Engineering financial RAG
Fourteen technical articles on the client’s equity analyst platform, from requirements and parsing economics to citations, agentic research and operations.
Read or print the complete series · Visual guide
A million documents, six weeks, and a $50,000 constraint
Starting with the equity analyst’s workflow, then turning commercial constraints into engineering decisions.
A financial corpus begins with identity, time and provenance
Sourcing filings and transcripts without losing amendments, availability dates, permissions or lineage.
A correctly read number can still be the wrong financial fact
Tables, footnotes, units, reading order and the contract between a parser and a retrieval system.
Bringing a $120,000 parsing iteration inside a $50,000 budget
The 2025 move from LlamaParse to Mistral, the 60% cost reduction, and what changes in 2026.
Chunk the evidence, not just the text
Filing sections, speaker turns, table rows and the hidden difference between word and token budgets.
Choosing embeddings for financial evidence
Financial BGE, SPLADE, Matryoshka dimensions and the cost of changing a million-document index.
Finding the right issuer, period and passage
Dense and sparse retrieval, metadata constraints, rank fusion and candidate-depth experiments.
From fifty candidates to an answerable evidence set
Cross-encoders, query rewriting, truncation, context packing and evidence diversity.
A citation should take the analyst to the evidence
Paragraph identity, PDF coordinates, HTML highlighting and the interface that makes answers inspectable.
Make the calculation inspectable, too
Grounded synthesis, financial units, deterministic arithmetic, contradictions and streaming answers.
When financial research needs more than one retrieval step
A bounded agentic RAG design with typed tools, an evidence ledger, cost limits and explicit stopping rules.
Evaluate the evidence chain, not just the final answer
Parser, retrieval, calculation, citation and agent evaluations that explain where quality was lost.
Operating RAG across a million financial documents
Durable ingestion, separate serving paths, latency budgets, AWS and GCP deployment designs.
The engineering decision that made the product affordable
Six-week delivery, parsing economics, analyst value, further funding and the next system improvements.