Data Science

FinanceGPT - Bilingual Financial Intelligence System

A LangGraph multi-agent system integrating vector DBs, GraphRAG, and Knowledge Graphs for finance data, achieving >95% retrieval accuracy with bilingual EN/UR support.

Client: Financial Services Client (Confidential)

01 Overview

Financial professionals dealing with large document libraries - annual reports, regulatory filings, internal research - spend disproportionate time searching for information they know exists somewhere in their corpus. This client needed a system that could answer complex financial questions across hundreds of documents in both English and Urdu, with citation-level accuracy.

We built FinanceGPT: a multi-agent financial intelligence system that ingests heterogeneous financial data (PDFs, CSVs, structured reports) and enables natural language querying with >95% retrieval accuracy.

02 The Challenge

• Financial data is highly structured but spread across PDFs, CSVs, Excel files, and proprietary formats - each requiring specialized parsing
• Relational financial reasoning (e.g., "compare Q3 revenue across subsidiaries with operating margin > 15%") requires graph-based knowledge representation, not just flat vector search
• Bilingual support (English and Urdu) with correct handling of mixed-language documents and RTL text rendering
• >95% retrieval accuracy requirement - meaning responses must cite the exact source passage, not hallucinate
• Strict data confidentiality - the system runs fully on-premise with no data leaving the client's infrastructure

03 Our Solution

• **Hybrid RAG architecture**: Combines dense vector retrieval (Pinecone) with Knowledge Graph traversal (Neo4j) - complex relational queries route to the graph, semantic search routes to the vector index, and a fusion layer merges results
• **Multi-agent LangGraph system**: A router agent classifies incoming queries and delegates to the appropriate specialist (tabular data agent for CSV/Excel, document agent for PDFs, comparison agent for cross-document analysis)
• **Bilingual embedding model**: Fine-tuned multilingual sentence transformer handling EN/UR code-switching common in Pakistani financial documents
• **Structured citation layer**: Every response is grounded with source document, page number, and passage - citations are verified against the source before delivery
• **On-premise LLM**: Deployed with a locally-hosted Mistral model for data confidentiality, with optional OpenAI fallback for complex reasoning tasks

04 Results & Impact

>95% retrieval accuracy verified against a held-out evaluation set of 500 expert-annotated queries
Cross-document financial analysis queries resolved in under 8 seconds
Bilingual support covering 100% of document types in the client corpus
Zero hallucinations on factual financial figures - all responses grounded with citations
Analyst research time reduced by an estimated 60% on document-intensive tasks

Project Details

Category
Data Science
Client
Financial Services Client (Confidential)

Technologies Used

LangGraph LangChain Pinecone Neo4j Mistral OpenAI FastAPI Python Pandas Sentence Transformers Docker

Have a similar challenge?

Let's talk about what we can build for you.

Start a Conversation