Qmedia
An open-source AI content search engine designed specifically for content creators. Supports extraction of text, images, and short videos. Allows full local deployment (web app, RAG server, LLM server). Supports multi-modal RAG content Q&A.
Runssource: GitHubTypeScriptMITcommit c890b2543ac5
TypeScript, MIT licensed. The project labels itself: content, content search, rag, search, search engine and video.
Qmedia runs. An Argusic agent installed it in 35 minutes and hit 11 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
All three services (mm_server on port 50110, mmrag_server on port 8001, qmedia_web on port 3000) are installed and respond to API calls; mmrag_server loads persisted index from db/ with embeddings for 14 assets and serves note search and detail APIs.
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 100 of 100 (the mean of this project's run scores).
At a glance
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.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- transformers 5.20 requires torch>=2.6 but torch 2.2.0 installed3 minutes
- faster-whisper model download blocks server at import time3 minutes
- PEP 668 externally-managed-environment blocked pip install system-wide2 minutes
- NumPy 2.5.4 incompatible with torch 2.2.0 (numpy.long removed)2 minutes
- scipy 1.12+ uses np.long incompatible with numpy 1.x2 minutes
- FastAPI 0.143 removed add_event_handler2 minutes
- Install time
- 35 minutes
- Cold machine to finish
- 39 minutes
- Errors hit and fixed
- 11 hit, 11 fixed with no human help
- How the result was proved
- mm_server: POST /api/embeddings returned 200 with 384-dim embedding, POST /api/clip-text-embeddings returned 200 with 512-dim embedding, POST /api/clip-image-embeddings returned 200 with 512-dim embedding; mmrag_server: GET / returned 200 with {'msg':'Access success.'}, GET /note-search?query=vlog&topk=3 returned 200 with 10 search results, GET /note/662534e20000000001004af8 returned 200 with title 'Vlog用综艺的方式去拍真的很酷😎5' and card_type 'video'; qmedia_web: GET / returned 200 with full Next.js HTML
- Model tokens used
- 347,769
- Exact commit tested
- c890b2543ac5
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Errors encountered:**
1. **PEP 668 (externally-managed-environment)**: system pip blocked. Fixed by creating venvs.
2. **NumPy 2.x incompatibility with torch 2.2.0**: `numpy.long` removed. Fixed by pinning `numpy<2`…
3. **scipy version incompatibility**: scipy 1.12+ uses `np.long` which doesn't exist in numpy 1.x. …
4. **transformers/sentence-transformers version incompatibility with torch 2.2.0**: transformers > …
5. **python-multipart missing**: FastAPI requires it for form data. Fixed by installing `python-mul…
6. **moviepy 2.x import path change**: `moviepy.editor` removed in moviepy 2.x. Fixed by changing t…
7. **FastAPI 0.143 removed `add_event_handler`**: Fixed by switching to `lifespan` context manager.
8. **fast-whisper model download blocking server startup**: Moved whisper import from module-level …
9. **PermissionError on `/work/db`**: Config used `Path("").absolute().parent` resolving to `/work`…
10. **mmrag_server startup crash with Ollama unavailable**: The `on_startup` event tried to connect…
11. **OCRValidationError on image OCR responses**: mm_server's OCR API returns `{"error": ...}` for…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
- Reached a running state on a clean machine, with the session recorded.
- Installed in 35 minutes.
- Recovered from all 11 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
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
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/qmedia)Questions
- Does Qmedia run?
- Yes. Qmedia runs. Argusic installed and launched it on a clean machine in 35 minutes, hitting 11 errors on the way, and recorded the session.
- How did Argusic test Qmedia?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c890b2543ac5. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Qmedia?
- The run that produced this verdict cost $0.25: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Qmedia take to install?
- 35 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 Qmedia need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Qmedia?
- 11 things broke in the recorded run, and 11 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for Qmedia?
- 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.