Build the first working CLI LLM summarizer

Build only what the claim requires: fake transport returns a summary string; real adapter is isolated behind env credentials. Prefer boring, deterministic code over frameworks you cannot yet explain. Run the path twice; identical output on this fixture is a feature, not a lack of creativity.

async function summarize(text,transport){const r=await transport({messages:[{role:'user',content:text}]}); return r.choices[0].message.content;}
summarize('hello',async()=>({choices:[{message:{content:'A short summary.'}}]})).then(console.log);

Expected evidence: unreliable LLM API call. Read each printed intermediate as part of the argument that the path works—not as decoration.

Narrate the journey from raw input to result for a single example from system+user job object for an embeddings definition sentence. If you cannot name an intermediate, the implementation is still too opaque for this lab. Only after this path is solid should you generalize data sources or UI.

While implementing the CLI LLM summarizer, print or log at least three intermediates that map to the claim (fake transport returns a summary string; real adapter is isolated behind env credentials). Good intermediates are values a teammate could recompute with a calculator or diff. Bad intermediates are framework traces you cannot explain.

Re-run with system+user job object for an embeddings definition sentence twice. If the second run differs, either the path is nondeterministic (document the seed) or you have hidden global state—both are lab bugs until named.

Stop adding features once the path supports turn one user passage into a bounded one-sentence summary via an HTTP-shaped client. Extra UI, extra tools, or extra models belong in later chapters. The mastery bar for this page is simply: a deterministic end-to-end path with intermediates.

At the implementation stage for llm-api-hello, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about system+user job object for an embeddings definition sentence that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: offline fake transport producing a fixed summary.

For this page specifically, success looks like a deterministic path with printed intermediates while still centering the user decision to turn one user passage into a bounded one-sentence summary via an HTTP-shaped client. If you cannot point to a file, command, or assertion that proves that for the CLI LLM summarizer, stay on this page instead of advancing.

API: chat completions · Glossary: API key

Previous · Next