Tables
Standard SQL data types including text, integers, floating-point values, and Booleans.
samtSQL
Semantic Analytics on Multimodal Tables
samtSQL lets you write SQL with AI operators over text, images, audio, and tables stored in your existing PostgreSQL database.
HouseAds Illustrative rows
id city year br price photo
1
Oshawa, ON
2008
4
$565,000
2
Marbella, ES
2015
4
$875,000
3
Yellow Springs, OH
1942
2
$310,000
4
Alicante, ES
2018
5
$1,120,000
5
Marblehead, MA
1908
5
$780,000
SELECT AVG(price)
FROM HouseAds
WHERE year_built > 1980
AND bedrooms >= 3
AND AIFILTER(photo, 'the house has a pool');Result $997,500 avg. over rows 2 and 4
Step 1
Connect your existing PostgreSQL database.
Step 2
Upload CSV or ZIP files containing images, audio, or text data.
Step 3
Run SQL with AI operators using REST API or visual interface.
Ingest and analyze mixed data workloads in one environment.
Standard SQL data types including text, integers, floating-point values, and Booleans.
AI analysis over common image formats such as JPEG and PNG.
Document and free-text analysis stored directly in relational tables.
Analyze audio files such as MP3 and WAV with AI operators.
Express analytical intent in natural language while staying in SQL.
Filter multimodal data with natural-language conditions.
Classify records with label names only.
Assign scores based on natural-language criteria.
Transform or extract information with natural-language instructions.
Join datasets using semantic matching rules defined in natural language.
Each uploaded format is available as a first-class input for SQL + AI workflows.
Structured tabular uploads for relational analysis.
Archive container for mixed multimodal assets.
Compressed image format for visual analysis tasks.
Lossless image format with high visual fidelity.
Image format supported for uploaded media datasets.
Modern web image format for compact storage.
Compressed audio format for speech and sound data.
Uncompressed audio format for detailed signal quality.
Pricing
Every plan unlocks the full SQL + AI operator set on PostgreSQL. Each plan bundles a monthly allotment of AI Credits for LLM usage and a per-day allowance of query compute time.
$9 / month
$29 / month
$99 / month
*Daily compute time resets at 00:00 UTC.
Switch between representative use cases and inspect each SQL pattern with syntax highlighting.
Count customers who mention pricing concerns in free-text responses.
SELECT COUNT(*)
FROM SurveyResults
WHERE AIFILTER(Comments, 'the customer complains about the price');Tag uploaded holiday images with semantic classes in one query.
SELECT AICLASSIFY(pic, 'beach picture', 'city visit', 'other')
FROM HolidayImages;Turn MP3 clips stored in your tables into plain-text transcripts with one query.
SELECT AIMAP(content, 'Transcribe this audio into plain text.') AS transcript
FROM AudioClips
WHERE filename LIKE '%.mp3';Sort comments by positivity score to prioritize outreach.
SELECT *
FROM SurveyResults
ORDER BY AISCORE(Comments, 1, 10, 'Positivity');Condense long tickets into short summaries for triage.
SELECT AIMAP(ticket_body, 'Summarize the customer issue in two sentences')
FROM SupportTickets;Match equivalent products from independent datasets with semantic joins.
SELECT *
FROM ProductDB1 P1, ProductDB2 P2
WHERE AIJOIN(P1.productName, P2.productName, 'this is the same product');Read endpoint-by-endpoint API docs, operator specs, and practical tutorials for both the visual interface and Python REST clients.
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。