GitHub deploy: 1b2ae7bb77153abb65fb1a02dbc696e08cf470a1

.github/workflows/integration-test.yml

@@ -15,13 +15,6 @@ jobs:
     name: Run Cypress Integration Tests
     runs-on: ubuntu-latest
     steps:
-      - name: Maximize build space
-        uses: AdityaGarg8/[email protected]
-        with:
-          remove-android: 'true'
-          remove-haskell: 'true'
-          remove-codeql: 'true'
-
       - name: Checkout Repository
         uses: actions/checkout@v4
 

backend/apps/images/main.py

@@ -150,11 +150,10 @@ async def update_engine_url(
     else:
         url = form_data.AUTOMATIC1111_BASE_URL.strip("/")
         try:
-            r = requests.head(url)
-            r.raise_for_status()
+            r = requests.head(url) 
             app.state.config.AUTOMATIC1111_BASE_URL = url
         except Exception as e:
-            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.INVALID_URL)
+            raise HTTPException(status_code=400, detail="Invalid URL provided.")
 
     if form_data.COMFYUI_BASE_URL == None:
         app.state.config.COMFYUI_BASE_URL = COMFYUI_BASE_URL
@@ -163,10 +162,9 @@ async def update_engine_url(
 
         try:
             r = requests.head(url)
-            r.raise_for_status()
             app.state.config.COMFYUI_BASE_URL = url
         except Exception as e:
-            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.INVALID_URL)
+            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
 
     if form_data.AUTOMATIC1111_API_AUTH == None:
         app.state.config.AUTOMATIC1111_API_AUTH = AUTOMATIC1111_API_AUTH

backend/apps/images/utils/comfyui.py

@@ -1,5 +1,6 @@
 import asyncio
 import websocket  # NOTE: websocket-client (https://github.com/websocket-client/websocket-client)
+import uuid
 import json
 import urllib.request
 import urllib.parse
@@ -397,9 +398,7 @@ async def comfyui_generate_image(
         return None
 
     try:
-        images = await asyncio.to_thread(
-            get_images, ws, comfyui_prompt, client_id, base_url
-        )
+        images = await asyncio.to_thread(get_images, ws, comfyui_prompt, client_id, base_url)
     except Exception as e:
         log.exception(f"Error while receiving images: {e}")
         images = None

backend/apps/ollama/main.py

@@ -1,21 +1,27 @@
 from fastapi import (
     FastAPI,
     Request,
+    Response,
     HTTPException,
     Depends,
+    status,
     UploadFile,
     File,
+    BackgroundTasks,
 )
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import StreamingResponse
+from fastapi.concurrency import run_in_threadpool
 
 from pydantic import BaseModel, ConfigDict
 
 import os
 import re
+import copy
 import random
 import requests
 import json
+import uuid
 import aiohttp
 import asyncio
 import logging
@@ -26,11 +32,16 @@ from typing import Optional, List, Union
 from starlette.background import BackgroundTask
 
 from apps.webui.models.models import Models
+from apps.webui.models.users import Users
 from constants import ERROR_MESSAGES
 from utils.utils import (
+    decode_token,
+    get_current_user,
     get_verified_user,
     get_admin_user,
 )
+from utils.task import prompt_template
+
 
 from config import (
     SRC_LOG_LEVELS,
@@ -42,12 +53,7 @@ from config import (
     UPLOAD_DIR,
     AppConfig,
 )
-from utils.misc import (
-    calculate_sha256,
-    apply_model_params_to_body_ollama,
-    apply_model_params_to_body_openai,
-    apply_model_system_prompt_to_body,
-)
+from utils.misc import calculate_sha256, add_or_update_system_message
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["OLLAMA"])
@@ -177,7 +183,7 @@ async def post_streaming_url(url: str, payload: str, stream: bool = True):
                 res = await r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except Exception:
+            except:
                 error_detail = f"Ollama: {e}"
 
         raise HTTPException(
@@ -232,7 +238,7 @@ async def get_all_models():
 async def get_ollama_tags(
     url_idx: Optional[int] = None, user=Depends(get_verified_user)
 ):
-    if url_idx is None:
+    if url_idx == None:
         models = await get_all_models()
 
         if app.state.config.ENABLE_MODEL_FILTER:
@@ -263,7 +269,7 @@ async def get_ollama_tags(
                     res = r.json()
                     if "error" in res:
                         error_detail = f"Ollama: {res['error']}"
-                except Exception:
+                except:
                     error_detail = f"Ollama: {e}"
 
             raise HTTPException(
@@ -276,7 +282,8 @@ async def get_ollama_tags(
 @app.get("/api/version/{url_idx}")
 async def get_ollama_versions(url_idx: Optional[int] = None):
     if app.state.config.ENABLE_OLLAMA_API:
-        if url_idx is None:
+        if url_idx == None:
+
             # returns lowest version
             tasks = [
                 fetch_url(f"{url}/api/version")
@@ -316,7 +323,7 @@ async def get_ollama_versions(url_idx: Optional[int] = None):
                         res = r.json()
                         if "error" in res:
                             error_detail = f"Ollama: {res['error']}"
-                    except Exception:
+                    except:
                         error_detail = f"Ollama: {e}"
 
                 raise HTTPException(
@@ -339,6 +346,8 @@ async def pull_model(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
+    r = None
+
     # Admin should be able to pull models from any source
     payload = {**form_data.model_dump(exclude_none=True), "insecure": True}
 
@@ -358,7 +367,7 @@ async def push_model(
     url_idx: Optional[int] = None,
     user=Depends(get_admin_user),
 ):
-    if url_idx is None:
+    if url_idx == None:
         if form_data.name in app.state.MODELS:
             url_idx = app.state.MODELS[form_data.name]["urls"][0]
         else:
@@ -408,7 +417,7 @@ async def copy_model(
     url_idx: Optional[int] = None,
     user=Depends(get_admin_user),
 ):
-    if url_idx is None:
+    if url_idx == None:
         if form_data.source in app.state.MODELS:
             url_idx = app.state.MODELS[form_data.source]["urls"][0]
         else:
@@ -419,13 +428,13 @@ async def copy_model(
 
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
-    r = requests.request(
-        method="POST",
-        url=f"{url}/api/copy",
-        data=form_data.model_dump_json(exclude_none=True).encode(),
-    )
 
     try:
+        r = requests.request(
+            method="POST",
+            url=f"{url}/api/copy",
+            data=form_data.model_dump_json(exclude_none=True).encode(),
+        )
         r.raise_for_status()
 
         log.debug(f"r.text: {r.text}")
@@ -439,7 +448,7 @@ async def copy_model(
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except Exception:
+            except:
                 error_detail = f"Ollama: {e}"
 
         raise HTTPException(
@@ -455,7 +464,7 @@ async def delete_model(
     url_idx: Optional[int] = None,
     user=Depends(get_admin_user),
 ):
-    if url_idx is None:
+    if url_idx == None:
         if form_data.name in app.state.MODELS:
             url_idx = app.state.MODELS[form_data.name]["urls"][0]
         else:
@@ -467,12 +476,12 @@ async def delete_model(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
-    r = requests.request(
-        method="DELETE",
-        url=f"{url}/api/delete",
-        data=form_data.model_dump_json(exclude_none=True).encode(),
-    )
     try:
+        r = requests.request(
+            method="DELETE",
+            url=f"{url}/api/delete",
+            data=form_data.model_dump_json(exclude_none=True).encode(),
+        )
         r.raise_for_status()
 
         log.debug(f"r.text: {r.text}")
@@ -486,7 +495,7 @@ async def delete_model(
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except Exception:
+            except:
                 error_detail = f"Ollama: {e}"
 
         raise HTTPException(
@@ -507,12 +516,12 @@ async def show_model_info(form_data: ModelNameForm, user=Depends(get_verified_us
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
-    r = requests.request(
-        method="POST",
-        url=f"{url}/api/show",
-        data=form_data.model_dump_json(exclude_none=True).encode(),
-    )
     try:
+        r = requests.request(
+            method="POST",
+            url=f"{url}/api/show",
+            data=form_data.model_dump_json(exclude_none=True).encode(),
+        )
         r.raise_for_status()
 
         return r.json()
@@ -524,7 +533,7 @@ async def show_model_info(form_data: ModelNameForm, user=Depends(get_verified_us
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except Exception:
+            except:
                 error_detail = f"Ollama: {e}"
 
         raise HTTPException(
@@ -547,7 +556,7 @@ async def generate_embeddings(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-    if url_idx is None:
+    if url_idx == None:
         model = form_data.model
 
         if ":" not in model:
@@ -564,12 +573,12 @@ async def generate_embeddings(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
-    r = requests.request(
-        method="POST",
-        url=f"{url}/api/embeddings",
-        data=form_data.model_dump_json(exclude_none=True).encode(),
-    )
     try:
+        r = requests.request(
+            method="POST",
+            url=f"{url}/api/embeddings",
+            data=form_data.model_dump_json(exclude_none=True).encode(),
+        )
         r.raise_for_status()
 
         return r.json()
@@ -581,7 +590,7 @@ async def generate_embeddings(
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except Exception:
+            except:
                 error_detail = f"Ollama: {e}"
 
         raise HTTPException(
@@ -594,9 +603,10 @@ def generate_ollama_embeddings(
     form_data: GenerateEmbeddingsForm,
     url_idx: Optional[int] = None,
 ):
+
     log.info(f"generate_ollama_embeddings {form_data}")
 
-    if url_idx is None:
+    if url_idx == None:
         model = form_data.model
 
         if ":" not in model:
@@ -613,12 +623,12 @@ def generate_ollama_embeddings(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
-    r = requests.request(
-        method="POST",
-        url=f"{url}/api/embeddings",
-        data=form_data.model_dump_json(exclude_none=True).encode(),
-    )
     try:
+        r = requests.request(
+            method="POST",
+            url=f"{url}/api/embeddings",
+            data=form_data.model_dump_json(exclude_none=True).encode(),
+        )
         r.raise_for_status()
 
         data = r.json()
@@ -628,7 +638,7 @@ def generate_ollama_embeddings(
         if "embedding" in data:
             return data["embedding"]
         else:
-            raise Exception("Something went wrong :/")
+            raise "Something went wrong :/"
     except Exception as e:
         log.exception(e)
         error_detail = "Open WebUI: Server Connection Error"
@@ -637,10 +647,10 @@ def generate_ollama_embeddings(
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except Exception:
+            except:
                 error_detail = f"Ollama: {e}"
 
-        raise Exception(error_detail)
+        raise error_detail
 
 
 class GenerateCompletionForm(BaseModel):
@@ -664,7 +674,8 @@ async def generate_completion(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-    if url_idx is None:
+
+    if url_idx == None:
         model = form_data.model
 
         if ":" not in model:
@@ -702,18 +713,6 @@ class GenerateChatCompletionForm(BaseModel):
     keep_alive: Optional[Union[int, str]] = None
 
 
-def get_ollama_url(url_idx: Optional[int], model: str):
-    if url_idx is None:
-        if model not in app.state.MODELS:
-            raise HTTPException(
-                status_code=400,
-                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(model),
-            )
-        url_idx = random.choice(app.state.MODELS[model]["urls"])
-    url = app.state.config.OLLAMA_BASE_URLS[url_idx]
-    return url
-
-
 @app.post("/api/chat")
 @app.post("/api/chat/{url_idx}")
 async def generate_chat_completion(
@@ -721,7 +720,12 @@ async def generate_chat_completion(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-    log.debug(f"{form_data.model_dump_json(exclude_none=True).encode()}=")
+
+    log.debug(
+        "form_data.model_dump_json(exclude_none=True).encode(): {0} ".format(
+            form_data.model_dump_json(exclude_none=True).encode()
+        )
+    )
 
     payload = {
         **form_data.model_dump(exclude_none=True, exclude=["metadata"]),
@@ -736,21 +740,185 @@ async def generate_chat_completion(
         if model_info.base_model_id:
             payload["model"] = model_info.base_model_id
 
-        params = model_info.params.model_dump()
+        model_info.params = model_info.params.model_dump()
 
-        if params:
+        if model_info.params:
             if payload.get("options") is None:
                 payload["options"] = {}
 
-            payload["options"] = apply_model_params_to_body_ollama(
-                params, payload["options"]
+            if (
+                model_info.params.get("mirostat", None)
+                and payload["options"].get("mirostat") is None
+            ):
+                payload["options"]["mirostat"] = model_info.params.get("mirostat", None)
+
+            if (
+                model_info.params.get("mirostat_eta", None)
+                and payload["options"].get("mirostat_eta") is None
+            ):
+                payload["options"]["mirostat_eta"] = model_info.params.get(
+                    "mirostat_eta", None
+                )
+
+            if (
+                model_info.params.get("mirostat_tau", None)
+                and payload["options"].get("mirostat_tau") is None
+            ):
+                payload["options"]["mirostat_tau"] = model_info.params.get(
+                    "mirostat_tau", None
+                )
+
+            if (
+                model_info.params.get("num_ctx", None)
+                and payload["options"].get("num_ctx") is None
+            ):
+                payload["options"]["num_ctx"] = model_info.params.get("num_ctx", None)
+
+            if (
+                model_info.params.get("num_batch", None)
+                and payload["options"].get("num_batch") is None
+            ):
+                payload["options"]["num_batch"] = model_info.params.get(
+                    "num_batch", None
+                )
+
+            if (
+                model_info.params.get("num_keep", None)
+                and payload["options"].get("num_keep") is None
+            ):
+                payload["options"]["num_keep"] = model_info.params.get("num_keep", None)
+
+            if (
+                model_info.params.get("repeat_last_n", None)
+                and payload["options"].get("repeat_last_n") is None
+            ):
+                payload["options"]["repeat_last_n"] = model_info.params.get(
+                    "repeat_last_n", None
+                )
+
+            if (
+                model_info.params.get("frequency_penalty", None)
+                and payload["options"].get("frequency_penalty") is None
+            ):
+                payload["options"]["repeat_penalty"] = model_info.params.get(
+                    "frequency_penalty", None
+                )
+
+            if (
+                model_info.params.get("temperature", None) is not None
+                and payload["options"].get("temperature") is None
+            ):
+                payload["options"]["temperature"] = model_info.params.get(
+                    "temperature", None
+                )
+
+            if (
+                model_info.params.get("seed", None) is not None
+                and payload["options"].get("seed") is None
+            ):
+                payload["options"]["seed"] = model_info.params.get("seed", None)
+
+            if (
+                model_info.params.get("stop", None)
+                and payload["options"].get("stop") is None
+            ):
+                payload["options"]["stop"] = (
+                    [
+                        bytes(stop, "utf-8").decode("unicode_escape")
+                        for stop in model_info.params["stop"]
+                    ]
+                    if model_info.params.get("stop", None)
+                    else None
+                )
+
+            if (
+                model_info.params.get("tfs_z", None)
+                and payload["options"].get("tfs_z") is None
+            ):
+                payload["options"]["tfs_z"] = model_info.params.get("tfs_z", None)
+
+            if (
+                model_info.params.get("max_tokens", None)
+                and payload["options"].get("max_tokens") is None
+            ):
+                payload["options"]["num_predict"] = model_info.params.get(
+                    "max_tokens", None
+                )
+
+            if (
+                model_info.params.get("top_k", None)
+                and payload["options"].get("top_k") is None
+            ):
+                payload["options"]["top_k"] = model_info.params.get("top_k", None)
+
+            if (
+                model_info.params.get("top_p", None)
+                and payload["options"].get("top_p") is None
+            ):
+                payload["options"]["top_p"] = model_info.params.get("top_p", None)
+
+            if (
+                model_info.params.get("min_p", None)
+                and payload["options"].get("min_p") is None
+            ):
+                payload["options"]["min_p"] = model_info.params.get("min_p", None)
+
+            if (
+                model_info.params.get("use_mmap", None)
+                and payload["options"].get("use_mmap") is None
+            ):
+                payload["options"]["use_mmap"] = model_info.params.get("use_mmap", None)
+
+            if (
+                model_info.params.get("use_mlock", None)
+                and payload["options"].get("use_mlock") is None
+            ):
+                payload["options"]["use_mlock"] = model_info.params.get(
+                    "use_mlock", None
+                )
+
+            if (
+                model_info.params.get("num_thread", None)
+                and payload["options"].get("num_thread") is None
+            ):
+                payload["options"]["num_thread"] = model_info.params.get(
+                    "num_thread", None
+                )
+
+        system = model_info.params.get("system", None)
+        if system:
+            system = prompt_template(
+                system,
+                **(
+                    {
+                        "user_name": user.name,
+                        "user_location": (
+                            user.info.get("location") if user.info else None
+                        ),
+                    }
+                    if user
+                    else {}
+                ),
             )
-            payload = apply_model_system_prompt_to_body(params, payload, user)
 
-    if ":" not in payload["model"]:
-        payload["model"] = f"{payload['model']}:latest"
+            if payload.get("messages"):
+                payload["messages"] = add_or_update_system_message(
+                    system, payload["messages"]
+                )
+
+    if url_idx == None:
+        if ":" not in payload["model"]:
+            payload["model"] = f"{payload['model']}:latest"
+
+        if payload["model"] in app.state.MODELS:
+            url_idx = random.choice(app.state.MODELS[payload["model"]]["urls"])
+        else:
+            raise HTTPException(
+                status_code=400,
+                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model),
+            )
 
-    url = get_ollama_url(url_idx, payload["model"])
+    url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
     log.debug(payload)
 
@@ -784,28 +952,83 @@ async def generate_openai_chat_completion(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-    completion_form = OpenAIChatCompletionForm(**form_data)
-    payload = {**completion_form.model_dump(exclude_none=True, exclude=["metadata"])}
+    form_data = OpenAIChatCompletionForm(**form_data)
+    payload = {**form_data.model_dump(exclude_none=True, exclude=["metadata"])}
+
     if "metadata" in payload:
         del payload["metadata"]
 
-    model_id = completion_form.model
+    model_id = form_data.model
     model_info = Models.get_model_by_id(model_id)
 
     if model_info:
         if model_info.base_model_id:
             payload["model"] = model_info.base_model_id
 
-        params = model_info.params.model_dump()
+        model_info.params = model_info.params.model_dump()
 
-        if params:
-            payload = apply_model_params_to_body_openai(params, payload)
-            payload = apply_model_system_prompt_to_body(params, payload, user)
+        if model_info.params:
+            payload["temperature"] = model_info.params.get("temperature", None)
+            payload["top_p"] = model_info.params.get("top_p", None)
+            payload["max_tokens"] = model_info.params.get("max_tokens", None)
+            payload["frequency_penalty"] = model_info.params.get(
+                "frequency_penalty", None
+            )
+            payload["seed"] = model_info.params.get("seed", None)
+            payload["stop"] = (
+                [
+                    bytes(stop, "utf-8").decode("unicode_escape")
+                    for stop in model_info.params["stop"]
+                ]
+                if model_info.params.get("stop", None)
+                else None
+            )
 
-    if ":" not in payload["model"]:
-        payload["model"] = f"{payload['model']}:latest"
+        system = model_info.params.get("system", None)
+
+        if system:
+            system = prompt_template(
+                system,
+                **(
+                    {
+                        "user_name": user.name,
+                        "user_location": (
+                            user.info.get("location") if user.info else None
+                        ),
+                    }
+                    if user
+                    else {}
+                ),
+            )
+            # Check if the payload already has a system message
+            # If not, add a system message to the payload
+            if payload.get("messages"):
+                for message in payload["messages"]:
+                    if message.get("role") == "system":
+                        message["content"] = system + message["content"]
+                        break
+                else:
+                    payload["messages"].insert(
+                        0,
+                        {
+                            "role": "system",
+                            "content": system,
+                        },
+                    )
 
-    url = get_ollama_url(url_idx, payload["model"])
+    if url_idx == None:
+        if ":" not in payload["model"]:
+            payload["model"] = f"{payload['model']}:latest"
+
+        if payload["model"] in app.state.MODELS:
+            url_idx = random.choice(app.state.MODELS[payload["model"]]["urls"])
+        else:
+            raise HTTPException(
+                status_code=400,
+                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model),
+            )
+
+    url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
     return await post_streaming_url(
@@ -821,7 +1044,7 @@ async def get_openai_models(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-    if url_idx is None:
+    if url_idx == None:
         models = await get_all_models()
 
         if app.state.config.ENABLE_MODEL_FILTER:
@@ -876,7 +1099,7 @@ async def get_openai_models(
                     res = r.json()
                     if "error" in res:
                         error_detail = f"Ollama: {res['error']}"
-                except Exception:
+                except:
                     error_detail = f"Ollama: {e}"
 
             raise HTTPException(
@@ -902,6 +1125,7 @@ def parse_huggingface_url(hf_url):
         path_components = parsed_url.path.split("/")
 
         # Extract the desired output
+        user_repo = "/".join(path_components[1:3])
         model_file = path_components[-1]
 
         return model_file
@@ -966,6 +1190,7 @@ async def download_model(
     url_idx: Optional[int] = None,
     user=Depends(get_admin_user),
 ):
+
     allowed_hosts = ["https://huggingface.co/", "https://github.com/"]
 
     if not any(form_data.url.startswith(host) for host in allowed_hosts):
@@ -974,7 +1199,7 @@ async def download_model(
             detail="Invalid file_url. Only URLs from allowed hosts are permitted.",
         )
 
-    if url_idx is None:
+    if url_idx == None:
         url_idx = 0
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
 
@@ -997,7 +1222,7 @@ def upload_model(
     url_idx: Optional[int] = None,
     user=Depends(get_admin_user),
 ):
-    if url_idx is None:
+    if url_idx == None:
         url_idx = 0
     ollama_url = app.state.config.OLLAMA_BASE_URLS[url_idx]
 

backend/apps/openai/main.py

@@ -17,10 +17,7 @@ from utils.utils import (
     get_verified_user,
     get_admin_user,
 )
-from utils.misc import (
-    apply_model_params_to_body_openai,
-    apply_model_system_prompt_to_body,
-)
+from utils.misc import apply_model_params_to_body, apply_model_system_prompt_to_body
 
 from config import (
     SRC_LOG_LEVELS,
@@ -371,7 +368,7 @@ async def generate_chat_completion(
             payload["model"] = model_info.base_model_id
 
         params = model_info.params.model_dump()
-        payload = apply_model_params_to_body_openai(params, payload)
+        payload = apply_model_params_to_body(params, payload)
         payload = apply_model_system_prompt_to_body(params, payload, user)
 
     model = app.state.MODELS[payload.get("model")]

backend/apps/webui/main.py

@@ -22,7 +22,7 @@ from apps.webui.utils import load_function_module_by_id
 from utils.misc import (
     openai_chat_chunk_message_template,
     openai_chat_completion_message_template,
-    apply_model_params_to_body_openai,
+    apply_model_params_to_body,
     apply_model_system_prompt_to_body,
 )
 
@@ -291,7 +291,7 @@ async def generate_function_chat_completion(form_data, user):
             form_data["model"] = model_info.base_model_id
 
         params = model_info.params.model_dump()
-        form_data = apply_model_params_to_body_openai(params, form_data)
+        form_data = apply_model_params_to_body(params, form_data)
         form_data = apply_model_system_prompt_to_body(params, form_data, user)
 
     pipe_id = get_pipe_id(form_data)

backend/requirements.txt

@@ -11,7 +11,7 @@ python-jose==3.3.0
 passlib[bcrypt]==1.7.4
 
 requests==2.32.3
-aiohttp==3.10.2
+aiohttp==3.9.5
 
 sqlalchemy==2.0.31
 alembic==1.13.2
@@ -34,12 +34,12 @@ anthropic
 google-generativeai==0.7.2
 tiktoken
 
-langchain==0.2.12
+langchain==0.2.11
 langchain-community==0.2.10
 langchain-chroma==0.1.2
 
 fake-useragent==1.5.1
-chromadb==0.5.5
+chromadb==0.5.4
 sentence-transformers==3.0.1
 pypdf==4.3.1
 docx2txt==0.8
@@ -62,11 +62,11 @@ rank-bm25==0.2.2
 
 faster-whisper==1.0.2
 
-PyJWT[crypto]==2.9.0
+PyJWT[crypto]==2.8.0
 authlib==1.3.1
 
 black==24.8.0
-langfuse==2.43.3
+langfuse==2.39.2
 youtube-transcript-api==0.6.2
 pytube==15.0.0
 
@@ -76,5 +76,5 @@ duckduckgo-search~=6.2.1
 
 ## Tests
 docker~=7.1.0
-pytest~=8.3.2
+pytest~=8.2.2
 pytest-docker~=3.1.1

backend/utils/misc.py

@@ -2,7 +2,7 @@ from pathlib import Path
 import hashlib
 import re
 from datetime import timedelta
-from typing import Optional, List, Tuple, Callable
+from typing import Optional, List, Tuple
 import uuid
 import time
 
@@ -135,21 +135,10 @@ def apply_model_system_prompt_to_body(params: dict, form_data: dict, user) -> di
 
 
 # inplace function: form_data is modified
-def apply_model_params_to_body(
-    params: dict, form_data: dict, mappings: dict[str, Callable]
-) -> dict:
+def apply_model_params_to_body(params: dict, form_data: dict) -> dict:
     if not params:
         return form_data
 
-    for key, cast_func in mappings.items():
-        if (value := params.get(key)) is not None:
-            form_data[key] = cast_func(value)
-
-    return form_data
-
-
-# inplace function: form_data is modified
-def apply_model_params_to_body_openai(params: dict, form_data: dict) -> dict:
     mappings = {
         "temperature": float,
         "top_p": int,
@@ -158,40 +147,10 @@ def apply_model_params_to_body_openai(params: dict, form_data: dict) -> dict:
         "seed": lambda x: x,
         "stop": lambda x: [bytes(s, "utf-8").decode("unicode_escape") for s in x],
     }
-    return apply_model_params_to_body(params, form_data, mappings)
-
-
-def apply_model_params_to_body_ollama(params: dict, form_data: dict) -> dict:
-    opts = [
-        "temperature",
-        "top_p",
-        "seed",
-        "mirostat",
-        "mirostat_eta",
-        "mirostat_tau",
-        "num_ctx",
-        "num_batch",
-        "num_keep",
-        "repeat_last_n",
-        "tfs_z",
-        "top_k",
-        "min_p",
-        "use_mmap",
-        "use_mlock",
-        "num_thread",
-        "num_gpu",
-    ]
-    mappings = {i: lambda x: x for i in opts}
-    form_data = apply_model_params_to_body(params, form_data, mappings)
-
-    name_differences = {
-        "max_tokens": "num_predict",
-        "frequency_penalty": "repeat_penalty",
-    }
 
-    for key, value in name_differences.items():
-        if (param := params.get(key, None)) is not None:
-            form_data[value] = param
+    for key, cast_func in mappings.items():
+        if (value := params.get(key)) is not None:
+            form_data[key] = cast_func(value)
 
     return form_data
 

cypress/e2e/chat.cy.ts

@@ -38,10 +38,9 @@ describe('Settings', () => {
 			// User's message should be visible
 			cy.get('.chat-user').should('exist');
 			// Wait for the response
-			// .chat-assistant is created after the first token is received
-			cy.get('.chat-assistant', { timeout: 10_000 }).should('exist');
-			// Generation Info is created after the stop token is received
-			cy.get('div[aria-label="Generation Info"]', { timeout: 120_000 }).should('exist');
+			cy.get('.chat-assistant', { timeout: 120_000 }) // .chat-assistant is created after the first token is received
+				.find('div[aria-label="Generation Info"]', { timeout: 120_000 }) // Generation Info is created after the stop token is received
+				.should('exist');
 		});
 
 		it('user can share chat', () => {
@@ -58,24 +57,21 @@ describe('Settings', () => {
 			// User's message should be visible
 			cy.get('.chat-user').should('exist');
 			// Wait for the response
-			// .chat-assistant is created after the first token is received
-			cy.get('.chat-assistant', { timeout: 10_000 }).should('exist');
-			// Generation Info is created after the stop token is received
-			cy.get('div[aria-label="Generation Info"]', { timeout: 120_000 }).should('exist');
+			cy.get('.chat-assistant', { timeout: 120_000 }) // .chat-assistant is created after the first token is received
+				.find('div[aria-label="Generation Info"]', { timeout: 120_000 }) // Generation Info is created after the stop token is received
+				.should('exist');
 			// spy on requests
 			const spy = cy.spy();
-			cy.intercept('POST', '/api/v1/chats/**/share', spy);
+			cy.intercept('GET', '/api/v1/chats/*', spy);
 			// Open context menu
 			cy.get('#chat-context-menu-button').click();
 			// Click share button
 			cy.get('#chat-share-button').click();
 			// Check if the share dialog is visible
 			cy.get('#copy-and-share-chat-button').should('exist');
-			// Click the copy button
-			cy.get('#copy-and-share-chat-button').click();
-			cy.wrap({}, { timeout: 5_000 }).should(() => {
-				// Check if the share request was made
-				expect(spy).to.be.callCount(1);
+			cy.wrap({}, { timeout: 5000 }).should(() => {
+				// Check if the request was made twice (once for to replace chat object and once more due to change event)
+				expect(spy).to.be.callCount(2);
 			});
 		});
 
@@ -93,10 +89,9 @@ describe('Settings', () => {
 			// User's message should be visible
 			cy.get('.chat-user').should('exist');
 			// Wait for the response
-			// .chat-assistant is created after the first token is received
-			cy.get('.chat-assistant', { timeout: 10_000 }).should('exist');
-			// Generation Info is created after the stop token is received
-			cy.get('div[aria-label="Generation Info"]', { timeout: 120_000 }).should('exist');
+			cy.get('.chat-assistant', { timeout: 120_000 }) // .chat-assistant is created after the first token is received
+				.find('div[aria-label="Generation Info"]', { timeout: 120_000 }) // Generation Info is created after the stop token is received
+				.should('exist');
 			// Click on the generate image button
 			cy.get('[aria-label="Generate Image"]').click();
 			// Wait for image to be visible

docs/CONTRIBUTING.md

@@ -22,6 +22,7 @@ Noticed something off? Have an idea? Check our [Issues tab](https://github.com/o
 > [!IMPORTANT]
 >
 > - **Template Compliance:** Please be aware that failure to follow the provided issue template, or not providing the requested information at all, will likely result in your issue being closed without further consideration. This approach is critical for maintaining the manageability and integrity of issue tracking.
+>
 > - **Detail is Key:** To ensure your issue is understood and can be effectively addressed, it's imperative to include comprehensive details. Descriptions should be clear, including steps to reproduce, expected outcomes, and actual results. Lack of sufficient detail may hinder our ability to resolve your issue.
 
 ### 🧭 Scope of Support

pyproject.toml

@@ -19,7 +19,7 @@ dependencies = [
     "passlib[bcrypt]==1.7.4",
 
     "requests==2.32.3",
-    "aiohttp==3.10.2",
+    "aiohttp==3.9.5",
 
     "sqlalchemy==2.0.31",
     "alembic==1.13.2",

src/app.html

@@ -1,4 +1,4 @@
-<!doctype html>
+<!DOCTYPE html>
 <html lang="en">
 	<head>
 		<meta charset="utf-8" />

src/lib/apis/openai/index.ts

@@ -260,7 +260,7 @@ export const getOpenAIModelsDirect = async (
 		throw error;
 	}
 
-	const models = Array.isArray(res) ? res : (res?.data ?? null);
+	const models = Array.isArray(res) ? res : res?.data ?? null;
 
 	return models
 		.map((model) => ({ id: model.id, name: model.name ?? model.id, external: true }))

src/lib/components/ChangelogModal.svelte

@@ -75,12 +75,12 @@
 										class="font-semibold uppercase text-xs {section === 'added'
 											? 'text-white bg-blue-600'
 											: section === 'fixed'
-												? 'text-white bg-green-600'
-												: section === 'changed'
-													? 'text-white bg-yellow-600'
-													: section === 'removed'
-														? 'text-white bg-red-600'
-														: ''}  w-fit px-3 rounded-full my-2.5"
+											? 'text-white bg-green-600'
+											: section === 'changed'
+											? 'text-white bg-yellow-600'
+											: section === 'removed'
+											? 'text-white bg-red-600'
+											: ''}  w-fit px-3 rounded-full my-2.5"
 									>
 										{section}
 									</div>

src/lib/components/admin/Settings/Documents.svelte

@@ -112,7 +112,7 @@
 							url: OpenAIUrl,
 							batch_size: OpenAIBatchSize
 						}
-					}
+				  }
 				: {})
 		}).catch(async (error) => {
 			toast.error(error);

src/lib/components/chat/Chat.svelte

@@ -579,8 +579,8 @@
 		let selectedModelIds = modelId
 			? [modelId]
 			: atSelectedModel !== undefined
-				? [atSelectedModel.id]
-				: selectedModels;
+			? [atSelectedModel.id]
+			: selectedModels;
 
 		// Create response messages for each selected model
 		const responseMessageIds = {};
@@ -739,11 +739,11 @@
 								? await getAndUpdateUserLocation(localStorage.token)
 								: undefined
 						)}${
-							(responseMessage?.userContext ?? null)
+							responseMessage?.userContext ?? null
 								? `\n\nUser Context:\n${responseMessage?.userContext ?? ''}`
 								: ''
 						}`
-					}
+				  }
 				: undefined,
 			...messages
 		]
@@ -811,10 +811,10 @@
 			options: {
 				...(params ?? $settings.params ?? {}),
 				stop:
-					(params?.stop ?? $settings?.params?.stop ?? undefined)
+					params?.stop ?? $settings?.params?.stop ?? undefined
 						? (params?.stop.split(',').map((token) => token.trim()) ?? $settings.params.stop).map(
 								(str) => decodeURIComponent(JSON.parse('"' + str.replace(/\"/g, '\\"') + '"'))
-							)
+						  )
 						: undefined,
 				num_predict: params?.max_tokens ?? $settings?.params?.max_tokens ?? undefined,
 				repeat_penalty:
@@ -1056,10 +1056,10 @@
 					stream: true,
 					model: model.id,
 					stream_options:
-						(model.info?.meta?.capabilities?.usage ?? false)
+						model.info?.meta?.capabilities?.usage ?? false
 							? {
 									include_usage: true
-								}
+							  }
 							: undefined,
 					messages: [
 						params?.system || $settings.system || (responseMessage?.userContext ?? null)
@@ -1072,11 +1072,11 @@
 											? await getAndUpdateUserLocation(localStorage.token)
 											: undefined
 									)}${
-										(responseMessage?.userContext ?? null)
+										responseMessage?.userContext ?? null
 											? `\n\nUser Context:\n${responseMessage?.userContext ?? ''}`
 											: ''
 									}`
-								}
+							  }
 							: undefined,
 						...messages
 					]
@@ -1092,7 +1092,7 @@
 												text:
 													arr.length - 1 !== idx
 														? message.content
-														: (message?.raContent ?? message.content)
+														: message?.raContent ?? message.content
 											},
 											...message.files
 												.filter((file) => file.type === 'image')
@@ -1103,20 +1103,20 @@
 													}
 												}))
 										]
-									}
+								  }
 								: {
 										content:
 											arr.length - 1 !== idx
 												? message.content
-												: (message?.raContent ?? message.content)
-									})
+												: message?.raContent ?? message.content
+								  })
 						})),
 					seed: params?.seed ?? $settings?.params?.seed ?? undefined,
 					stop:
-						(params?.stop ?? $settings?.params?.stop ?? undefined)
+						params?.stop ?? $settings?.params?.stop ?? undefined
 							? (params?.stop.split(',').map((token) => token.trim()) ?? $settings.params.stop).map(
 									(str) => decodeURIComponent(JSON.parse('"' + str.replace(/\"/g, '\\"') + '"'))
-								)
+							  )
 							: undefined,
 					temperature: params?.temperature ?? $settings?.params?.temperature ?? undefined,
 					top_p: params?.top_p ?? $settings?.params?.top_p ?? undefined,

src/lib/components/chat/Controls/Controls.svelte

@@ -9,8 +9,6 @@
 	import FileItem from '$lib/components/common/FileItem.svelte';
 	import Collapsible from '$lib/components/common/Collapsible.svelte';
 
-	import { user } from '$lib/stores';
-
 	export let models = [];
 
 	export let chatFiles = [];
@@ -80,7 +78,7 @@
 		<Collapsible title={$i18n.t('Advanced Params')} open={true}>
 			<div class="text-sm mt-1.5" slot="content">
 				<div>
-					<AdvancedParams admin={$user?.role === 'admin'} bind:params />
+					<AdvancedParams bind:params />
 				</div>
 			</div>
 		</Collapsible>

src/lib/components/chat/MessageInput/CallOverlay.svelte

@@ -609,10 +609,10 @@
 								style="font-size:{rmsLevel * 100 > 4
 									? '4.5'
 									: rmsLevel * 100 > 2
-										? '4.25'
-										: rmsLevel * 100 > 1
-											? '3.75'
-											: '3.5'}rem;width: 100%; text-align:center;"
+									? '4.25'
+									: rmsLevel * 100 > 1
+									? '3.75'
+									: '3.5'}rem;width: 100%; text-align:center;"
 							>
 								{emoji}
 							</div>
@@ -658,10 +658,10 @@
 								class=" {rmsLevel * 100 > 4
 									? ' size-[4.5rem]'
 									: rmsLevel * 100 > 2
-										? ' size-16'
-										: rmsLevel * 100 > 1
-											? 'size-14'
-											: 'size-12'}  transition-all rounded-full {(model?.info?.meta
+									? ' size-16'
+									: rmsLevel * 100 > 1
+									? 'size-14'
+									: 'size-12'}  transition-all rounded-full {(model?.info?.meta
 									?.profile_image_url ?? '/static/favicon.png') !== '/static/favicon.png'
 									? ' bg-cover bg-center bg-no-repeat'
 									: 'bg-black dark:bg-white'}  bg-black dark:bg-white"
@@ -691,10 +691,10 @@
 									style="font-size:{rmsLevel * 100 > 4
 										? '13'
 										: rmsLevel * 100 > 2
-											? '12'
-											: rmsLevel * 100 > 1
-												? '11.5'
-												: '11'}rem;width:100%;text-align:center;"
+										? '12'
+										: rmsLevel * 100 > 1
+										? '11.5'
+										: '11'}rem;width:100%;text-align:center;"
 								>
 									{emoji}
 								</div>
@@ -740,10 +740,10 @@
 									class=" {rmsLevel * 100 > 4
 										? ' size-52'
 										: rmsLevel * 100 > 2
-											? 'size-48'
-											: rmsLevel * 100 > 1
-												? 'size-[11.5rem]'
-												: 'size-44'}  transition-all rounded-full {(model?.info?.meta
+										? 'size-48'
+										: rmsLevel * 100 > 1
+										? 'size-[11.5rem]'
+										: 'size-44'}  transition-all rounded-full {(model?.info?.meta
 										?.profile_image_url ?? '/static/favicon.png') !== '/static/favicon.png'
 										? ' bg-cover bg-center bg-no-repeat'
 										: 'bg-black dark:bg-white'} "

src/lib/components/chat/MessageInput/Documents.svelte

@@ -27,7 +27,7 @@
 						title: $i18n.t('All Documents'),
 						collection_names: $documents.map((doc) => doc.collection_name)
 					}
-				]
+			  ]
 			: []),
 		...$documents
 			.reduce((a, e, i, arr) => {

src/lib/components/chat/Messages.svelte

@@ -305,7 +305,7 @@
 				{#each messages as message, messageIdx}
 					<div class=" w-full {messageIdx === messages.length - 1 ? ' pb-12' : ''}">
 						<div
-							class="flex flex-col justify-between px-5 mb-3 {($settings?.widescreenMode ?? null)
+							class="flex flex-col justify-between px-5 mb-3 {$settings?.widescreenMode ?? null
 								? 'max-w-full'
 								: 'max-w-5xl'} mx-auto rounded-lg group"
 						>
@@ -317,10 +317,10 @@
 									{message}
 									isFirstMessage={messageIdx === 0}
 									siblings={message.parentId !== null
-										? (history.messages[message.parentId]?.childrenIds ?? [])
-										: (Object.values(history.messages)
+										? history.messages[message.parentId]?.childrenIds ?? []
+										: Object.values(history.messages)
 												.filter((message) => message.parentId === null)
-												.map((message) => message.id) ?? [])}
+												.map((message) => message.id) ?? []}
 									{confirmEditMessage}
 									{showPreviousMessage}
 									{showNextMessage}

src/lib/components/chat/Messages/CitationsModal.svelte

@@ -60,8 +60,8 @@
 									href={document?.metadata?.file_id
 										? `/api/v1/files/${document?.metadata?.file_id}/content`
 										: document.source.name.includes('http')
-											? document.source.name
-											: `#`}
+										? document.source.name
+										: `#`}
 									target="_blank"
 								>
 									{document?.metadata?.name ?? document.source.name}

src/lib/components/chat/Messages/ResponseMessage.svelte

@@ -191,7 +191,7 @@
 							const res = await synthesizeOpenAISpeech(
 								localStorage.token,
 								$settings?.audio?.tts?.defaultVoice === $config.audio.tts.voice
-									? ($settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice)
+									? $settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice
 									: $config?.audio?.tts?.voice,
 								sentence
 							).catch((error) => {
@@ -803,7 +803,7 @@
 																100
 														) / 100
 													} tokens` ?? 'N/A'
-												}<br/>
+											  }<br/>
 					prompt_token/s: ${
 						Math.round(
 							((message.info.prompt_eval_count ?? 0) /

src/lib/components/chat/Messages/UserMessage.svelte

@@ -62,8 +62,8 @@
 	{#if !($settings?.chatBubble ?? true)}
 		<ProfileImage
 			src={message.user
-				? ($models.find((m) => m.id === message.user)?.info?.meta?.profile_image_url ?? '/user.png')
-				: (user?.profile_image_url ?? '/user.png')}
+				? $models.find((m) => m.id === message.user)?.info?.meta?.profile_image_url ?? '/user.png'
+				: user?.profile_image_url ?? '/user.png'}
 		/>
 	{/if}
 	<div class="w-full overflow-hidden pl-1">
@@ -96,7 +96,7 @@
 			{#if message.files}
 				<div class="mt-2.5 mb-1 w-full flex flex-col justify-end overflow-x-auto gap-1 flex-wrap">
 					{#each message.files as file}
-						<div class={($settings?.chatBubble ?? true) ? 'self-end' : ''}>
+						<div class={$settings?.chatBubble ?? true ? 'self-end' : ''}>
 							{#if file.type === 'image'}
 								<img src={file.url} alt="input" class=" max-h-96 rounded-lg" draggable="false" />
 							{:else}
@@ -162,12 +162,12 @@
 				</div>
 			{:else}
 				<div class="w-full">
-					<div class="flex {($settings?.chatBubble ?? true) ? 'justify-end' : ''} mb-2">
+					<div class="flex {$settings?.chatBubble ?? true ? 'justify-end' : ''} mb-2">
 						<div
-							class="rounded-3xl {($settings?.chatBubble ?? true)
+							class="rounded-3xl {$settings?.chatBubble ?? true
 								? `max-w-[90%] px-5 py-2  bg-gray-50 dark:bg-gray-850 ${
 										message.files ? 'rounded-tr-lg' : ''
-									}`
+								  }`
 								: ''}  "
 						>
 							<pre id="user-message">{message.content}</pre>
@@ -175,7 +175,7 @@
 					</div>
 
 					<div
-						class=" flex {($settings?.chatBubble ?? true)
+						class=" flex {$settings?.chatBubble ?? true
 							? 'justify-end'
 							: ''}  text-gray-600 dark:text-gray-500"
 					>

src/lib/components/chat/ModelSelector/Selector.svelte

@@ -66,7 +66,7 @@
 	$: filteredItems = searchValue
 		? fuse.search(searchValue).map((e) => {
 				return e.item;
-			})
+		  })
 		: items.filter((item) => !item.model?.info?.meta?.hidden);
 
 	const pullModelHandler = async () => {

src/lib/components/chat/Settings/About.svelte

@@ -65,8 +65,8 @@
 							{updateAvailable === null
 								? $i18n.t('Checking for updates...')
 								: updateAvailable
-									? `(v${version.latest} ${$i18n.t('available!')})`
-									: $i18n.t('(latest)')}
+								? `(v${version.latest} ${$i18n.t('available!')})`
+								: $i18n.t('(latest)')}
 						</a>
 					</div>
 

src/lib/components/chat/Settings/Advanced/AdvancedParams.svelte

@@ -29,7 +29,6 @@
 		use_mmap: null,
 		use_mlock: null,
 		num_thread: null,
-		num_gpu: null,
 		template: null
 	};
 
@@ -865,52 +864,6 @@
 			{/if}
 		</div>
 
-		<div class=" py-0.5 w-full justify-between">
-			<div class="flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">{$i18n.t('num_gpu (Ollama)')}</div>
-
-				<button
-					class="p-1 px-3 text-xs flex rounded transition flex-shrink-0 outline-none"
-					type="button"
-					on:click={() => {
-						params.num_gpu = (params?.num_gpu ?? null) === null ? 0 : null;
-					}}
-				>
-					{#if (params?.num_gpu ?? null) === null}
-						<span class="ml-2 self-center">{$i18n.t('Default')}</span>
-					{:else}
-						<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
-					{/if}
-				</button>
-			</div>
-
-			{#if (params?.num_gpu ?? null) !== null}
-				<div class="flex mt-0.5 space-x-2">
-					<div class=" flex-1">
-						<input
-							id="steps-range"
-							type="range"
-							min="0"
-							max="256"
-							step="1"
-							bind:value={params.num_gpu}
-							class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
-						/>
-					</div>
-					<div class="">
-						<input
-							bind:value={params.num_gpu}
-							type="number"
-							class=" bg-transparent text-center w-14"
-							min="0"
-							max="256"
-							step="1"
-						/>
-					</div>
-				</div>
-			{/if}
-		</div>
-
 		<!-- <div class=" py-0.5 w-full justify-between">
 			<div class="flex w-full justify-between">
 				<div class=" self-center text-xs font-medium">{$i18n.t('Template')}</div>

src/lib/components/common/Valves.svelte

@@ -27,7 +27,7 @@
 					on:click={() => {
 						valves[property] =
 							(valves[property] ?? null) === null
-								? (valvesSpec.properties[property]?.default ?? '')
+								? valvesSpec.properties[property]?.default ?? ''
 								: null;
 
 						dispatch('change');

src/lib/components/layout/Sidebar/ChatItem.svelte

@@ -83,8 +83,8 @@
 			class=" w-full flex justify-between rounded-xl px-3 py-2 {chat.id === $chatId || confirmEdit
 				? 'bg-gray-200 dark:bg-gray-900'
 				: selected
-					? 'bg-gray-100 dark:bg-gray-950'
-					: 'group-hover:bg-gray-100 dark:group-hover:bg-gray-950'}  whitespace-nowrap text-ellipsis"
+				? 'bg-gray-100 dark:bg-gray-950'
+				: 'group-hover:bg-gray-100 dark:group-hover:bg-gray-950'}  whitespace-nowrap text-ellipsis"
 		>
 			<input
 				use:focusEdit
@@ -97,8 +97,8 @@
 			class=" w-full flex justify-between rounded-xl px-3 py-2 {chat.id === $chatId || confirmEdit
 				? 'bg-gray-200 dark:bg-gray-900'
 				: selected
-					? 'bg-gray-100 dark:bg-gray-950'
-					: ' group-hover:bg-gray-100 dark:group-hover:bg-gray-950'}  whitespace-nowrap text-ellipsis"
+				? 'bg-gray-100 dark:bg-gray-950'
+				: ' group-hover:bg-gray-100 dark:group-hover:bg-gray-950'}  whitespace-nowrap text-ellipsis"
 			href="/c/{chat.id}"
 			on:click={() => {
 				dispatch('select');
@@ -134,8 +134,8 @@
         {chat.id === $chatId || confirmEdit
 			? 'from-gray-200 dark:from-gray-900'
 			: selected
-				? 'from-gray-100 dark:from-gray-950'
-				: 'invisible group-hover:visible from-gray-100 dark:from-gray-950'}
+			? 'from-gray-100 dark:from-gray-950'
+			: 'invisible group-hover:visible from-gray-100 dark:from-gray-950'}
             absolute right-[10px] top-[6px] py-1 pr-2 pl-5 bg-gradient-to-l from-80%
 
               to-transparent"

src/lib/components/playground/Playground.svelte

@@ -121,7 +121,7 @@
 						? {
 								role: 'system',
 								content: system
-							}
+						  }
 						: undefined,
 					...messages
 				].filter((message) => message)

src/lib/components/workspace/Documents.svelte

@@ -88,7 +88,7 @@
 				tags?.length > 0
 					? {
 							tags: tags
-						}
+					  }
 					: null
 			).catch((error) => {
 				toast.error(error);

src/lib/components/workspace/Models.svelte

@@ -292,7 +292,7 @@
 			>
 				<div class=" self-start w-8 pt-0.5">
 					<div
-						class=" rounded-full bg-stone-700 {(model?.info?.meta?.hidden ?? false)
+						class=" rounded-full bg-stone-700 {model?.info?.meta?.hidden ?? false
 							? 'brightness-90 dark:brightness-50'
 							: ''} "
 					>
@@ -305,7 +305,7 @@
 				</div>
 
 				<div
-					class=" flex-1 self-center {(model?.info?.meta?.hidden ?? false) ? 'text-gray-500' : ''}"
+					class=" flex-1 self-center {model?.info?.meta?.hidden ?? false ? 'text-gray-500' : ''}"
 				>
 					<div class="  font-semibold line-clamp-1">{model.name}</div>
 					<div class=" text-xs overflow-hidden text-ellipsis line-clamp-1">

src/lib/components/workspace/Models/Knowledge/Selector.svelte

@@ -25,7 +25,7 @@
 							title: $i18n.t('All Documents'),
 							collection_names: $documents.map((doc) => doc.collection_name)
 						}
-					]
+				  ]
 				: []),
 			...$documents
 				.reduce((a, e, i, arr) => {

src/lib/i18n/locales/ar-BH/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "ملاحظة: إذا قمت بتعيين الحد الأدنى من النقاط، فلن يؤدي البحث إلا إلى إرجاع المستندات التي لها نقاط أكبر من أو تساوي الحد الأدنى من النقاط.",
 	"Notifications": "إشعارات",
 	"November": "نوفمبر",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (أولاما)",
 	"OAuth ID": "",
 	"October": "اكتوبر",

src/lib/i18n/locales/bg-BG/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "Забележка: Ако зададете минимален резултат, търсенето ще върне само документи с резултат, по-голям или равен на минималния резултат.",
 	"Notifications": "Десктоп Известия",
 	"November": "Ноември",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (Ollama)",
 	"OAuth ID": "",
 	"October": "Октомври",

src/lib/i18n/locales/bn-BD/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "দ্রষ্টব্য: আপনি যদি ন্যূনতম স্কোর সেট করেন তবে অনুসন্ধানটি কেবলমাত্র ন্যূনতম স্কোরের চেয়ে বেশি বা সমান স্কোর সহ নথিগুলি ফেরত দেবে।",
 	"Notifications": "নোটিফিকেশনসমূহ",
 	"November": "নভেম্বর",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (ওলামা)",
 	"OAuth ID": "",
 	"October": "অক্টোবর",

src/lib/i18n/locales/ca-ES/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "Nota: Si s'estableix una puntuació mínima, la cerca només retornarà documents amb una puntuació major o igual a la puntuació mínima.",
 	"Notifications": "Notificacions",
 	"November": "Novembre",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (Ollama)",
 	"OAuth ID": "ID OAuth",
 	"October": "Octubre",

src/lib/i18n/locales/ceb-PH/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "",
 	"Notifications": "Mga pahibalo sa desktop",
 	"November": "",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "",
 	"OAuth ID": "",
 	"October": "",

src/lib/i18n/locales/de-DE/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "Hinweis: Wenn Sie eine Mindestpunktzahl festlegen, werden in der Suche nur Dokumente mit einer Punktzahl größer oder gleich der Mindestpunktzahl zurückgegeben.",
 	"Notifications": "Benachrichtigungen",
 	"November": "November",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (Ollama)",
 	"OAuth ID": "OAuth-ID",
 	"October": "Oktober",

src/lib/i18n/locales/dg-DG/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "",
 	"Notifications": "Notifications",
 	"November": "",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "",
 	"OAuth ID": "",
 	"October": "",

src/lib/i18n/locales/en-GB/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "",
 	"Notifications": "",
 	"November": "",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "",
 	"OAuth ID": "",
 	"October": "",

src/lib/i18n/locales/en-US/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "",
 	"Notifications": "",
 	"November": "",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "",
 	"OAuth ID": "",
 	"October": "",

src/lib/i18n/locales/es-ES/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "Nota: Si estableces una puntuación mínima, la búsqueda sólo devolverá documentos con una puntuación mayor o igual a la puntuación mínima.",
 	"Notifications": "Notificaciones",
 	"November": "Noviembre",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (Ollama)",
 	"OAuth ID": "OAuth ID",
 	"October": "Octubre",

src/lib/i18n/locales/fa-IR/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "توجه: اگر حداقل نمره را تعیین کنید، جستجو تنها اسنادی را با نمره بیشتر یا برابر با حداقل نمره باز می گرداند.",
 	"Notifications": "اعلان",
 	"November": "نوامبر",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (اولاما)",
 	"OAuth ID": "",
 	"October": "اکتبر",

src/lib/i18n/locales/fi-FI/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "Huom: Jos asetat vähimmäispisteet, haku palauttaa vain asiakirjat, joiden pisteet ovat suurempia tai yhtä suuria kuin vähimmäispistemäärä.",
 	"Notifications": "Ilmoitukset",
 	"November": "marraskuu",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (Ollama)",
 	"OAuth ID": "",
 	"October": "lokakuu",

src/lib/i18n/locales/fr-CA/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "Note : Si vous définissez un score minimum, seuls les documents ayant un score supérieur ou égal à ce score minimum seront retournés par la recherche.",
 	"Notifications": "Notifications",
 	"November": "Novembre",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (Ollama)",
 	"OAuth ID": "ID OAuth",
 	"October": "Octobre",

src/lib/i18n/locales/fr-FR/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "Note : Si vous définissez un score minimum, seuls les documents ayant un score supérieur ou égal à ce score minimum seront retournés par la recherche.",
 	"Notifications": "Notifications",
 	"November": "Novembre",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (Ollama)",
 	"OAuth ID": "ID OAuth",
 	"October": "Octobre",

src/lib/i18n/locales/he-IL/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "הערה: אם תקבע ציון מינימלי, החיפוש יחזיר רק מסמכים עם ציון שגבוה או שווה לציון המינימלי.",
 	"Notifications": "התראות",
 	"November": "נובמבר",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (Ollama)",
 	"OAuth ID": "",
 	"October": "אוקטובר",

src/lib/i18n/locales/hi-IN/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "ध्यान दें: यदि आप न्यूनतम स्कोर निर्धारित करते हैं, तो खोज केवल न्यूनतम स्कोर से अधिक या उसके बराबर स्कोर वाले दस्तावेज़ वापस लाएगी।",
 	"Notifications": "सूचनाएं",
 	"November": "नवंबर",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (ओलामा)",
 	"OAuth ID": "",
 	"October": "अक्टूबर",

src/lib/i18n/locales/hr-HR/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "Napomena: Ako postavite minimalnu ocjenu, pretraga će vratiti samo dokumente s ocjenom većom ili jednakom minimalnoj ocjeni.",
 	"Notifications": "Obavijesti",
 	"November": "Studeni",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (Ollama)",
 	"OAuth ID": "",
 	"October": "Listopad",

src/lib/i18n/locales/id-ID/translation.json

@@ -418,7 +418,6 @@
 	"Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.": "Catatan: Jika Anda menetapkan skor minimum, pencarian hanya akan mengembalikan dokumen dengan skor yang lebih besar atau sama dengan skor minimum.",
 	"Notifications": "Pemberitahuan",
 	"November": "November",
-	"num_gpu (Ollama)": "",
 	"num_thread (Ollama)": "num_thread (Ollama)",
 	"OAuth ID": "ID OAuth",
 	"October": "Oktober",