TheDocumentation Index
Fetch the complete documentation index at: https://docs.trulayer.ai/llms.txt
Use this file to discover all available pages before exploring further.
demo-python repository contains a curated set of standalone scripts that show every public surface of the trulayer SDK end-to-end. Each example is intentionally small — one concept per file — so you can copy a pattern straight into your own app.
Status: alpha. The demo scripts currently pin the SDK from a local sibling path while we cut the first public release. Standalone clones will fail to install until
trulayer 0.1.0 is on PyPI. Track the release in the demo-python repo. Once 0.1.0 ships, this notice will be removed.What’s in the repo
- 11 runnable examples under
examples/, one per SDK concept (manual tracing, auto-instrumentation, RAG, agents, streaming, feedback, async, LangChain). - A local mock ingestion server (
examples/mock_server.py) so you can run every example offline. - A pytest suite (
tests/test_examples.py) that asserts each script’s payload shape end-to-end.
Clone and run
Representative examples
basic_trace.py
Manual
trace() and span() around a real OpenAI call — the smallest possible end-to-end example.openai_auto.py
instrument_openai() — patches the client so every chat.completions.create becomes a span automatically.rag_pipeline.py
Embed → retrieve → generate, captured as three typed spans (
retrieval, llm) inside one trace.agent.py
Tool-calling agent loop, with one span per tool invocation and one per LLM turn.
feedback.py
Trace an answer, then attach a thumbs-up
FeedbackData record to it via submit_feedback().Where to go next
Tutorial
Build the same patterns from scratch with a step-by-step walkthrough.
Reference
Every public export, with signatures and types.