bhetherman/open-webui
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'dev' into feat/scim-2.0-support

Browse Source
This commit is contained in:
Dieu
2025-07-14 00:48:50 +02:00
committed by GitHub
parent 6469822af1 8e7731f139
commit 41faec758b
302 changed files with 16478 additions and 7350 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/open_webui/routers/audio.py
+29 -22
View File
@@ -15,6 +15,7 @@ import aiohttp
import aiofiles
import requests
import mimetypes
from urllib.parse import quote
from fastapi import (
Depends,
@@ -327,6 +328,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
log.exception(e)
raise HTTPException(status_code=400, detail="Invalid JSON payload")
r = None
if request.app.state.config.TTS_ENGINE == "openai":
payload["model"] = request.app.state.config.TTS_MODEL
@@ -335,7 +337,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
async with aiohttp.ClientSession(
timeout=timeout, trust_env=True
) as session:
async with session.post(
r = await session.post(
url=f"{request.app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
json=payload,
headers={
@@ -343,7 +345,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
"Authorization": f"Bearer {request.app.state.config.TTS_OPENAI_API_KEY}",
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -353,14 +355,15 @@ async def speech(request: Request, user=Depends(get_verified_user)):
),
},
ssl=AIOHTTP_CLIENT_SESSION_SSL,
) as r:
r.raise_for_status()
)
async with aiofiles.open(file_path, "wb") as f:
await f.write(await r.read())
r.raise_for_status()
async with aiofiles.open(file_body_path, "w") as f:
await f.write(json.dumps(payload))
async with aiofiles.open(file_path, "wb") as f:
await f.write(await r.read())
async with aiofiles.open(file_body_path, "w") as f:
await f.write(json.dumps(payload))
return FileResponse(file_path)
@@ -368,18 +371,18 @@ async def speech(request: Request, user=Depends(get_verified_user)):
log.exception(e)
detail = None
try:
if r.status != 200:
res = await r.json()
status_code = 500
detail = f"Open WebUI: Server Connection Error"
if "error" in res:
detail = f"External: {res['error'].get('message', '')}"
except Exception:
detail = f"External: {e}"
if r is not None:
status_code = r.status
res = await r.json()
if "error" in res:
detail = f"External: {res['error'].get('message', '')}"
raise HTTPException(
status_code=getattr(r, "status", 500) if r else 500,
detail=detail if detail else "Open WebUI: Server Connection Error",
status_code=status_code,
detail=detail,
)
elif request.app.state.config.TTS_ENGINE == "elevenlabs":
@@ -919,14 +922,18 @@ def transcription(
):
log.info(f"file.content_type: {file.content_type}")
supported_content_types = request.app.state.config.STT_SUPPORTED_CONTENT_TYPES or [
"audio/*",
"video/webm",
]
stt_supported_content_types = getattr(
request.app.state.config, "STT_SUPPORTED_CONTENT_TYPES", []
)
if not any(
fnmatch(file.content_type, content_type)
for content_type in supported_content_types
for content_type in (
stt_supported_content_types
if stt_supported_content_types
and any(t.strip() for t in stt_supported_content_types)
else ["audio/*", "video/webm"]
)
):
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
backend/open_webui/routers/auths.py
+8 -2
View File
@@ -669,12 +669,13 @@ async def signup(request: Request, response: Response, form_data: SignupForm):
@router.get("/signout")
async def signout(request: Request, response: Response):
response.delete_cookie("token")
response.delete_cookie("oui-session")
if ENABLE_OAUTH_SIGNUP.value:
oauth_id_token = request.cookies.get("oauth_id_token")
if oauth_id_token:
try:
async with ClientSession() as session:
async with ClientSession(trust_env=True) as session:
async with session.get(OPENID_PROVIDER_URL.value) as resp:
if resp.status == 200:
openid_data = await resp.json()
@@ -686,7 +687,12 @@ async def signout(request: Request, response: Response):
status_code=200,
content={
"status": True,
"redirect_url": f"{logout_url}?id_token_hint={oauth_id_token}",
"redirect_url": f"{logout_url}?id_token_hint={oauth_id_token}"
+ (
f"&post_logout_redirect_uri={WEBUI_AUTH_SIGNOUT_REDIRECT_URL}"
if WEBUI_AUTH_SIGNOUT_REDIRECT_URL
else ""
),
},
headers=response.headers,
)
backend/open_webui/routers/channels.py
+6 -2
View File
@@ -40,10 +40,14 @@ router = APIRouter()
@router.get("/", response_model=list[ChannelModel])
async def get_channels(user=Depends(get_verified_user)):
return Channels.get_channels_by_user_id(user.id)
@router.get("/list", response_model=list[ChannelModel])
async def get_all_channels(user=Depends(get_verified_user)):
if user.role == "admin":
return Channels.get_channels()
else:
return Channels.get_channels_by_user_id(user.id)
return Channels.get_channels_by_user_id(user.id)
############################
backend/open_webui/routers/chats.py
+4 -2
View File
@@ -684,8 +684,10 @@ async def archive_chat_by_id(id: str, user=Depends(get_verified_user)):
@router.post("/{id}/share", response_model=Optional[ChatResponse])
async def share_chat_by_id(request: Request, id: str, user=Depends(get_verified_user)):
if not has_permission(
user.id, "chat.share", request.app.state.config.USER_PERMISSIONS
if (user.role != "admin") and (
not has_permission(
user.id, "chat.share", request.app.state.config.USER_PERMISSIONS
)
):
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,
backend/open_webui/routers/configs.py
+14 -7
View File
@@ -39,32 +39,39 @@ async def export_config(user=Depends(get_admin_user)):
############################
# Direct Connections Config
# Connections Config
############################
class DirectConnectionsConfigForm(BaseModel):
class ConnectionsConfigForm(BaseModel):
ENABLE_DIRECT_CONNECTIONS: bool
ENABLE_BASE_MODELS_CACHE: bool
@router.get("/direct_connections", response_model=DirectConnectionsConfigForm)
async def get_direct_connections_config(request: Request, user=Depends(get_admin_user)):
@router.get("/connections", response_model=ConnectionsConfigForm)
async def get_connections_config(request: Request, user=Depends(get_admin_user)):
return {
"ENABLE_DIRECT_CONNECTIONS": request.app.state.config.ENABLE_DIRECT_CONNECTIONS,
"ENABLE_BASE_MODELS_CACHE": request.app.state.config.ENABLE_BASE_MODELS_CACHE,
}
@router.post("/direct_connections", response_model=DirectConnectionsConfigForm)
async def set_direct_connections_config(
@router.post("/connections", response_model=ConnectionsConfigForm)
async def set_connections_config(
request: Request,
form_data: DirectConnectionsConfigForm,
form_data: ConnectionsConfigForm,
user=Depends(get_admin_user),
):
request.app.state.config.ENABLE_DIRECT_CONNECTIONS = (
form_data.ENABLE_DIRECT_CONNECTIONS
)
request.app.state.config.ENABLE_BASE_MODELS_CACHE = (
form_data.ENABLE_BASE_MODELS_CACHE
)
return {
"ENABLE_DIRECT_CONNECTIONS": request.app.state.config.ENABLE_DIRECT_CONNECTIONS,
"ENABLE_BASE_MODELS_CACHE": request.app.state.config.ENABLE_BASE_MODELS_CACHE,
}
backend/open_webui/routers/files.py
+8 -7
View File
@@ -155,17 +155,18 @@ def upload_file(
if process:
try:
if file.content_type:
stt_supported_content_types = (
request.app.state.config.STT_SUPPORTED_CONTENT_TYPES
or [
"audio/*",
"video/webm",
]
stt_supported_content_types = getattr(
request.app.state.config, "STT_SUPPORTED_CONTENT_TYPES", []
)
if any(
fnmatch(file.content_type, content_type)
for content_type in stt_supported_content_types
for content_type in (
stt_supported_content_types
if stt_supported_content_types
and any(t.strip() for t in stt_supported_content_types)
else ["audio/*", "video/webm"]
)
):
file_path = Storage.get_file(file_path)
result = transcribe(request, file_path, file_metadata)
backend/open_webui/routers/folders.py
+2 -4
View File
@@ -120,16 +120,14 @@ async def update_folder_name_by_id(
existing_folder = Folders.get_folder_by_parent_id_and_user_id_and_name(
folder.parent_id, user.id, form_data.name
)
if existing_folder:
if existing_folder and existing_folder.id != id:
raise HTTPException(
status_code=status.HTTP_400_BAD_REQUEST,
detail=ERROR_MESSAGES.DEFAULT("Folder already exists"),
)
try:
folder = Folders.update_folder_name_by_id_and_user_id(
id, user.id, form_data.name
)
folder = Folders.update_folder_by_id_and_user_id(id, user.id, form_data)
return folder
except Exception as e:
backend/open_webui/routers/functions.py
+1 -1
View File
@@ -105,7 +105,7 @@ async def load_function_from_url(
)
try:
async with aiohttp.ClientSession() as session:
async with aiohttp.ClientSession(trust_env=True) as session:
async with session.get(
url, headers={"Content-Type": "application/json"}
) as resp:
backend/open_webui/routers/images.py
+19 -3
View File
@@ -8,6 +8,7 @@ import re
from pathlib import Path
from typing import Optional
from urllib.parse import quote
import requests
from fastapi import APIRouter, Depends, HTTPException, Request, UploadFile
from open_webui.config import CACHE_DIR
@@ -302,8 +303,16 @@ async def update_image_config(
):
set_image_model(request, form_data.MODEL)
if form_data.IMAGE_SIZE == "auto" and form_data.MODEL != "gpt-image-1":
raise HTTPException(
status_code=400,
detail=ERROR_MESSAGES.INCORRECT_FORMAT(
" (auto is only allowed with gpt-image-1)."
),
)
pattern = r"^\d+x\d+$"
if re.match(pattern, form_data.IMAGE_SIZE):
if form_data.IMAGE_SIZE == "auto" or re.match(pattern, form_data.IMAGE_SIZE):
request.app.state.config.IMAGE_SIZE = form_data.IMAGE_SIZE
else:
raise HTTPException(
@@ -471,7 +480,14 @@ async def image_generations(
form_data: GenerateImageForm,
user=Depends(get_verified_user),
):
width, height = tuple(map(int, request.app.state.config.IMAGE_SIZE.split("x")))
# if IMAGE_SIZE = 'auto', default WidthxHeight to the 512x512 default
# This is only relevant when the user has set IMAGE_SIZE to 'auto' with an
# image model other than gpt-image-1, which is warned about on settings save
width, height = (
tuple(map(int, request.app.state.config.IMAGE_SIZE.split("x")))
if "x" in request.app.state.config.IMAGE_SIZE
else (512, 512)
)
r = None
try:
@@ -483,7 +499,7 @@ async def image_generations(
headers["Content-Type"] = "application/json"
if ENABLE_FORWARD_USER_INFO_HEADERS:
headers["X-OpenWebUI-User-Name"] = user.name
headers["X-OpenWebUI-User-Name"] = quote(user.name, safe=" ")
headers["X-OpenWebUI-User-Id"] = user.id
headers["X-OpenWebUI-User-Email"] = user.email
headers["X-OpenWebUI-User-Role"] = user.role
backend/open_webui/routers/notes.py
+10 -8
View File
@@ -51,7 +51,14 @@ async def get_notes(request: Request, user=Depends(get_verified_user)):
return notes
@router.get("/list", response_model=list[NoteUserResponse])
class NoteTitleIdResponse(BaseModel):
id: str
title: str
updated_at: int
created_at: int
@router.get("/list", response_model=list[NoteTitleIdResponse])
async def get_note_list(request: Request, user=Depends(get_verified_user)):
if user.role != "admin" and not has_permission(
@@ -63,13 +70,8 @@ async def get_note_list(request: Request, user=Depends(get_verified_user)):
)
notes = [
NoteUserResponse(
**{
**note.model_dump(),
"user": UserResponse(**Users.get_user_by_id(note.user_id).model_dump()),
}
)
for note in Notes.get_notes_by_user_id(user.id, "read")
NoteTitleIdResponse(**note.model_dump())
for note in Notes.get_notes_by_user_id(user.id, "write")
]
return notes
backend/open_webui/routers/ollama.py
+46 -26
View File
@@ -16,6 +16,7 @@ from urllib.parse import urlparse
import aiohttp
from aiocache import cached
import requests
from urllib.parse import quote
from open_webui.models.chats import Chats
from open_webui.models.users import UserModel
@@ -58,6 +59,7 @@ from open_webui.config import (
from open_webui.env import (
ENV,
SRC_LOG_LEVELS,
MODELS_CACHE_TTL,
AIOHTTP_CLIENT_SESSION_SSL,
AIOHTTP_CLIENT_TIMEOUT,
AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST,
@@ -87,7 +89,7 @@ async def send_get_request(url, key=None, user: UserModel = None):
**({"Authorization": f"Bearer {key}"} if key else {}),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -138,7 +140,7 @@ async def send_post_request(
**({"Authorization": f"Bearer {key}"} if key else {}),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -242,7 +244,7 @@ async def verify_connection(
**({"Authorization": f"Bearer {key}"} if key else {}),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -329,7 +331,7 @@ def merge_ollama_models_lists(model_lists):
return list(merged_models.values())
@cached(ttl=1)
@cached(ttl=MODELS_CACHE_TTL)
async def get_all_models(request: Request, user: UserModel = None):
log.info("get_all_models()")
if request.app.state.config.ENABLE_OLLAMA_API:
@@ -462,7 +464,7 @@ async def get_ollama_tags(
**({"Authorization": f"Bearer {key}"} if key else {}),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -634,7 +636,10 @@ async def get_ollama_versions(request: Request, url_idx: Optional[int] = None):
class ModelNameForm(BaseModel):
name: str
model: Optional[str] = None
model_config = ConfigDict(
extra="allow",
)
@router.post("/api/unload")
@@ -643,10 +648,12 @@ async def unload_model(
form_data: ModelNameForm,
user=Depends(get_admin_user),
):
model_name = form_data.name
form_data = form_data.model_dump(exclude_none=True)
model_name = form_data.get("model", form_data.get("name"))
if not model_name:
raise HTTPException(
status_code=400, detail="Missing 'name' of model to unload."
status_code=400, detail="Missing name of the model to unload."
)
# Refresh/load models if needed, get mapping from name to URLs
@@ -709,11 +716,14 @@ async def pull_model(
url_idx: int = 0,
user=Depends(get_admin_user),
):
form_data = form_data.model_dump(exclude_none=True)
form_data["model"] = form_data.get("model", form_data.get("name"))
url = request.app.state.config.OLLAMA_BASE_URLS[url_idx]
log.info(f"url: {url}")
# Admin should be able to pull models from any source
payload = {**form_data.model_dump(exclude_none=True), "insecure": True}
payload = {**form_data, "insecure": True}
return await send_post_request(
url=f"{url}/api/pull",
@@ -724,7 +734,7 @@ async def pull_model(
class PushModelForm(BaseModel):
name: str
model: str
insecure: Optional[bool] = None
stream: Optional[bool] = None
@@ -741,12 +751,12 @@ async def push_model(
await get_all_models(request, user=user)
models = request.app.state.OLLAMA_MODELS
if form_data.name in models:
url_idx = models[form_data.name]["urls"][0]
if form_data.model in models:
url_idx = models[form_data.model]["urls"][0]
else:
raise HTTPException(
status_code=400,
detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.name),
detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model),
)
url = request.app.state.config.OLLAMA_BASE_URLS[url_idx]
@@ -824,7 +834,7 @@ async def copy_model(
**({"Authorization": f"Bearer {key}"} if key else {}),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -865,16 +875,21 @@ async def delete_model(
url_idx: Optional[int] = None,
user=Depends(get_admin_user),
):
form_data = form_data.model_dump(exclude_none=True)
form_data["model"] = form_data.get("model", form_data.get("name"))
model = form_data.get("model")
if url_idx is None:
await get_all_models(request, user=user)
models = request.app.state.OLLAMA_MODELS
if form_data.name in models:
url_idx = models[form_data.name]["urls"][0]
if model in models:
url_idx = models[model]["urls"][0]
else:
raise HTTPException(
status_code=400,
detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.name),
detail=ERROR_MESSAGES.MODEL_NOT_FOUND(model),
)
url = request.app.state.config.OLLAMA_BASE_URLS[url_idx]
@@ -884,13 +899,13 @@ async def delete_model(
r = requests.request(
method="DELETE",
url=f"{url}/api/delete",
data=form_data.model_dump_json(exclude_none=True).encode(),
data=json.dumps(form_data).encode(),
headers={
"Content-Type": "application/json",
**({"Authorization": f"Bearer {key}"} if key else {}),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -926,16 +941,21 @@ async def delete_model(
async def show_model_info(
request: Request, form_data: ModelNameForm, user=Depends(get_verified_user)
):
form_data = form_data.model_dump(exclude_none=True)
form_data["model"] = form_data.get("model", form_data.get("name"))
await get_all_models(request, user=user)
models = request.app.state.OLLAMA_MODELS
if form_data.name not in models:
model = form_data.get("model")
if model not in models:
raise HTTPException(
status_code=400,
detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.name),
detail=ERROR_MESSAGES.MODEL_NOT_FOUND(model),
)
url_idx = random.choice(models[form_data.name]["urls"])
url_idx = random.choice(models[model]["urls"])
url = request.app.state.config.OLLAMA_BASE_URLS[url_idx]
key = get_api_key(url_idx, url, request.app.state.config.OLLAMA_API_CONFIGS)
@@ -949,7 +969,7 @@ async def show_model_info(
**({"Authorization": f"Bearer {key}"} if key else {}),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -958,7 +978,7 @@ async def show_model_info(
else {}
),
},
data=form_data.model_dump_json(exclude_none=True).encode(),
data=json.dumps(form_data).encode(),
)
r.raise_for_status()
@@ -1036,7 +1056,7 @@ async def embed(
**({"Authorization": f"Bearer {key}"} if key else {}),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -1123,7 +1143,7 @@ async def embeddings(
**({"Authorization": f"Bearer {key}"} if key else {}),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
backend/open_webui/routers/openai.py
+34 -23
View File
@@ -8,7 +8,7 @@ from typing import Literal, Optional, overload
import aiohttp
from aiocache import cached
import requests
from urllib.parse import quote
from fastapi import Depends, FastAPI, HTTPException, Request, APIRouter
from fastapi.middleware.cors import CORSMiddleware
@@ -21,6 +21,7 @@ from open_webui.config import (
CACHE_DIR,
)
from open_webui.env import (
MODELS_CACHE_TTL,
AIOHTTP_CLIENT_SESSION_SSL,
AIOHTTP_CLIENT_TIMEOUT,
AIOHTTP_CLIENT_TIMEOUT_MODEL_LIST,
@@ -66,7 +67,7 @@ async def send_get_request(url, key=None, user: UserModel = None):
**({"Authorization": f"Bearer {key}"} if key else {}),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -225,7 +226,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -386,7 +387,7 @@ async def get_filtered_models(models, user):
return filtered_models
@cached(ttl=1)
@cached(ttl=MODELS_CACHE_TTL)
async def get_all_models(request: Request, user: UserModel) -> dict[str, list]:
log.info("get_all_models()")
@@ -478,7 +479,7 @@ async def get_models(
"Content-Type": "application/json",
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -573,7 +574,7 @@ async def verify_connection(
"Content-Type": "application/json",
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -633,13 +634,7 @@ async def verify_connection(
raise HTTPException(status_code=500, detail=error_detail)
def convert_to_azure_payload(
url,
payload: dict,
):
model = payload.get("model", "")
# Filter allowed parameters based on Azure OpenAI API
def get_azure_allowed_params(api_version: str) -> set[str]:
allowed_params = {
"messages",
"temperature",
@@ -669,6 +664,23 @@ def convert_to_azure_payload(
"max_completion_tokens",
}
try:
if api_version >= "2024-09-01-preview":
allowed_params.add("stream_options")
except ValueError:
log.debug(
f"Invalid API version {api_version} for Azure OpenAI. Defaulting to allowed parameters."
)
return allowed_params
def convert_to_azure_payload(url, payload: dict, api_version: str):
model = payload.get("model", "")
# Filter allowed parameters based on Azure OpenAI API
allowed_params = get_azure_allowed_params(api_version)
# Special handling for o-series models
if model.startswith("o") and model.endswith("-mini"):
# Convert max_tokens to max_completion_tokens for o-series models
@@ -806,7 +818,7 @@ async def generate_chat_completion(
),
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -817,8 +829,8 @@ async def generate_chat_completion(
}
if api_config.get("azure", False):
request_url, payload = convert_to_azure_payload(url, payload)
api_version = api_config.get("api_version", "") or "2023-03-15-preview"
api_version = api_config.get("api_version", "2023-03-15-preview")
request_url, payload = convert_to_azure_payload(url, payload, api_version)
headers["api-key"] = key
headers["api-version"] = api_version
request_url = f"{request_url}/chat/completions?api-version={api_version}"
@@ -924,7 +936,7 @@ async def embeddings(request: Request, form_data: dict, user):
"Content-Type": "application/json",
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -996,7 +1008,7 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
"Content-Type": "application/json",
**(
{
"X-OpenWebUI-User-Name": user.name,
"X-OpenWebUI-User-Name": quote(user.name, safe=" "),
"X-OpenWebUI-User-Id": user.id,
"X-OpenWebUI-User-Email": user.email,
"X-OpenWebUI-User-Role": user.role,
@@ -1007,16 +1019,15 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
}
if api_config.get("azure", False):
api_version = api_config.get("api_version", "2023-03-15-preview")
headers["api-key"] = key
headers["api-version"] = (
api_config.get("api_version", "") or "2023-03-15-preview"
)
headers["api-version"] = api_version
payload = json.loads(body)
url, payload = convert_to_azure_payload(url, payload)
url, payload = convert_to_azure_payload(url, payload, api_version)
body = json.dumps(payload).encode()
request_url = f"{url}/{path}?api-version={api_config.get('api_version', '2023-03-15-preview')}"
request_url = f"{url}/{path}?api-version={api_version}"
else:
headers["Authorization"] = f"Bearer {key}"
request_url = f"{url}/{path}"
backend/open_webui/routers/retrieval.py
+66 -2
View File
@@ -29,6 +29,7 @@ import tiktoken
from langchain.text_splitter import RecursiveCharacterTextSplitter, TokenTextSplitter
from langchain_text_splitters import MarkdownHeaderTextSplitter
from langchain_core.documents import Document
from open_webui.models.files import FileModel, Files
@@ -1146,6 +1147,7 @@ def save_docs_to_vector_db(
chunk_overlap=request.app.state.config.CHUNK_OVERLAP,
add_start_index=True,
)
docs = text_splitter.split_documents(docs)
elif request.app.state.config.TEXT_SPLITTER == "token":
log.info(
f"Using token text splitter: {request.app.state.config.TIKTOKEN_ENCODING_NAME}"
@@ -1158,11 +1160,56 @@ def save_docs_to_vector_db(
chunk_overlap=request.app.state.config.CHUNK_OVERLAP,
add_start_index=True,
)
docs = text_splitter.split_documents(docs)
elif request.app.state.config.TEXT_SPLITTER == "markdown_header":
log.info("Using markdown header text splitter")
# Define headers to split on - covering most common markdown header levels
headers_to_split_on = [
("#", "Header 1"),
("##", "Header 2"),
("###", "Header 3"),
("####", "Header 4"),
("#####", "Header 5"),
("######", "Header 6"),
]
markdown_splitter = MarkdownHeaderTextSplitter(
headers_to_split_on=headers_to_split_on,
strip_headers=False, # Keep headers in content for context
)
md_split_docs = []
for doc in docs:
md_header_splits = markdown_splitter.split_text(doc.page_content)
text_splitter = RecursiveCharacterTextSplitter(
chunk_size=request.app.state.config.CHUNK_SIZE,
chunk_overlap=request.app.state.config.CHUNK_OVERLAP,
add_start_index=True,
)
md_header_splits = text_splitter.split_documents(md_header_splits)
# Convert back to Document objects, preserving original metadata
for split_chunk in md_header_splits:
headings_list = []
# Extract header values in order based on headers_to_split_on
for _, header_meta_key_name in headers_to_split_on:
if header_meta_key_name in split_chunk.metadata:
headings_list.append(
split_chunk.metadata[header_meta_key_name]
)
md_split_docs.append(
Document(
page_content=split_chunk.page_content,
metadata={**doc.metadata, "headings": headings_list},
)
)
docs = md_split_docs
else:
raise ValueError(ERROR_MESSAGES.DEFAULT("Invalid text splitter"))
docs = text_splitter.split_documents(docs)
if len(docs) == 0:
raise ValueError(ERROR_MESSAGES.EMPTY_CONTENT)
@@ -1747,6 +1794,16 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]:
)
else:
raise Exception("No TAVILY_API_KEY found in environment variables")
elif engine == "exa":
if request.app.state.config.EXA_API_KEY:
return search_exa(
request.app.state.config.EXA_API_KEY,
query,
request.app.state.config.WEB_SEARCH_RESULT_COUNT,
request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
)
else:
raise Exception("No EXA_API_KEY found in environment variables")
elif engine == "searchapi":
if request.app.state.config.SEARCHAPI_API_KEY:
return search_searchapi(
@@ -1784,6 +1841,13 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]:
request.app.state.config.WEB_SEARCH_RESULT_COUNT,
request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
)
elif engine == "exa":
return search_exa(
request.app.state.config.EXA_API_KEY,
query,
request.app.state.config.WEB_SEARCH_RESULT_COUNT,
request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST,
)
elif engine == "perplexity":
return search_perplexity(
request.app.state.config.PERPLEXITY_API_KEY,
backend/open_webui/routers/tools.py
+1 -1
View File
@@ -153,7 +153,7 @@ async def load_tool_from_url(
)
try:
async with aiohttp.ClientSession() as session:
async with aiohttp.ClientSession(trust_env=True) as session:
async with session.get(
url, headers={"Content-Type": "application/json"}
) as resp: