Data & Retrieval

Use when Under a few million vectors, or when retrieval joins rows you already have.

Skip when Vector search has become the workload rather than a side feature.

Use when Vector-first workloads with heavy metadata filtering at scale.

Skip when You want no new datastore to operate.

Use when Hybrid or multi-vector search with a graph-shaped data model.

Skip when Your data is genuinely relational and joins matter more than vectors.

Use when Getting a prototype working in an afternoon.

Skip when You need durability, scaling or concurrent writes.

Use when Zero operational work, and vector search is not your core competence.

Skip when Residency, cost predictability or a query language you control.

Use when Billion-scale indexes with a cloud-native deployment.

Skip when You need a small, comprehensible system.

Use when High-recall retrieval at volume, without operating the index yourself.

Skip when You need to tune the index directly.

Use when Partitioning messy documents into retrievable chunks before indexing.

Skip when Your input is already structured.

Use when One index carrying BM25 and dense vectors, with ranking you can tune.

Skip when You need a permissive licence — the Elastic licence is not OSI-approved.

Use when Ranking-heavy retrieval where the ranking function is the product.

Skip when You want a small, low-operations component.

Use when A cross-encoder in the second retrieval stage, to lift precision cheaply.

Skip when You have no way to measure whether recall actually improved.

Use when Multimodal embeddings and a reranker behind one endpoint.

Skip when Embeddings must stay in-house.

Use when Document loaders and splitters, if you are already in that ecosystem.

Skip when Structure matters — fixed-size splitting is rarely the right boundary.

Use when Layout-aware parsing that preserves tables and heading structure.

Skip when Your documents are plain text.

Use when Managed parsing for PDFs, especially the ugly ones.

Skip when Document contents cannot leave your infrastructure.

Use when Data-centric work where retrieval is the centre of the problem.

Skip when You need agent orchestration more than data access.

Use when Agents whose memory is a first-class, inspectable and editable state.

Skip when You want memory to be a detail the framework handles for you.

Use when Data and ML pipelines framed as assets with explicit dependencies.

Skip when You want a task queue rather than a lineage-aware orchestrator.

Use when Python-native flows with a managed cloud option behind them.

Skip when You need deep lineage modelling.

Use when Scheduled batch data engineering, where DAGs are the shared language.

Skip when You are building a latency-sensitive product — it was not designed for one.

Use when One evaluation model for both classical ML and LLM systems.

Skip when You only need LLM-specific tracing.

Use when The model hub, the datasets and the open-source library ecosystem.

Skip when You need a self-hosted artefact registry.

Use when Visual explanations of transformers, RAG and model internals.

Skip when You want depth beyond the intuition.