wikipedia-semantic-search

Semantic Search on Wikipedia with Upstash Vector

Runs with mockssource: GitHubhomepageTypeScriptMITcommit e0bad8f0c256

TypeScript, MIT licensed. The project labels itself: ai, search, semantic, vector and vector database.

wikipedia-semantic-search runs, with stand-ins for the services it depends on. An Argusic agent installed it in 30 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

pnpm install and next build succeed; next start serves / with HTTP 200 and the full chat/search pipeline runs end-to-end against local schema-correct Upstash/OpenAI mocks, with retrieval context and streaming answers verified via the installed SDKs; connecting real Upstash/OpenAI credentials is the only remaining external step.

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.94 (measured)
recorded runs
1
last tested
stars
471
forks
35
open issues
2
watchers
8
size
0 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing wikipedia-semantic-search, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • mock-only: chat endpoint returned 500 because history pipeline needed list semantics (pipeline result array) and vector query mock routing/response shape were incomplete; later the mock LLM was bypassed by the app hardcoding https://api.openai.com/v115 minutes
  • README/.env documents UPSTASH_* and QSTASH_TOKEN but src/lib/rag-chat.ts hardcodes the OpenAI provider base URL to https://api.openai.com/v1, so the chat LLM cannot be pointed at a local mock via env15 minutes
  • production next start exited after .next lost BUILD_ID following a dev run; first start with mock env also died at container exec teardown8 minutes
  • next build failed during page data collection: UPSTASH_VECTOR_REST_TOKEN is missing (env not configured)5 minutes
  • pnpm not installed in container (no root)2 minutes
Install time
30 minutes
Cold machine to finish
30 minutes
Errors hit and fixed
5 hit, 5 fixed with no human help
How the result was proved
curl -s -o /dev/null -w %{http_code} http://127.0.0.1:3000/ returned 200 (HTML contains 'Wikipedia Semantic Search by Upstash Vector'); curl -c cookiejar -o /dev/null http://127.0.0.1:3000/ set a sessionId cookie via middleware; pnpm build exited 0 ('Generating static pages (5/5)'); index.query({data}) against the vector mock returned the seeded Eiffel Tower document, and ragChat.chat with streaming returned 'Mock answer for: ...ctx=The Eiffel Tower is a wrought-iron lattice tower in Paris, France...,q=What is the Eiffel Tower? [mock]'
Model tokens used
4,743,999
Exact commit tested
e0bad8f0c256
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

/bin/sh -lc "echo \"ARGUSIC_RESULT:\"; echo '{\"install_succeeded\": true, \"launch_succeeded\": tr…
 exited 2 in 0ms:
/bin/sh: 1: Syntax error: "(" unexpected
exec
/bin/sh -lc "cat > /tmp/result.json <<'EOF'
{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 30, \"errors\": [{\"…
EOF
python3 -c \"import json; json.load(open('/tmp/result.json')); print('json valid')\" && printf 'ARG…
 succeeded in 0ms:
json valid
tokens used
4,743,999

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Recovered from all 5 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 30 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 237 ai projects Argusic has installed and timed, wikipedia-semantic-search was the 224th fastest to reach a running state, and 168 of 237 reached one at all.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.000.94

Topics (from GitHub)

aisearchsemanticvectorvector-database

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/wikipedia-semantic-search.svg)](https://argusic.com/subject/wikipedia-semantic-search)

Questions

Does wikipedia-semantic-search run?
wikipedia-semantic-search runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 30 minutes, hitting 5 errors on the way, and recorded the session.
How did Argusic test wikipedia-semantic-search?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit e0bad8f0c256. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test wikipedia-semantic-search?
The run that produced this verdict cost $0.94: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does wikipedia-semantic-search take to install?
30 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does wikipedia-semantic-search need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing wikipedia-semantic-search?
5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does wikipedia-semantic-search compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, wikipedia-semantic-search was the 224th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for wikipedia-semantic-search?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion