elastic-vectorsearch-workshop

Elastic Inference Service runs embedding generation inside Elasticsearch Serverless. In the workshop, it is used with acquired GINA dense-vector and reranking models as part of Elasticsearch's vector, hybrid-search, and reranking capabilities. Elastic describes its platform as providing GPU inference through an API for AI applications and agents.

An Elasticsearch hybrid-search retriever that combines lexical BM25 scores with vector-search scores. It applies min-max normalization to scale the scores to 0–1 and exposes tunable weights for controlling the contribution of each retrieval method.

The Unblocked Context Engine Workshop is a hands-on repository-based learning resource that walks through six stacked pull requests for turning a stubbed query playground into a relational context engine over a GitHub repository. It demonstrates schema discovery by sampling documents and merging their structures, identity resolution through fuzzy matching, query planning with schema and date context, and deny-by-default validation with an allowlist of operators and reinjected tenant metadata. A retry loop returns validation and execution errors to the model and exposes the need for full-text search when exact matching fails; the resulting engine also powers a chat agent. The workshop covers retrieval over structured engineering context such as pull requests, review comments, tickets, wikis, and chat, along with schema scaling, continuous ingestion, MCP, and hybrid search.

Agent Context Workshop is a hands-on workshop resource for building and evaluating context layers for coding agents. It uses selected crates from the Qdrant Rust codebase to extract syntax with tree-sitter, resolve symbols and relationships with rustdoc JSON, store the resulting code knowledge graph in Neo4j, and expose graph tools such as search, blast-radius analysis, and implementor lookup to an agent. The workshop compares graph-based agents with grep-style agents using gold-verified questions, deterministic scoring, cached evaluation results, tool-adoption measurements, and trace inspection. Additional notebooks cover static Python resolution with Griffe and an optional Fenic-and-LLM semantic layer. The GitHub repository maintains the workshop through ordered Jupyter notebooks, typed extraction and graph code, evaluation harnesses, tests, committed Qdrant seed data, and a committed evaluation cache; it is licensed under Apache-2.0.

Elasticsearch is a distributed search and analytics engine, scalable data store, and vector database developed by Elastic. It stores and indexes structured or unstructured text, numerical, geospatial, log, and metric data as JSON documents, which clients submit and query through REST APIs or language clients. Documents are organized in indexes and data streams and become searchable in near real time; supported search modes include full-text, vector, and hybrid retrieval for applications such as logs, metrics, application performance monitoring, security analysis, and retrieval-augmented generation. It can be used as a managed deployment through Elastic Cloud or installed and operated independently. The repository also documents a Docker-based local setup with Elasticsearch and Kibana for development and testing, and Kibana provides tools for exploring indexed data, filtering it, and creating visualizations and dashboards.