Skip to main content
Back to challenges
Challenge

LlamaIndex Institutional VC Portfolio & Financial Intelligence Agent

Venture capital analysts tracking rapid startup investments need unified RAG pipelines over complex regulatory, financial SEC/ROC filings, and news roundups. Build an advanced RAG engine using LlamaIndex to query funding momentum and valuation signals.

Business OperationsHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Construct an advanced financial document RAG agent using LlamaIndex sub-question query engines.

Delivery guide

How work is evaluated

Evaluation

Evaluates financial query answer recall, table data extraction, and hallucination rate.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

funding_total_matches

Validates exact match on retrieved financial sum.

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

faithfulness

RAG answer faithfulness metric • target: 0.95 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Implement LlamaIndex hierarchical indexing and SubQuestionQueryEngine

  • Parse multi-table balance sheets and unstructured investor updates

  • Synthesize deal trends and funding inflow patterns across funding rounds

Resources and assets

Reference links and supporting material

Dataset notes

Venture capital transaction logs, press releases, and ROC filings.

Challenge setup

Evaluates financial query answer recall, table data extraction, and hallucination rate.

Challenge input

JSON query string

LlamaIndex

Mandatory framework requirement

Evaluated output

JSON answer output with cited source chunks

Evaluation checks
  • Validates exact match on retrieved financial sum.
  • RAG answer faithfulness metric • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: FinRAG-Bench
  • Faithfulness target: 0.95
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Llama Index · Required
  • deepchecks · Optional
  • Voiceflow · Optional

Evaluation contract

  • funding_total_matches · Weight 1
  • faithfulness · Weight 1

Metrics

  • faithfulness · Target 0.95

Benchmarks

  • FinRAG-Bench
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON query string

    Output: JSON answer output with cited source chunks

    Execution harness: Python

Evaluation tools

  • LlamaIndex · Data Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about LlamaIndex Institutional VC Portfolio & Financial Intelligence Agent