docs: add Quick Install section for litellm --setup wizard #23905
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -5,11 +5,76 @@ import TabItem from '@theme/TabItem'; | |
| # Getting Started Tutorial | ||
|
|
||
| End-to-End tutorial for LiteLLM Proxy to: | ||
| - Add an Azure OpenAI model | ||
| - Make a successful /chat/completion call | ||
| - Generate a virtual key | ||
| - Set RPM limit on virtual key | ||
|
|
||
| ## Quick Install (Recommended for local / beginners) | ||
|
|
||
| New to LiteLLM? This is the easiest way to get started locally. One command installs LiteLLM and walks you through setup interactively — no config files to write by hand. | ||
|
|
||
| ### 1. Install | ||
|
|
||
| ```bash | ||
| curl -fsSL https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh | sh | ||
| ``` | ||
|
|
||
| This detects your OS, installs `litellm[proxy]`, and drops you straight into the setup wizard. | ||
|
|
||
| ### 2. Follow the wizard | ||
|
|
||
| ``` | ||
| $ litellm --setup | ||
|
|
||
| Welcome to LiteLLM | ||
|
|
||
| Choose your LLM providers | ||
| ○ 1. OpenAI GPT-4o, GPT-4o-mini, o1 | ||
| ○ 2. Anthropic Claude Opus, Sonnet, Haiku | ||
| ○ 3. Azure OpenAI GPT-4o via Azure | ||
| ○ 4. Google Gemini Gemini 2.0 Flash, 1.5 Pro | ||
| ○ 5. AWS Bedrock Claude, Llama via AWS | ||
| ○ 6. Ollama Local models | ||
|
|
||
| ❯ Provider(s): 1,2 | ||
|
|
||
| ❯ OpenAI API key: sk-... | ||
| ❯ Anthropic API key: sk-ant-... | ||
|
|
||
| ❯ Port [4000]: | ||
| ❯ Master key [auto-generate]: | ||
|
|
||
| ✔ Config saved → ./litellm_config.yaml | ||
|
|
||
| ❯ Start the proxy now? (Y/n): | ||
|
Comment on lines
+46
to
+50
Contributor
There was a problem hiding this comment.
The wizard TUI shows Consider adding a sentence after the wizard block, e.g.: "Your master key is printed at the end of the wizard and also stored in |
||
| ``` | ||
|
Comment on lines
+28
to
+51
Contributor
There was a problem hiding this comment.
The This confirms the documentation is being merged ahead of the actual feature from PR #23644. Users who follow this guide will hit an immediate failure at step 2. |
||
|
|
||
| The wizard walks you through: | ||
| 1. Pick your LLM providers (OpenAI, Anthropic, Azure, Bedrock, Gemini, Ollama) | ||
| 2. Enter API keys for each provider | ||
| 3. Set a port and master key (or accept the defaults) | ||
| 4. Config is saved to `./litellm_config.yaml` and the proxy starts immediately | ||
|
|
||
| ### 3. Make a call | ||
|
|
||
| Your proxy is running on `http://0.0.0.0:4000`. Test it: | ||
|
|
||
| ```bash | ||
| curl -X POST 'http://0.0.0.0:4000/chat/completions' \ | ||
| -H 'Content-Type: application/json' \ | ||
| -H 'Authorization: Bearer <your-master-key>' \ | ||
| -d '{ | ||
| "model": "gpt-4o", | ||
| "messages": [{"role": "user", "content": "Hello!"}] | ||
| }' | ||
| ``` | ||
|
Comment on lines
+64
to
+71
Contributor
There was a problem hiding this comment.
The wizard demo in Step 2 shows the user selecting providers Consider adding a note that the model name must match a provider you configured in the wizard, or change the example to reflect the wizard's demo output more explicitly (e.g. |
||
|
|
||
| :::tip Already have pip installed? | ||
| You can skip the curl install and run `litellm --setup` directly after `pip install 'litellm[proxy]'`. | ||
| ::: | ||
|
|
||
| --- | ||
|
|
||
| ## Pre-Requisites | ||
|
|
||
|
|
||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
install.shscript does not exist in the repositoryThe curl command references
https://raw.githubusercontent.com/BerriAI/litellm/main/scripts/install.sh, but noscripts/install.shfile exists anywhere in this repository. Running this command as written will produce a 404 error, likely causing a silent failure or a confusing error message for users.This documentation is tied to PR #23644, but that feature PR does not appear to have been merged yet — the
scripts/install.shfile is absent and so is the--setupCLI flag (see the next comment). Publishing these docs before the feature lands will lead users through a broken getting-started flow.