▶
Fast Document Search: File Upload & Entity Extraction
The Terminology Server's Document Search feature lets you upload PDF, TXT, and DOCX files and automatically extract and map every medical entity found in the text to standardized code systems — SNOMED CT, ICD-10, RxNorm, and more — without typing a single search term. This video walks through the Fast Search mode, which uses a schema-aligned NER model to produce deterministic, repeatable extractions with entities mapped directly to official code systems, and demonstrates the full UI workflow: uploading files, navigating the Document Analysis panel alongside the Coding Results section, filtering by vocabulary or entity label, sorting by confidence score, and exporting coded output as CSV. Fast Search is the right choice when you need consistent, pipeline-ready results tied to a standardized clinical schema.
📚 Documentation: https://nlp.johnsnowlabs.com/docs/en/terminology_server/term_server
Install
on AWS: https://aws.amazon.com/marketplace/pp/prodview-3hta3hebivvrk
on Azure: https://marketplace.microsoft.com/en-us/product/johnsnowlabsinc1646051154808.medical_terminology_server?tab=Overview
🔍 Fast Search Docs: https://nlp.johnsnowlabs.com/docs/en/terminology_server/features/search#fast-search
🎯 Accurate Search Docs: https://nlp.johnsnowlabs.com/docs/en/terminology_server/features/search#accurate-search
🔌 MCP Server (Agent Integration): https://nlp.johnsnowlabs.com/docs/en/terminology_server/features/mcp_server#mcp-server---agent-conn
📓 Code Sample Notebook: https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/master/products/term_server/terminology_mcp
