Articles on declarative multimodal backends, agents, and the data infrastructure that replaces a stitch of object storage, databases, vector indexes, and orchestrators.
An Agno agent searches notes stored in a Pixeltable table. sentence-transformers embeds them on the machine, and the embedding index stays on the table. No embedding API key and no vector database server.
Four AI engines, three of them search-grounded, 8 prompts, 96 runs. FastAPI in all 96. Qdrant 46 vs pgvector 33. Orchestration split by prompt and by engine. Citations are not the same as picks.
XDA's Abhinav Raj runs three local jobs on a 16GB RTX 4070 Ti Super for deep research, coding and image generation. Here is the same stack driven from Pixeltable tables, so every answer, script and image is stored, versioned, searchable and re-runnable.
Pixeltable exports one OpenTelemetry trace per table operation, with a span tree for rows, files, and UDF calls. Point that same trace at Langfuse, Arize Phoenix, MLflow, or Opik.
Turn a Pixeltable table into a typed HTTP endpoint: serve it locally, deploy it to Pixeltable Cloud, and call it from Next.js with generated TypeScript types.
Pierre Brunelle
1mo ago
Jev is TypeSafe AI's System One model: text state in, typed probabilities out. It does not chat. LangChain put it in the agent loop. Pixeltable puts it on the row.
Pierre Brunelle
1mo ago
An AI automation workflow is a multimodal table: insert a row, computed columns run, indexes stay current, and HTTP serves the result. Pixeltable is that table — not a Zapier canvas, not an Airflow DAG.
Pierre Brunelle
1mo ago
Ingest MP4 or WAV, transcribe, chapter the episode, cut a highlight. Pixeltable is the episode row — not FFmpeg plus a transcription fleet plus a vector DB.
Pierre Brunelle
1mo ago
Dictation, lab PDF, and a scan on the same row. Whisper and Gemini fill columns. A UDF flags contradictions. Not a diagnostic device. Not three microservices.
Pierre Brunelle
1mo ago
Pair an MP4 with a slide PDF. Split pages, sample frames, retrieve, then cite. Pixeltable is two views on one lecture — not PyMuPDF plus FFmpeg plus Pinecone.
Pierre Brunelle
1mo ago
Ingest ad images (and optional video), read the copy, transcribe the voiceover, score fatigue from spend and days. CLIP finds lookalikes. Not a trained fatigue model.
Pierre Brunelle
1mo ago
Pixeltable is the database, orchestration, and serving layers in one Python file. Images, video, audio, and documents live in tables. A transform is a computed column. An index is a declaration, and so is an HTTP route.
Pierre Brunelle
1mo ago
Ingest MP3s, transcribe on insert, extract objections and competitors, search past calls. Whisper and the LLM are columns. The index follows the transcript.
Pierre Brunelle
2mo ago
Sign up for Cloud, or start locally with the skill and pip install pixeltable.
