mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-16 06:53:47 +00:00
# What does this PR do? As discussed on discord, we do not need to reinvent the wheel for telemetry. Instead we'll lean into the canonical OTEL stack. Logs/traces/metrics will still be sent via OTEL - they just won't be stored on, queried through Stack. This is the first of many PRs to remove telemetry API from Stack. 1) removed webmethod decorators to remove from API spec 2) removed tests as @iamemilio is adding them on otel directly. ## Test Plan |
||
---|---|---|
.. | ||
docs | ||
notebooks | ||
openapi_generator | ||
src | ||
static | ||
supplementary | ||
zero_to_hero_guide | ||
docusaurus.config.ts | ||
dog.jpg | ||
getting_started.ipynb | ||
getting_started_llama4.ipynb | ||
getting_started_llama_api.ipynb | ||
license_header.txt | ||
original_rfc.md | ||
package-lock.json | ||
package.json | ||
quick_start.ipynb | ||
README.md | ||
sidebars.ts | ||
tsconfig.json |
Llama Stack Documentation
Here's a collection of comprehensive guides, examples, and resources for building AI applications with Llama Stack. For the complete documentation, visit our Github page.
Render locally
From the llama-stack docs/
directory, run the following commands to render the docs locally:
npm install
npm run gen-api-docs all
npm run build
npm run serve
You can open up the docs in your browser at http://localhost:3000
Content
Try out Llama Stack's capabilities through our detailed Jupyter notebooks:
- Building AI Applications Notebook - A comprehensive guide to building production-ready AI applications using Llama Stack
- Benchmark Evaluations Notebook - Detailed performance evaluations and benchmarking results
- Zero-to-Hero Guide - Step-by-step guide for getting started with Llama Stack