Skip to content
Retrieval

Hybrid RAG with reranking and citations

Keyword plus vector search, fused and reranked, answered with sources.

Use it when

Questions over a body of documents, tickets or records where exact terms matter as much as meaning, and where every answer must be checkable and permission-aware.

Structure

The parts, top to bottom

hover a part to see its job

across every level

Hover or tap any part to see what it does. The light shows the order a request moves through.

Flow

What happens, in order

  1. 1Ingest & chunk by structure
  2. 2Enrich with context & metadata
  3. 3Embed + keyword index
  4. 4Query: BM25 + vectors, fuse (RRF)
  5. 5Rerank top candidates
  6. 6Generate with citations
  7. 7Log feedback to evals
Tools

What we typically build it with

pgvector / Qdrant / PineconeElasticsearch / OpenSearchCohere RerankOpenAI / Voyage embeddingsRAGAS

Trade-offs

More moving parts than naive RAG, but the numbers justify them: contextual chunking with BM25 cut retrieval failures by 49% and reranking took that to 67% in Anthropic's evaluation; cross-encoder reranking typically lifts recall@5 by 5–15 points. Naive pipelines answer in 200–500 ms, advanced ones in 0.5–1.5 s.

What we solve

Problems this architecture solves

Generic problem statements with the flow and the outcomes the industry has documented.

Grounded support agent

Support queues that never shrink

Tier-1 questions consume most of the team's day, answers vary by agent, and customers wait. Generic chatbots deflect badly because they do not know your policies or your systems.

How the system works

  1. Customer message
  2. Intent & policy check
  3. Retrieve from your docs & orders
  4. Answer or act via tools
  5. Escalate with context
Hybrid RAGTool callingLangGraphZendesk / IntercomLangfuse

Outcome: Klarna's assistant handled two thirds of customer chats in its first month and cut resolution time from 11 minutes to under two; Intercom reports Fin resolving 76% of conversations on average. Klarna press release

Architecture
Enterprise knowledge assistant

Answers buried in ten systems

Policies live in SharePoint, decisions in email, procedures in Confluence and history in tickets. New staff take months to become useful and experts answer the same questions daily.

How the system works

  1. Connect sources
  2. Chunk with context, embed + index
  3. Hybrid retrieval + rerank
  4. Cited answer with permissions
  5. Feedback into evals
pgvector / QdrantBM25 + embeddingsCohere / Voyage rerankPermission filtersSlack / Teams

Outcome: Contextual chunking with hybrid search and reranking cuts retrieval failures by 67% versus plain vector search, which is the difference between an assistant people trust and one they abandon. Anthropic: Contextual Retrieval

Architecture
Related

Other retrieval patterns

Retrieval

Agentic and graph-based retrieval

The agent decides how to search; a knowledge graph answers the global questions.

Use it when: Multi-hop questions, comparisons across many documents, or questions about themes across a whole corpus where chunk retrieval alone returns fragments.

Flow

  1. 1Question analysed
  2. 2Agent chooses strategy: search, graph, SQL, or ask
  3. 3Runs several retrievals
  4. 4Verifies & consolidates evidence
  5. 5Answers with a reasoning trail
Retrieval

Visual document retrieval (late interaction)

Search scanned forms, slides, drawings and table-heavy PDFs as images, with no OCR pipeline to maintain.

Use it when: Corpora where layout carries meaning: engineering drawings, slide decks, scanned contracts, invoices and financial tables that OCR-based pipelines flatten and lose.

Flow

  1. 1Rasterise each page
  2. 2Encode into patch embeddings (ColPali / ColQwen)
  3. 3Store multi-vectors with MaxSim support
  4. 4Query encoded token by token
  5. 5Top pages passed to a vision model

Let's build intelligent systems that drive growth

Tachyon is the engineering partner for teams that need AI in production, not in a deck. Start with a free 60-minute discovery call.

Contact

Tell us the problem, we will map it to the architecture

Every great partnership begins with a conversation. Whether you are exploring possibilities or ready to scale, tell us what you are actually trying to build.

Prefer to talk?

Pick a 60-minute slot. No pitch, just an engineer with honest answers.

Book a call

NDA available on request. We reply within one business day.