Portfolio · Project 06

Alexander CHERNOV

Principal Engineer · Agentic AI & scientific data systems

← the whole portfolio
06

Semantic gateway: search, graph and MCP over any data source

2025 – present · AstraZeneca

One engine over any source — search, grounded chat, an entity graph and MCP, governed on every surface.

Rust and React, desktop and browser. Connected sources become cited answers, a knowledge graph with a live ontology, and tools for Copilot, with access trimmed to each reader. First demonstrated on 4,115 laboratory assets.

Recorded live, in real time, in the gateway's static browser build, over a pseudonymised corpus of 4,115 lab-asset records: people, sites, labs and entity names are invented; the distributions are real. A search in plain words puts 12 hits on the graph; chat says where a freezer is from the record's own fields and cites 5 sources — this build has no language model, so the answer is extractive; the graph changes lens to lab, then status; and the source lists the 13 capabilities it publishes over MCP. Record text and identifiers are hidden in the recording; the notes are read off the page.

A Rust and React semantic gateway. One engine — extract, chunk, embed, index, serve — turns a data source into four surfaces: semantic search, grounded chat with citations, an interactive entity graph, and a Model Context Protocol surface of tools, resources and code-generation prompts for Copilot and any MCP client. Desktop through Tauri, web through WebAssembly. A document is anything a source yields: a file, a database record, an instrument run, an API response.

Sources connect rather than fork. Connectors cover SharePoint, S3, Postgres, SQL Server, local files, a laboratory asset platform's REST API and chromatography systems, and the view is data-driven per source, so adding one is a profile and a connector. Demonstrated on a 4,115-asset corpus.

The graph is a knowledge graph: entity kinds are classes, typed fields are properties, and relations are edges to follow. The ontology is derived live from the data, so it cannot drift from what is there, and a source can declare vocabulary hints — SNOMED CT, FHIR, MeSH, DCAT.

Governance holds on every surface. Attribute-based access control trims search, chat, graph and MCP results to the reader; every typed field keeps its change history; and authentication is configuration — open on a desktop, reverse-proxy SSO, API keys, or per-user OIDC such as Microsoft Entra. Documents can also be embedded in published pages as a card, a detail pane or the full body, resolved on every view and trimmed to the reader's access: a window on the source, not a copy of it.

Architecturally it is a repointing, not a rebuild: the same ingestion, entity graph, ontology and retrieval moved from documents to equipment without redesign. The thesis is a data foundation, not a chatbot — the conversational surface is the demo, the entity graph and its governance are the product.

References

  1. Hogan et al. (2021). Knowledge Graphs. ACM Computing Surveys 54(4), 1–37. doi:10.1145/3447772
  2. Lewis et al. (2020). Retrieval-augmented generation for knowledge-intensive NLP tasks. NeurIPS 2020. arXiv:2005.11401
  3. Model Context Protocol (2025). Model Context Protocol specification, revision 2025-06-18. modelcontextprotocol.io. modelcontextprotocol.io
  4. Chernov (2026). Agentic Datasets as an Engineering Control Plane. IEEE CCECE 2026, 326–332. doi:10.1109/CCECE68150.2026.11610344
  5. Chernov (2026). Agentic Data Services: A Control-Plane Architecture for Adaptive Data Workflows. IEEE BigDataService 2026, 125–129. doi:10.1109/BigDataService70481.2026.00025

No public URL — internal system.