chatWeb

ChatWeb can crawl web pages, read PDF, DOCX, TXT, and extract the main content, then answer your questions based on the content, or summarize the key points.

Runs with mockssource: GitHubPythonMITcommit 2e5e1addf422

Python, MIT licensed. The project labels itself: ai, chatgpt, crawler, docx, embedding, faiss, gpt and gpt 35 turbo.

chatWeb runs, with stand-ins for the services it depends on. An Argusic agent installed it in 5 minutes and hit 8 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

ChatWeb launches in both API mode (FastAPI/uvicorn on :9531) and WebUI mode (Gradio on :7860). File upload, summary generation, and Q&A endpoints all return HTTP 200 with correct JSON schema against a mock OpenAI API. The three startup modes (console/api/webui) are all functional; console mode was not interactively tested but shares the same fixed library path.

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
$0.13 (measured)
recorded runs
2
last tested
stars
916
forks
136
open issues
7
watchers
18
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 chatWeb, 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.

  • xxhash v4 requires bytes input for xxh3_128_hexdigest (str→TypeError)4 minutes
  • openai.proxy module-level attribute removed in openai v33 minutes
  • FastAPI /answer declared as GET with Pydantic body (runtime 422/500)3 minutes
  • System pip blocked by externally-managed-environment (PEP 668)2 minutes
  • openai v3 streaming delta is a pydantic model, no .get() method2 minutes
  • psycopg2 fails to build from source (no libpq/pg_config)1 minute
Install time
5 minutes
Cold machine to finish
9 minutes
Errors hit and fixed
8 hit, 8 fixed with no human help
How the result was proved
E2E test: POST /upload_file (text) → 200 with URI; GET /summary?uri=... → 200, code=0, summary present; GET /answer?uri=...&query=... → 200, code=0, answer present. WebUI: curl http://127.0.0.1:7860 → 200, body contains Gradio chat HTML.
Model tokens used
107,761
Exact commit tested
2e5e1addf422
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

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

  'api_host': 'localhost',
  'webui_port': 7860,
  'webui_host': '0.0.0.0'
}
with open('config.json', 'w') as f:
    json.dump(cfg, f, indent=2)
print('Config reset to default')
\"" in /work/repo
 succeeded in 0ms:
Config reset to default
tokens used
107,761

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 8 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

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 5 minutes to install, slower than the median of the 236 comparable projects Argusic has measured.

Of the 237 ai projects Argusic has installed and timed, chatWeb was the 127th 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 Runner2/3Runs with mocks92.000.13
Argusic Runner1/3Runs with mocks92.000.12

Topics (from GitHub)

aichatgptcrawlerdocxembeddingfaissgptgpt-35-turbonews-extractornewspaperopenaipdfpgvectorpostgresqlvector-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/chatWeb.svg)](https://argusic.com/subject/chatweb)

Questions

Does chatWeb run?
chatWeb runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 8 errors on the way, and recorded the session.
How did Argusic test chatWeb?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 2e5e1addf422. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test chatWeb?
The run that produced this verdict cost $0.13: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does chatWeb take to install?
5 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 chatWeb need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing chatWeb?
8 things broke in the recorded run, and 8 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does chatWeb compare with the alternatives?
Of the 237 ai projects Argusic has installed and timed, chatWeb was the 127th fastest to reach a running state, and 168 of 237 reached one at all.
Where is the evidence for chatWeb?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion