Skip to content

[Bug]: /ui is not accessible #11531

@thibmaek

Description

@thibmaek

What happened?

This happened after I pulled the latest image. I failed to fix it with my existing containers so here's what I did:

  1. Verify LiteLLM is still available as an API → ✅
  2. Listed models via /v1/models and saved the response as a backup
  3. Removed the running container and deleted the image: docker stop litellm && docker rm litellm && docker image rm ghcr.io/berriai/litellm:main-latest
  4. Recreated the container: docker compose up -d
  5. Disabled pi-hole on the network just in case

The DB seems to work fine, but even after this the UI remains inaccessible and shows the log output below and the following in the browser:

Image

My compose.yaml:

services:
  litellm:
    image: ghcr.io/berriai/litellm:main-latest
    container_name: litellm
    env_file: litellm.env
    volumes:
      - ./data/config.yaml:/app/config.yaml
    ports:
      - 4000:4000
    command: ['--config=/app/config.yaml']
    restart: unless-stopped

  litellm_db:
    image: postgres
    container_name: litellm_db
    env_file: litellm.env
    ports:
      - 5432:5432
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -d litellm -U llmproxy"]
      interval: 1s
      timeout: 5s
      retries: 10
    restart: unless-stopped

My litellm.env file:

DATABASE_URL="postgresql://llmproxy:*******@litellm_db:5432/litellm"
STORE_MODEL_IN_DB=True
MASTER_KEY="*******"

POSTGRES_DB=litellm
POSTGRES_USER=llmproxy
POSTGRES_PASSWORD=*******

# Ollama
OLLAMA_API_BASE=*******
OLLAMA_API_KEY=""

MISTRAL_API_KEY=*******

LANGFUSE_PUBLIC_KEY=pk-*******
LANGFUSE_SECRET_KEY=sk-*******
LANGFUSE_HOST=*******

My LiteLLM config:

general_settings:
  master_key: os.environ/MASTER_KEY
  pass_through_endpoints:
    - path: "/mistral/v1/ocr"
      target: "https://api.mistral.ai/v1/ocr"
      headers:
        Authorization: "bearer os.environ/MISTRAL_API_KEY"
        content-type: application/json
        accept: application/json
      forward_headers: True

model_list: []

Relevant log output

litellm  | INFO:     Shutting down
litellm  | INFO:     Waiting for application shutdown.
litellm  | INFO:     Application shutdown complete.
litellm  | INFO:     Finished server process [1]
litellm  | prisma:warn Prisma doesn't know which engines to download for the Linux distro "wolfi". Falling back to Prisma engines built "debian".
litellm  | Please report your experience by creating an issue at https://github.com/prisma/prisma/issues so we can add your distro to the list of known supported distros.
litellm  | Prisma schema loaded from schema.prisma
litellm  | Datasource "client": PostgreSQL database "litellm", schema "public" at "litellm_db:5432"
litellm  |
litellm  | The database is already in sync with the Prisma schema.
litellm  |
Running generate... - Prisma Client Python (v0.11.0)
litellm  |
litellm  | Some types are disabled by default due to being incompatible with Mypy, it is highly recommended
litellm  | to use Pyright instead and configure Prisma Python to use recursive types. To re-enable certain types:
litellm  |
litellm  | generator client {
litellm  |   provider             = "prisma-client-py"
litellm  |   recursive_type_depth = -1
litellm  | }
litellm  |
litellm  | If you need to use Mypy, you can also disable this message by explicitly setting the default value:
litellm  |
litellm  | generator client {
litellm  |   provider             = "prisma-client-py"
litellm  |   recursive_type_depth = 5
litellm  | }
litellm  |
litellm  | For more information see: https://prisma-client-py.readthedocs.io/en/stable/reference/limitations/#default-type-limitations
litellm  |
✔ Generated Prisma Client Python (v0.11.0) to ./../../prisma in 388ms
litellm  |
litellm  | INFO:     Started server process [1]
litellm  | INFO:     Waiting for application startup.
litellm  | INFO:     Application startup complete.
litellm  | INFO:     Uvicorn running on http://0.0.0.0:4000 (Press CTRL+C to quit)
litellm  |
litellm  | #------------------------------------------------------------#
litellm  | #                                                            #
litellm  | #           'It would help me if you could add...'            #
litellm  | #        https://github.com/BerriAI/litellm/issues/new        #
litellm  | #                                                            #
litellm  | #------------------------------------------------------------#
litellm  |
litellm  |  Thank you for using LiteLLM! - Krrish & Ishaan
litellm  |
litellm  |
litellm  |
litellm  | Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
litellm  |
litellm  |
litellm  | INFO:     192.168.1.x:58284 - "GET /ui/ HTTP/1.1" 200 OK
litellm  | INFO:     192.168.1.x:58284 - "GET /litellm2/_next/static/chunks/webpack-a426aae3231a8df1.js HTTP/1.1" 404 Not Found
litellm  | INFO:     192.168.1.x:58285 - "GET /litellm2/_next/static/chunks/fd9d1056-205af899b895cbac.js HTTP/1.1" 404 Not Found
litellm  | INFO:     192.168.1.x:58284 - "GET /litellm2/_next/static/chunks/117-c4922b1dd81b62ce.js HTTP/1.1" 404 Not Found
litellm  | INFO:     192.168.1.x:58286 - "GET /litellm2/_next/static/chunks/main-app-4f7318ae681a6d94.js HTTP/1.1" 404 Not Found

Are you a ML Ops Team?

No

What LiteLLM version are you on ?

always the latest main-stable

Twitter / LinkedIn details

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions