- Notifications
You must be signed in to change notification settings - Fork0
🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps
License
Python-Repository-Hub/langfuse-docs
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Repo forlangfuse.com, based onNextra
You can easily contribute to the docs using GitHub Codespaces. Just click on the "Code" button and select "Open with Codespaces". This will open a new Codespace with all the dependencies installed and the development server running.
Pre-requisites: Node.js 20+, pnpm v9.5.0
- Optional: Create env based on.env.template
- Run
pnpm ito install the dependencies. - Run
pnpm devto start the development server on localhost:3333
All Jupyter notebooks are in thecookbook/ directory. For JS/TS notebooks we use Deno, see Readme in cookbook folder for more details.
To render them within the documentation site, we convert them to markdown usingjupyter nbconvert, move them to right path in the pages/ directory where they are rendered by Nextra (remark).
Steps after updating notebooks:
- Load python shell/env which has jupyter installed, e.g.
poetry install && poetry shell - Run
bash scripts/update_cookbook_docs.sh - Commit the changed markdown files
Note: All.md files in thepages/ directory are automatically generated from Jupyter notebooks. Do not edit them manually as they will be overwritten. Always edit the Jupyter notebooks and run the conversion script.
We store all images in thepublic/images/ directory. To use them in the markdown files, use the abslute path/images/your-image.png.
We use Cloudflare Video as a video hosting provider. Ping one of the maintainers to upload a video to Cloudflare Video and get the video id.
To embed a video, use the CloudflareVideo component and set a title and fixed aspect ratio.
To embed a "gif", actually embed a video via the CloudflareVideo component and usegifMode (<CloudflareVideo videoId="" gifMode />). This will look like a gif, but at a much smaller file size and higher quality.
Interested in stack of Q&A docs chatbot? Checkout theblog post for implementation details (all open source)
Runpnpm run analyze to analyze the bundle size of the production build using@next/bundle-analyzer.
About
🪢 Langfuse documentation -- Langfuse is the open source LLM Engineering Platform. Observability, evals, prompt management, playground and metrics to debug and improve LLM apps
Resources
License
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Releases
Packages0
Languages
- Jupyter Notebook70.2%
- MDX22.1%
- TypeScript7.1%
- JavaScript0.4%
- CSS0.1%
- PLpgSQL0.1%
