Jina AI

Reading on retrieval

• Fix the ranking, not the promptWhen a RAG system gives a bad answer, the instinct is to rewrite the prompt. Nine times out of ten the prompt is fine and the context was never there.

• RerankersPurpose-built cross-encoders for the second retrieval stage.

Listed as an alternative to

• RerankersRerankersPurpose-built cross-encoders for the second retrieval stage.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.proprietary · saas · usage-based

Also in retrieval

• pgvectorpgvectorVector similarity search as a Postgres extension.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.PostgreSQL · self-hosted · free
• QdrantQdrantRust vector database with rich filtering payloads.Use when Vector-first workloads with heavy metadata filtering at scale.Skip when You want no new datastore to operate.Apache-2.0 · self-hosted · free
• WeaviateWeaviateGraph-aware vector database with hybrid and multi-vector search.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.BSD-3-Clause · self-hosted · free
• ChromaChromaEmbeddings database designed for fast prototyping.Use when Getting a prototype working in an afternoon.Skip when You need durability, scaling or concurrent writes.Apache-2.0 · self-hosted · free
• PineconePineconeFully managed vector database with serverless scaling.Use when Zero operational work, and vector search is not your core competence.Skip when Residency, cost predictability or a query language you control.proprietary · saas · usage-based
• MilvusMilvusCloud-native vector database supporting billion-scale indexes.Use when Billion-scale indexes with a cloud-native deployment.Skip when You need a small, comprehensible system.Apache-2.0 · self-hosted · free
• TurbopufferTurbopufferVector search engine tuned for high-recall retrieval workloads.Use when High-recall retrieval at volume, without operating the index yourself.Skip when You need to tune the index directly.proprietary · saas · usage-based
• UnstructuredUnstructuredPreprocessing library that partitions raw documents for indexing.Use when Partitioning messy documents into retrievable chunks before indexing.Skip when Your input is already structured.Apache-2.0 · self-hosted · free
• ElasticsearchElasticsearchBM25 plus dense vectors in one index, with hybrid ranking.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.Elastic-License-2.0 · self-hosted · usage-based
• VespaVespaSearch engine built for ranking-heavy retrieval at scale.Use when Ranking-heavy retrieval where the ranking function is the product.Skip when You want a small, low-operations component.Apache-2.0 · self-hosted · free
• RerankersRerankersPurpose-built cross-encoders for the second retrieval stage.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.proprietary · saas · usage-based
• LangChain Text SplittersLangChain Text SplittersDocument loaders and splitters for the ingest stage.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.MIT · self-hosted · free
• DoclingDoclingLayout-aware parsing that preserves table and heading structure.Use when Layout-aware parsing that preserves tables and heading structure.Skip when Your documents are plain text.MIT · self-hosted · free
• LlamaParseLlamaParseManaged parsing for PDFs, especially the ugly ones.Use when Managed parsing for PDFs, especially the ugly ones.Skip when Document contents cannot leave your infrastructure.proprietary · managed · usage-based