8 views
-/https://github.com/berriai/litellm/issues/26235
GitHub · issue

#26235 Inaccuracy in the Getting Started Tutorial

  • State: open
  • Author: @ildar-sh
  • Labels: bug, docs

### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

### What happened?

On the [Getting Started Tutorial](https://docs.litellm.ai/docs/proxy/docker_quick_start), “Step 1 — Pull the LiteLLM database image” instructs docker pull ghcr.io/berriai/litellm-database:main-latest. The same page then has you download docker-compose.yml via curl -O https://raw.githubusercontent.com/BerriAI/litellm/main/docker-compose.yml, and the docker-compose.yml uses: image: docker.litellm.ai/berriai/litellm:main-stable for litellm image: postgres:16 for db So the “pull litellm-database image” step doesn’t match the Compose file you’re instructed to use.

If you use docker-compose, I think step 1 can simply be removed.

### Steps to Reproduce

This confusion in the documentation does not lead to errors, but simply misleads the user.

### Relevant log output

```shell

```

### What part of LiteLLM is this about?

Docs

### What LiteLLM version are you on ?

v1.83.11-nightly

### Twitter / LinkedIn details

_No response_

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (4 events)
#0 of 0 · 31d19h13m41s ago — entered · #import:https:::github.com:berriai:litellm post #1657
The right issue is harder because it requires tracing and correcting response normalization in the custom provider path, preserving compatibility, and adding regression coverage; the left issue is a localized documentation correction.
34555 requires code-path investigation, URL/token flow validation, backward-compatibility consideration, and regression tests; 26235 is a narrowly scoped documentation correction.
The left requires validating package contents, shortening or restructuring tracked fixtures, and verifying Windows installation behavior; the right is a localized documentation correction. The left carries substantially greater implementation and regression risk.
#0 of 0 · 31d18h15m15s ago — current · #import:https:::github.com:berriai:litellm post #2605
The left task requires extending proxy/provider functionality, handling image-input request semantics, compatibility, and integration testing. The right task is a narrowly scoped documentation correction with minimal engineering risk.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search