John Snow Labs 91d ago

Standard keyword search for "hypertension" in a sentence like "the patient has hypertension and complaints about headache" will surface codes for both terms — context resolution lets you specify which term is the primary target and how many surrounding words (the scope) should influence the embedding calculation. This video walks through the term weight and scope parameters live, demonstrating how adjusting them shifts result relevance, and shows how to layer context resolution on top of vocabulary and domain filters for highly precise, scenario-specific coding. 📖 Search: https://nlp.johnsnowlabs.com/docs/en/terminology_server/features/search 📚 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 🔌 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_strands_demo.ipynb