refac: byebye litellm

This commit is contained in:
Timothy J. Baek 2024-05-25 14:43:35 -07:00
parent 50951459c9
commit 79f440f302
13 changed files with 14 additions and 808 deletions

View File

@ -11,7 +11,3 @@ OPENAI_API_KEY=''
SCARF_NO_ANALYTICS=true
DO_NOT_TRACK=true
ANONYMIZED_TELEMETRY=false
# Use locally bundled version of the LiteLLM cost map json
# to avoid repetitive startup connections
LITELLM_LOCAL_MODEL_COST_MAP="True"

View File

@ -59,11 +59,6 @@ ENV OPENAI_API_KEY="" \
DO_NOT_TRACK=true \
ANONYMIZED_TELEMETRY=false
# Use locally bundled version of the LiteLLM cost map json
# to avoid repetitive startup connections
ENV LITELLM_LOCAL_MODEL_COST_MAP="True"
#### Other models #########################################################
## whisper TTS model settings ##
ENV WHISPER_MODEL="base" \

View File

@ -1,388 +0,0 @@
import sys
from contextlib import asynccontextmanager
from fastapi import FastAPI, Depends, HTTPException
from fastapi.routing import APIRoute
from fastapi.middleware.cors import CORSMiddleware
import logging
from fastapi import FastAPI, Request, Depends, status, Response
from fastapi.responses import JSONResponse
from starlette.middleware.base import BaseHTTPMiddleware, RequestResponseEndpoint
from starlette.responses import StreamingResponse
import json
import time
import requests
from pydantic import BaseModel, ConfigDict
from typing import Optional, List
from apps.web.models.models import Models
from utils.utils import get_verified_user, get_current_user, get_admin_user
from config import SRC_LOG_LEVELS
from constants import MESSAGES
import os
log = logging.getLogger(__name__)
log.setLevel(SRC_LOG_LEVELS["LITELLM"])
from config import (
ENABLE_LITELLM,
ENABLE_MODEL_FILTER,
MODEL_FILTER_LIST,
DATA_DIR,
LITELLM_PROXY_PORT,
LITELLM_PROXY_HOST,
)
import warnings
warnings.simplefilter("ignore")
from litellm.utils import get_llm_provider
import asyncio
import subprocess
import yaml
@asynccontextmanager
async def lifespan(app: FastAPI):
log.info("startup_event")
# TODO: Check config.yaml file and create one
asyncio.create_task(start_litellm_background())
yield
app = FastAPI(lifespan=lifespan)
origins = ["*"]
app.add_middleware(
CORSMiddleware,
allow_origins=origins,
allow_credentials=True,
allow_methods=["*"],
allow_headers=["*"],
)
LITELLM_CONFIG_DIR = f"{DATA_DIR}/litellm/config.yaml"
with open(LITELLM_CONFIG_DIR, "r") as file:
litellm_config = yaml.safe_load(file)
app.state.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER.value
app.state.MODEL_FILTER_LIST = MODEL_FILTER_LIST.value
app.state.MODEL_CONFIG = Models.get_all_models()
app.state.ENABLE = ENABLE_LITELLM
app.state.CONFIG = litellm_config
# Global variable to store the subprocess reference
background_process = None
CONFLICT_ENV_VARS = [
# Uvicorn uses PORT, so LiteLLM might use it as well
"PORT",
# LiteLLM uses DATABASE_URL for Prisma connections
"DATABASE_URL",
]
async def run_background_process(command):
global background_process
log.info("run_background_process")
try:
# Log the command to be executed
log.info(f"Executing command: {command}")
# Filter environment variables known to conflict with litellm
env = {k: v for k, v in os.environ.items() if k not in CONFLICT_ENV_VARS}
# Execute the command and create a subprocess
process = await asyncio.create_subprocess_exec(
*command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, env=env
)
background_process = process
log.info("Subprocess started successfully.")
# Capture STDERR for debugging purposes
stderr_output = await process.stderr.read()
stderr_text = stderr_output.decode().strip()
if stderr_text:
log.info(f"Subprocess STDERR: {stderr_text}")
# log.info output line by line
async for line in process.stdout:
log.info(line.decode().strip())
# Wait for the process to finish
returncode = await process.wait()
log.info(f"Subprocess exited with return code {returncode}")
except Exception as e:
log.error(f"Failed to start subprocess: {e}")
raise # Optionally re-raise the exception if you want it to propagate
async def start_litellm_background():
log.info("start_litellm_background")
# Command to run in the background
command = [
"litellm",
"--port",
str(LITELLM_PROXY_PORT),
"--host",
LITELLM_PROXY_HOST,
"--telemetry",
"False",
"--config",
LITELLM_CONFIG_DIR,
]
await run_background_process(command)
async def shutdown_litellm_background():
log.info("shutdown_litellm_background")
global background_process
if background_process:
background_process.terminate()
await background_process.wait() # Ensure the process has terminated
log.info("Subprocess terminated")
background_process = None
@app.get("/")
async def get_status():
return {"status": True}
async def restart_litellm():
"""
Endpoint to restart the litellm background service.
"""
log.info("Requested restart of litellm service.")
try:
# Shut down the existing process if it is running
await shutdown_litellm_background()
log.info("litellm service shutdown complete.")
# Restart the background service
asyncio.create_task(start_litellm_background())
log.info("litellm service restart complete.")
return {
"status": "success",
"message": "litellm service restarted successfully.",
}
except Exception as e:
log.info(f"Error restarting litellm service: {e}")
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(e)
)
@app.get("/restart")
async def restart_litellm_handler(user=Depends(get_admin_user)):
return await restart_litellm()
@app.get("/config")
async def get_config(user=Depends(get_admin_user)):
return app.state.CONFIG
class LiteLLMConfigForm(BaseModel):
general_settings: Optional[dict] = None
litellm_settings: Optional[dict] = None
model_list: Optional[List[dict]] = None
router_settings: Optional[dict] = None
model_config = ConfigDict(protected_namespaces=())
@app.post("/config/update")
async def update_config(form_data: LiteLLMConfigForm, user=Depends(get_admin_user)):
app.state.CONFIG = form_data.model_dump(exclude_none=True)
with open(LITELLM_CONFIG_DIR, "w") as file:
yaml.dump(app.state.CONFIG, file)
await restart_litellm()
return app.state.CONFIG
@app.get("/models")
@app.get("/v1/models")
async def get_models(user=Depends(get_current_user)):
if app.state.ENABLE:
while not background_process:
await asyncio.sleep(0.1)
url = f"http://localhost:{LITELLM_PROXY_PORT}/v1"
r = None
try:
r = requests.request(method="GET", url=f"{url}/models")
r.raise_for_status()
data = r.json()
if app.state.ENABLE_MODEL_FILTER:
if user and user.role == "user":
data["data"] = list(
filter(
lambda model: model["id"] in app.state.MODEL_FILTER_LIST,
data["data"],
)
)
return data
except Exception as e:
log.exception(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}"
return {
"data": [
{
"id": model["model_name"],
"object": "model",
"created": int(time.time()),
"owned_by": "openai",
"custom_info": next(
(
item
for item in app.state.MODEL_CONFIG
if item.id == model["model_name"]
),
None,
),
}
for model in app.state.CONFIG["model_list"]
],
"object": "list",
}
else:
return {
"data": [],
"object": "list",
}
@app.get("/model/info")
async def get_model_list(user=Depends(get_admin_user)):
return {"data": app.state.CONFIG["model_list"]}
class AddLiteLLMModelForm(BaseModel):
model_name: str
litellm_params: dict
model_config = ConfigDict(protected_namespaces=())
@app.post("/model/new")
async def add_model_to_config(
form_data: AddLiteLLMModelForm, user=Depends(get_admin_user)
):
try:
get_llm_provider(model=form_data.model_name)
app.state.CONFIG["model_list"].append(form_data.model_dump())
with open(LITELLM_CONFIG_DIR, "w") as file:
yaml.dump(app.state.CONFIG, file)
await restart_litellm()
return {"message": MESSAGES.MODEL_ADDED(form_data.model_name)}
except Exception as e:
print(e)
raise HTTPException(
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, detail=str(e)
)
class DeleteLiteLLMModelForm(BaseModel):
id: str
@app.post("/model/delete")
async def delete_model_from_config(
form_data: DeleteLiteLLMModelForm, user=Depends(get_admin_user)
):
app.state.CONFIG["model_list"] = [
model
for model in app.state.CONFIG["model_list"]
if model["model_name"] != form_data.id
]
with open(LITELLM_CONFIG_DIR, "w") as file:
yaml.dump(app.state.CONFIG, file)
await restart_litellm()
return {"message": MESSAGES.MODEL_DELETED(form_data.id)}
@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
body = await request.body()
url = f"http://localhost:{LITELLM_PROXY_PORT}"
target_url = f"{url}/{path}"
headers = {}
# headers["Authorization"] = f"Bearer {key}"
headers["Content-Type"] = "application/json"
r = None
try:
r = requests.request(
method=request.method,
url=target_url,
data=body,
headers=headers,
stream=True,
)
r.raise_for_status()
# Check if response is SSE
if "text/event-stream" in r.headers.get("Content-Type", ""):
return StreamingResponse(
r.iter_content(chunk_size=8192),
status_code=r.status_code,
headers=dict(r.headers),
)
else:
response_data = r.json()
return response_data
except Exception as e:
log.exception(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']['message'] if 'message' in res['error'] else res['error']}"
except:
error_detail = f"External: {e}"
raise HTTPException(
status_code=r.status_code if r else 500, detail=error_detail
)

View File

@ -1,144 +0,0 @@
################################################################################
# DEPRECATION NOTICE #
# #
# This file has been deprecated since version 0.2.0. #
# #
################################################################################
from pydantic import BaseModel
from peewee import *
from playhouse.shortcuts import model_to_dict
from typing import List, Union, Optional
import time
from utils.utils import decode_token
from utils.misc import get_gravatar_url
from apps.web.internal.db import DB
import json
####################
# Modelfile DB Schema
####################
class Modelfile(Model):
tag_name = CharField(unique=True)
user_id = CharField()
modelfile = TextField()
timestamp = BigIntegerField()
class Meta:
database = DB
class ModelfileModel(BaseModel):
tag_name: str
user_id: str
modelfile: str
timestamp: int # timestamp in epoch
####################
# Forms
####################
class ModelfileForm(BaseModel):
modelfile: dict
class ModelfileTagNameForm(BaseModel):
tag_name: str
class ModelfileUpdateForm(ModelfileForm, ModelfileTagNameForm):
pass
class ModelfileResponse(BaseModel):
tag_name: str
user_id: str
modelfile: dict
timestamp: int # timestamp in epoch
class ModelfilesTable:
def __init__(self, db):
self.db = db
self.db.create_tables([Modelfile])
def insert_new_modelfile(
self, user_id: str, form_data: ModelfileForm
) -> Optional[ModelfileModel]:
if "tagName" in form_data.modelfile:
modelfile = ModelfileModel(
**{
"user_id": user_id,
"tag_name": form_data.modelfile["tagName"],
"modelfile": json.dumps(form_data.modelfile),
"timestamp": int(time.time()),
}
)
try:
result = Modelfile.create(**modelfile.model_dump())
if result:
return modelfile
else:
return None
except:
return None
else:
return None
def get_modelfile_by_tag_name(self, tag_name: str) -> Optional[ModelfileModel]:
try:
modelfile = Modelfile.get(Modelfile.tag_name == tag_name)
return ModelfileModel(**model_to_dict(modelfile))
except:
return None
def get_modelfiles(self, skip: int = 0, limit: int = 50) -> List[ModelfileResponse]:
return [
ModelfileResponse(
**{
**model_to_dict(modelfile),
"modelfile": json.loads(modelfile.modelfile),
}
)
for modelfile in Modelfile.select()
# .limit(limit).offset(skip)
]
def update_modelfile_by_tag_name(
self, tag_name: str, modelfile: dict
) -> Optional[ModelfileModel]:
try:
query = Modelfile.update(
modelfile=json.dumps(modelfile),
timestamp=int(time.time()),
).where(Modelfile.tag_name == tag_name)
query.execute()
modelfile = Modelfile.get(Modelfile.tag_name == tag_name)
return ModelfileModel(**model_to_dict(modelfile))
except:
return None
def delete_modelfile_by_tag_name(self, tag_name: str) -> bool:
try:
query = Modelfile.delete().where((Modelfile.tag_name == tag_name))
query.execute() # Remove the rows, return number of rows removed.
return True
except:
return False
Modelfiles = ModelfilesTable(DB)

View File

@ -56,7 +56,6 @@ log_sources = [
"CONFIG",
"DB",
"IMAGES",
"LITELLM",
"MAIN",
"MODELS",
"OLLAMA",
@ -374,10 +373,10 @@ def create_config_file(file_path):
LITELLM_CONFIG_PATH = f"{DATA_DIR}/litellm/config.yaml"
if not os.path.exists(LITELLM_CONFIG_PATH):
log.info("Config file doesn't exist. Creating...")
create_config_file(LITELLM_CONFIG_PATH)
log.info("Config file created successfully.")
# if not os.path.exists(LITELLM_CONFIG_PATH):
# log.info("Config file doesn't exist. Creating...")
# create_config_file(LITELLM_CONFIG_PATH)
# log.info("Config file created successfully.")
####################################
@ -826,18 +825,6 @@ AUDIO_OPENAI_API_VOICE = PersistentConfig(
os.getenv("AUDIO_OPENAI_API_VOICE", "alloy"),
)
####################################
# LiteLLM
####################################
ENABLE_LITELLM = os.environ.get("ENABLE_LITELLM", "True").lower() == "true"
LITELLM_PROXY_PORT = int(os.getenv("LITELLM_PROXY_PORT", "14365"))
if LITELLM_PROXY_PORT < 0 or LITELLM_PROXY_PORT > 65535:
raise ValueError("Invalid port number for LITELLM_PROXY_PORT")
LITELLM_PROXY_HOST = os.getenv("LITELLM_PROXY_HOST", "127.0.0.1")
####################################
# Database

View File

@ -22,13 +22,6 @@ from starlette.responses import StreamingResponse, Response
from apps.ollama.main import app as ollama_app, get_all_models as get_ollama_models
from apps.openai.main import app as openai_app, get_all_models as get_openai_models
from apps.litellm.main import (
app as litellm_app,
start_litellm_background,
shutdown_litellm_background,
)
from apps.audio.main import app as audio_app
from apps.images.main import app as images_app
from apps.rag.main import app as rag_app
@ -55,7 +48,6 @@ from config import (
STATIC_DIR,
ENABLE_OPENAI_API,
ENABLE_OLLAMA_API,
ENABLE_LITELLM,
ENABLE_MODEL_FILTER,
MODEL_FILTER_LIST,
GLOBAL_LOG_LEVEL,
@ -100,11 +92,7 @@ https://github.com/open-webui/open-webui
@asynccontextmanager
async def lifespan(app: FastAPI):
if ENABLE_LITELLM:
asyncio.create_task(start_litellm_background())
yield
if ENABLE_LITELLM:
await shutdown_litellm_background()
app = FastAPI(
@ -262,9 +250,6 @@ async def update_embedding_function(request: Request, call_next):
return response
# TODO: Deprecate LiteLLM
app.mount("/litellm/api", litellm_app)
app.mount("/ollama", ollama_app)
app.mount("/openai", openai_app)
@ -407,9 +392,6 @@ async def update_model_filter_config(
openai_app.state.config.ENABLE_MODEL_FILTER = app.state.config.ENABLE_MODEL_FILTER
openai_app.state.config.MODEL_FILTER_LIST = app.state.config.MODEL_FILTER_LIST
litellm_app.state.ENABLE_MODEL_FILTER = app.state.config.ENABLE_MODEL_FILTER
litellm_app.state.MODEL_FILTER_LIST = app.state.config.MODEL_FILTER_LIST
return {
"enabled": app.state.config.ENABLE_MODEL_FILTER,
"models": app.state.config.MODEL_FILTER_LIST,

View File

@ -18,8 +18,6 @@ psycopg2-binary==2.9.9
PyMySQL==1.1.1
bcrypt==4.1.3
litellm[proxy]==1.37.20
boto3==1.34.110
argon2-cffi==23.1.0

View File

@ -1,43 +0,0 @@
litellm_settings:
drop_params: true
model_list:
- model_name: 'HuggingFace: Mistral: Mistral 7B Instruct v0.1'
litellm_params:
model: huggingface/mistralai/Mistral-7B-Instruct-v0.1
api_key: os.environ/HF_TOKEN
max_tokens: 1024
- model_name: 'HuggingFace: Mistral: Mistral 7B Instruct v0.2'
litellm_params:
model: huggingface/mistralai/Mistral-7B-Instruct-v0.2
api_key: os.environ/HF_TOKEN
max_tokens: 1024
- model_name: 'HuggingFace: Meta: Llama 3 8B Instruct'
litellm_params:
model: huggingface/meta-llama/Meta-Llama-3-8B-Instruct
api_key: os.environ/HF_TOKEN
max_tokens: 2047
- model_name: 'HuggingFace: Mistral: Mixtral 8x7B Instruct v0.1'
litellm_params:
model: huggingface/mistralai/Mixtral-8x7B-Instruct-v0.1
api_key: os.environ/HF_TOKEN
max_tokens: 8192
- model_name: 'HuggingFace: Microsoft: Phi-3 Mini-4K-Instruct'
litellm_params:
model: huggingface/microsoft/Phi-3-mini-4k-instruct
api_key: os.environ/HF_TOKEN
max_tokens: 1024
- model_name: 'HuggingFace: Google: Gemma 7B 1.1'
litellm_params:
model: huggingface/google/gemma-1.1-7b-it
api_key: os.environ/HF_TOKEN
max_tokens: 1024
- model_name: 'HuggingFace: Yi-1.5 34B Chat'
litellm_params:
model: huggingface/01-ai/Yi-1.5-34B-Chat
api_key: os.environ/HF_TOKEN
max_tokens: 1024
- model_name: 'HuggingFace: Nous Research: Nous Hermes 2 Mixtral 8x7B DPO'
litellm_params:
model: huggingface/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
api_key: os.environ/HF_TOKEN
max_tokens: 2048

View File

@ -34,11 +34,6 @@ fi
# Check if SPACE_ID is set, if so, configure for space
if [ -n "$SPACE_ID" ]; then
echo "Configuring for HuggingFace Space deployment"
# Copy litellm_config.yaml with specified ownership
echo "Copying litellm_config.yaml to the desired location with specified ownership..."
cp -f ./space/litellm_config.yaml ./data/litellm/config.yaml
if [ -n "$ADMIN_USER_EMAIL" ] && [ -n "$ADMIN_USER_PASSWORD" ]; then
echo "Admin user configured, creating"
WEBUI_SECRET_KEY="$WEBUI_SECRET_KEY" uvicorn main:app --host "$HOST" --port "$PORT" --forwarded-allow-ips '*' &

View File

@ -1,151 +0,0 @@
import { LITELLM_API_BASE_URL } from '$lib/constants';
export const getLiteLLMModels = async (token: string = '') => {
let error = null;
const res = await fetch(`${LITELLM_API_BASE_URL}/v1/models`, {
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);
error = `LiteLLM: ${err?.error?.message ?? 'Network Problem'}`;
return [];
});
if (error) {
throw error;
}
const models = Array.isArray(res) ? res : res?.data ?? null;
return models
? models
.map((model) => ({
id: model.id,
name: model.name ?? model.id,
external: true,
source: 'LiteLLM',
custom_info: model.custom_info
}))
.sort((a, b) => {
return a.name.localeCompare(b.name);
})
: models;
};
export const getLiteLLMModelInfo = async (token: string = '') => {
let error = null;
const res = await fetch(`${LITELLM_API_BASE_URL}/model/info`, {
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);
error = `LiteLLM: ${err?.error?.message ?? 'Network Problem'}`;
return [];
});
if (error) {
throw error;
}
const models = Array.isArray(res) ? res : res?.data ?? null;
return models;
};
type AddLiteLLMModelForm = {
name: string;
model: string;
api_base: string;
api_key: string;
rpm: string;
max_tokens: string;
};
export const addLiteLLMModel = async (token: string = '', payload: AddLiteLLMModelForm) => {
let error = null;
const res = await fetch(`${LITELLM_API_BASE_URL}/model/new`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
},
body: JSON.stringify({
model_name: payload.name,
litellm_params: {
model: payload.model,
...(payload.api_base === '' ? {} : { api_base: payload.api_base }),
...(payload.api_key === '' ? {} : { api_key: payload.api_key }),
...(isNaN(parseInt(payload.rpm)) ? {} : { rpm: parseInt(payload.rpm) }),
...(payload.max_tokens === '' ? {} : { max_tokens: payload.max_tokens })
}
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = `LiteLLM: ${err?.error?.message ?? 'Network Problem'}`;
return [];
});
if (error) {
throw error;
}
return res;
};
export const deleteLiteLLMModel = async (token: string = '', id: string) => {
let error = null;
const res = await fetch(`${LITELLM_API_BASE_URL}/model/delete`, {
method: 'POST',
headers: {
Accept: 'application/json',
'Content-Type': 'application/json',
...(token && { authorization: `Bearer ${token}` })
},
body: JSON.stringify({
id: id
})
})
.then(async (res) => {
if (!res.ok) throw await res.json();
return res.json();
})
.catch((err) => {
console.log(err);
error = `LiteLLM: ${err?.error?.message ?? 'Network Problem'}`;
return [];
});
if (error) {
throw error;
}
return res;
};

View File

@ -35,12 +35,7 @@
import MessageInput from '$lib/components/chat/MessageInput.svelte';
import Messages from '$lib/components/chat/Messages.svelte';
import Navbar from '$lib/components/layout/Navbar.svelte';
import {
LITELLM_API_BASE_URL,
OLLAMA_API_BASE_URL,
OPENAI_API_BASE_URL,
WEBUI_BASE_URL
} from '$lib/constants';
import { OLLAMA_API_BASE_URL, OPENAI_API_BASE_URL, WEBUI_BASE_URL } from '$lib/constants';
import { createOpenAITextStream } from '$lib/apis/streaming';
import { queryMemory } from '$lib/apis/memories';
import type { Writable } from 'svelte/store';
@ -733,9 +728,7 @@
docs: docs.length > 0 ? docs : undefined,
citations: docs.length > 0
},
model?.source?.toLowerCase() === 'litellm'
? `${LITELLM_API_BASE_URL}/v1`
: `${OPENAI_API_BASE_URL}`
`${OPENAI_API_BASE_URL}`
);
// Wait until history/message have been updated

View File

@ -5,12 +5,7 @@
import { toast } from 'svelte-sonner';
import {
LITELLM_API_BASE_URL,
OLLAMA_API_BASE_URL,
OPENAI_API_BASE_URL,
WEBUI_API_BASE_URL
} from '$lib/constants';
import { OLLAMA_API_BASE_URL, OPENAI_API_BASE_URL, WEBUI_API_BASE_URL } from '$lib/constants';
import { WEBUI_NAME, config, user, models, settings } from '$lib/stores';
import { cancelOllamaRequest, generateChatCompletion } from '$lib/apis/ollama';
@ -79,11 +74,7 @@
}
]
},
model.external
? model.source === 'litellm'
? `${LITELLM_API_BASE_URL}/v1`
: `${OPENAI_API_BASE_URL}`
: `${OLLAMA_API_BASE_URL}/v1`
model?.owned_by === 'openai' ? `${OPENAI_API_BASE_URL}` : `${OLLAMA_API_BASE_URL}/v1`
);
if (res && res.ok) {
@ -150,11 +141,7 @@
...messages
].filter((message) => message)
},
model.external
? model.source === 'litellm'
? `${LITELLM_API_BASE_URL}/v1`
: `${OPENAI_API_BASE_URL}`
: `${OLLAMA_API_BASE_URL}/v1`
model?.owned_by === 'openai' ? `${OPENAI_API_BASE_URL}` : `${OLLAMA_API_BASE_URL}/v1`
);
let responseMessage;

View File

@ -6,7 +6,6 @@ export const WEBUI_BASE_URL = browser ? (dev ? `http://${location.hostname}:8080
export const WEBUI_API_BASE_URL = `${WEBUI_BASE_URL}/api/v1`;
export const LITELLM_API_BASE_URL = `${WEBUI_BASE_URL}/litellm/api`;
export const OLLAMA_API_BASE_URL = `${WEBUI_BASE_URL}/ollama`;
export const OPENAI_API_BASE_URL = `${WEBUI_BASE_URL}/openai`;
export const AUDIO_API_BASE_URL = `${WEBUI_BASE_URL}/audio/api/v1`;