Skip to main content
Loading navigation
Back to challenges

SEBI DRHP Compliance RAG Pipeline with LlamaIndex

Fintech startups preparing for IPOs face exhaustive SEBI disclosure audits across thousands of financial report pages. Build an automated DRHP compliance audit pipeline using LlamaIndex to extract financial metrics and verify statutory compliance with 95% metric precision.

Business OperationsHosted by Vera
Sign in free to start

What you are building

Build an enterprise SEBI Draft Red Herring Prospectus (DRHP) compliance and auditing pipeline using LlamaIndex structured RAG agents.

How work is evaluated

Evaluation

Evaluates financial metric extraction accuracy and statutory compliance disclosure verification from sample DRHP filings.

Datasets

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

How submissions are scored

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

citation_presence

Verifies that every compliance finding includes specific document page citations

Binary check

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

Dimension 2

metric_extraction_precision

Precision of extracted financial metrics against ground-truth DRHP tables • 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

  • Build advanced RAG pipelines with LlamaIndex SubQuestionQueryEngine

  • Extract complex financial table structures from multi-hundred page PDF prospectuses

  • Validate disclosures against SEBI ICDR (Issue of Capital and Disclosure Requirements) rules

  • Implement automated audit trail generation with citations

Resources

Dataset notes

Extracted text and tabular contents from public Indian startup DRHP filings with SEBI audit annotations.

Challenge setup

Evaluates financial metric extraction accuracy and statutory compliance disclosure verification from sample DRHP filings.

Challenge input

Document text chunk and required disclosure item ID

LlamaIndex

Data framework for LLM applications featuring RAG, indexing, and query tools.

Evaluated output

JSON with status (COMPLIANT|NON_COMPLIANT|INCOMPLETE), page_citation, and findings

Evaluation checks
  • Verifies that every compliance finding includes specific document page citations
  • Precision of extracted financial metrics against ground-truth DRHP tables • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: SEBI IPO Regulatory Compliance Benchmark
  • Metric Extraction Precision target: 0.95
  • 1 public reference case
Configured runtime
  • Python execution harness
  • Python sandbox (unavailable on Versalist)

Shows the first task, up to three tools, and up to three evidence items.

View technical recipe

Configured tools

Action Space
  • Llama Index · Required
  • TensorBoard · Optional
  • Hamming · Optional

Evaluation contract

  • citation_presence · Weight 1
  • metric_extraction_precision · Weight 1

Metrics

  • metric_extraction_precision · Target 0.95

Benchmarks

  • SEBI IPO Regulatory Compliance Benchmark
  • general

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: Document text chunk and required disclosure item ID

    Output: JSON with status (COMPLIANT|NON_COMPLIANT|INCOMPLETE), page_citation, and findings

    Execution harness: Python

Evaluation tools

  • LlamaIndex · Agent Orchestration Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about SEBI DRHP Compliance RAG Pipeline with LlamaIndex