - }); - }} - /> - {/if} -
+ const message = e.detail; + history.messages[message.id] = message; + await updateChatById(localStorage.token, chatId, { + messages: messages, + history: history + }); + }} + /> + {/if}
- {/if} +
{/each} {#if bottomPadding} diff --git a/src/lib/components/chat/Messages/ResponseMessage.svelte b/src/lib/components/chat/Messages/ResponseMessage.svelte index 7c6985acd..c5d2c602e 100644 --- a/src/lib/components/chat/Messages/ResponseMessage.svelte +++ b/src/lib/components/chat/Messages/ResponseMessage.svelte @@ -24,6 +24,7 @@ import CodeBlock from './CodeBlock.svelte'; import Image from '$lib/components/common/Image.svelte'; import { WEBUI_BASE_URL } from '$lib/constants'; + import Tooltip from '$lib/components/common/Tooltip.svelte'; export let modelfiles = []; export let message; @@ -346,6 +347,7 @@ class=" bg-transparent outline-none w-full resize-none" bind:value={editedContent} on:input={(e) => { + e.target.style.height = ''; e.target.style.height = `${e.target.scrollHeight}px`; }} /> @@ -464,189 +466,125 @@
{/if} - - - - - - - - - - {#if $config.images} + + + + + + + + + + + + + + + + + + + + {#if $config.images} + + + {/if} {#if message.info} - + + + + + {/if} {#if isLastMessage} - + + + + + + - + + + + + {/if}
{/if} diff --git a/src/lib/components/chat/Messages/UserMessage.svelte b/src/lib/components/chat/Messages/UserMessage.svelte index 6de9e67a1..9e6c72d2d 100644 --- a/src/lib/components/chat/Messages/UserMessage.svelte +++ b/src/lib/components/chat/Messages/UserMessage.svelte @@ -5,6 +5,7 @@ import Name from './Name.svelte'; import ProfileImage from './ProfileImage.svelte'; import { modelfiles, settings } from '$lib/stores'; + import Tooltip from '$lib/components/common/Tooltip.svelte'; const i18n = getContext('i18n'); @@ -171,7 +172,8 @@ class=" bg-transparent outline-none w-full resize-none" bind:value={editedContent} on:input={(e) => { - messageEditTextAreaElement.style.height = `${messageEditTextAreaElement.scrollHeight}px`; + e.target.style.height = ''; + e.target.style.height = `${e.target.scrollHeight}px`; }} /> @@ -248,55 +250,11 @@ {/if} - - - - - {#if !isFirstMessage} + + + + + + + + {#if !isFirstMessage} + + + {/if} diff --git a/src/lib/components/chat/Settings/Connections.svelte b/src/lib/components/chat/Settings/Connections.svelte index 0329e0b7c..fedd916f7 100644 --- a/src/lib/components/chat/Settings/Connections.svelte +++ b/src/lib/components/chat/Settings/Connections.svelte @@ -4,7 +4,12 @@ const dispatch = createEventDispatcher(); import { getOllamaUrls, getOllamaVersion, updateOllamaUrls } from '$lib/apis/ollama'; - import { getOpenAIKey, getOpenAIUrl, updateOpenAIKey, updateOpenAIUrl } from '$lib/apis/openai'; + import { + getOpenAIKeys, + getOpenAIUrls, + updateOpenAIKeys, + updateOpenAIUrls + } from '$lib/apis/openai'; import { toast } from 'svelte-sonner'; const i18n = getContext('i18n'); @@ -18,12 +23,14 @@ let OPENAI_API_KEY = ''; let OPENAI_API_BASE_URL = ''; + let OPENAI_API_KEYS = ['']; + let OPENAI_API_BASE_URLS = ['']; + let showOpenAI = false; - let showLiteLLM = false; const updateOpenAIHandler = async () => { - OPENAI_API_BASE_URL = await updateOpenAIUrl(localStorage.token, OPENAI_API_BASE_URL); - OPENAI_API_KEY = await updateOpenAIKey(localStorage.token, OPENAI_API_KEY); + OPENAI_API_BASE_URLS = await updateOpenAIUrls(localStorage.token, OPENAI_API_BASE_URLS); + OPENAI_API_KEYS = await updateOpenAIKeys(localStorage.token, OPENAI_API_KEYS); await models.set(await getModels()); }; @@ -45,8 +52,8 @@ onMount(async () => { if ($user.role === 'admin') { OLLAMA_BASE_URLS = await getOllamaUrls(localStorage.token); - OPENAI_API_BASE_URL = await getOpenAIUrl(localStorage.token); - OPENAI_API_KEY = await getOpenAIKey(localStorage.token); + OPENAI_API_BASE_URLS = await getOpenAIUrls(localStorage.token); + OPENAI_API_KEYS = await getOpenAIKeys(localStorage.token); } }); @@ -73,37 +80,74 @@ {#if showOpenAI} -
-
{$i18n.t('API Key')}
-
-
- -
-
-
+
+ {#each OPENAI_API_BASE_URLS as url, idx} +
+
+ +
-
-
{$i18n.t('API Base URL')}
-
-
- +
+ +
+
+ {#if idx === 0} + + {:else} + + {/if} +
-
-
- WebUI will make requests to '{OPENAI_API_BASE_URL}/chat' -
+
+ WebUI will make requests to '{url}/models' +
+ {/each}
{/if}
diff --git a/src/lib/components/chat/Settings/Models.svelte b/src/lib/components/chat/Settings/Models.svelte index a59e71025..ba4168168 100644 --- a/src/lib/components/chat/Settings/Models.svelte +++ b/src/lib/components/chat/Settings/Models.svelte @@ -56,7 +56,7 @@ let modelUploadMode = 'file'; let modelInputFile = ''; let modelFileUrl = ''; - let modelFileContent = `TEMPLATE """{{ .System }}\nUSER: {{ .Prompt }}\nASSSISTANT: """\nPARAMETER num_ctx 4096\nPARAMETER stop ""\nPARAMETER stop "USER:"\nPARAMETER stop "ASSSISTANT:"`; + let modelFileContent = `TEMPLATE """{{ .System }}\nUSER: {{ .Prompt }}\nASSISTANT: """\nPARAMETER num_ctx 4096\nPARAMETER stop ""\nPARAMETER stop "USER:"\nPARAMETER stop "ASSISTANT:"`; let modelFileDigest = ''; let uploadProgress = null; @@ -517,7 +517,7 @@ {#if !deleteModelTag} {/if} - {#each $models.filter((m) => m.size != null) as model} + {#each $models.filter((m) => m.size != null && (selectedOllamaUrlIdx === null ? true : (m?.urls ?? []).includes(selectedOllamaUrlIdx))) as model} @@ -599,7 +599,7 @@ on:change={() => { console.log(modelInputFile); }} - accept=".gguf" + accept=".gguf,.safetensors" required hidden /> diff --git a/src/lib/components/documents/AddDocModal.svelte b/src/lib/components/documents/AddDocModal.svelte index bbd29ae9c..3ea91c02b 100644 --- a/src/lib/components/documents/AddDocModal.svelte +++ b/src/lib/components/documents/AddDocModal.svelte @@ -140,7 +140,9 @@