ai-research-assistant
Vinay Kumar# AI Research Assistant (LLM-Powered RAG) - Complete Project Specification ## Project Overview This project is being built for a college placement hackathon organized by a fintech/brokerage company. The goal is to build an AI-powered financial research assistant capable of answering natural-language questions about Indian publicly listed companies. The assistant should provide accurate, grounded, citation-backed responses using Retrieval-Augmented Generation (RAG) instead of relying solely on the LLM's internal knowledge. The product is designed as an embedded AI assistant inside a stock brokerage application. --- # Primary Objectives The assistant should be able to answer questions like: * Summarize TCS's latest quarterly results. * Compare HDFC Bank and ICICI Bank. * What are the major risks facing Asian Paints? * What are Reliance's future growth drivers? * Explain Infosys revenue growth. * Summarize recent news about Tata Motors. * What are the key highlights from the latest annual report? Every answer must be grounded using retrieved documents and must include citations. --- # Companies Covered The project currently supports 20 large-cap Indian companies including: * Reliance * TCS * Infosys * HDFC Bank * ICICI Bank * SBI * Bharti Airtel * ITC * Asian Paints * Tata Motors * Maruti * L&T * Bajaj Finance * Kotak Bank * Axis Bank * Sun Pharma * NTPC * UltraTech Cement * Hindustan Unilever * Mahindra & Mahindra --- # Data Sources ## Synthetic Knowledge Base Synthetic data is allowed in the hackathon. Instead of downloading massive annual reports, a curated synthetic knowledge base has been created. Each company has three markdown documents. Example: knowledge_base/ TCS/ * company_knowledge.md * quarterly_results.md * recent_news.md AsianPaints/ * company_knowledge.md * quarterly_results.md * recent_news.md etc. --- ## company_knowledge.md Contains * Company Overview * Business Segments * Products & Services * Financial Highlights * Competitive Advantages * Risk Factors * Industry Outlook * Future Strategy --- ## quarterly_results.md Contains * Revenue * PAT * EBITDA * EPS * Operating Margins * Key Highlights * Management Commentary * Future Guidance --- ## recent_news.md Contains multiple realistic news articles including * Title * Date * Publisher * Summary This simulates Yahoo Finance news. --- # Backend Stack Python FastAPI MongoDB Google Gemini API Sentence Transformer Embedding Model --- # Frontend Stack React Vite Tailwind CSS Axios --- # RAG Pipeline Document Loader ↓ Read Markdown Files ↓ Metadata Extraction ↓ Chunking ↓ Embedding Generation ↓ Store Chunks in MongoDB ↓ Semantic Retrieval ↓ Prompt Builder ↓ Gemini ↓ Response + Citations --- # Chunking Strategy Chunk Size Approximately 500 words Overlap Approximately 100 words Chunks should preserve semantic meaning. Avoid splitting sections in the middle. --- # Metadata Each chunk should include metadata. Example { company: "TCS", ticker: "TCS", document_type: "company_knowledge", section: "Risk Factors", chunk_id: 21, source: "company_knowledge.md" } This metadata will later be used for citations and filtering. --- # MongoDB Structure Collection: documents Each document contains { company, ticker, document_type, chunk_id, section, text, embedding } --- # Retrieval Flow User asks a question ↓ Extract company names (if present) ↓ Retrieve relevant chunks ↓ Rank by semantic similarity ↓ Return Top-K chunks ↓ Pass retrieved context to Gemini --- # Prompt Design System Prompt "You are an AI Financial Research Assistant. Answer ONLY using the supplied context. Do not invent facts. If information is unavailable, clearly state that the context does not contain the answer. Always provide citations." --- # LLM Google Gemini Responsibilities * Read retrieved context * Generate grounded answer * Never hallucinate * Produce concise financial explanations * Add citations --- # Citations Each response should include citations like Source: Company Knowledge Section: Risk Factors or Quarterly Results Management Commentary --- # Frontend Requirements Pages Home Search Company Stock Detail Page AI Assistant Panel --- ## AI Assistant Chat interface User enters question ↓ Backend API ↓ Response displayed with citations --- # Suggested UI Left Company Information Center Stock Details Right AI Research Assistant Below answer Sources Used --- # Backend API POST /chat Input { "query":"Summarize TCS latest quarterly results." } Output { "answer":"...", "citations":[] } --- # Future APIs POST /compare POST /summarize POST /search --- # Expected Features Mandatory ✓ Question Answering ✓ Company Comparison ✓ Quarterly Report Summary ✓ News Summary ✓ Citation Support Stretch ✓ Streaming Responses ✓ Suggested Follow-up Questions ✓ Conversation Memory ✓ Bull vs Bear Analysis --- # Folder Structure project/ frontend/ backend/ knowledge_base/ TCS/ company_knowledge.md quarterly_results.md recent_news.md Infosys/ ... embeddings/ prompts/ models/ api/ docs/ README.md --- # Development Workflow Phase 1 Knowledge Base Completed Phase 2 Document Loader Chunking Metadata Extraction Embedding Generation Phase 3 MongoDB Storage Semantic Retrieval Phase 4 Gemini Integration Prompt Engineering Citation Generation Phase 5 Frontend React Vite Tailwind Chat UI Phase 6 Testing Presentation Demo --- # Success Criteria The assistant should * Answer questions correctly. * Use only retrieved context. * Produce concise financial summaries. * Cite sources. * Work with all 20 companies. * Respond in under 5 seconds. * Have a clean modern interface. The project should resemble an AI assistant integrated into a modern stock brokerage platform rather than a generic chatbot.
Comments (0)
Sign in to leave a comment
Intelligent Financial
Research at Your Fingertips
Ask questions about Indian large-cap companies. Get citation-backed answers powered by Gemini and real document retrieval.
What are the latest quarterly results for TCS and how do they compare to Infosys and Wipro?
TCS Q3 FY2025 Financial Performance Analysis
Tata Consultancy Services reported strong Q3 FY2025 results with consolidated revenue of ₹59,381 crore, marking a 6.8% year-over-year growth driven primarily by its cloud and AI transformation services.1 The company's operating margin expanded by 40 basis points to 25.2%, reflecting improved operational efficiency across delivery centers.2
The BFSI vertical — TCS's largest revenue segment contributing 32% of total revenue — showed signs of recovery with 4.2% sequential growth as North American banking clients resumed discretionary technology spending.3 The manufacturing and life sciences verticals grew 11.3% and 9.7% YoY respectively, outpacing the company average.
Key Highlights
Citations & Sources
8Tata Consultancy Services reported consolidated revenue of ₹245,315 crore for FY2025, a year-on-year increase of 8.2%. The company added 37,000 employees during the year, bringing total headcount to 637,000. Operating margin expanded by 120 bps to 25.4%, driven by automation-led productivity improvements and strong deal wins across the BFSI and retail verticals.
Reliance Industries achieved gross revenue of ₹1,001,534 crore for the fiscal year 2025, marking the first time the conglomerate has crossed the ₹10 lakh crore revenue milestone. The retail segment grew 23% year-on-year, while the digital services arm added 42 million new subscribers. Jio Platforms continued its market leadership with 485 million active users.
HDFC Bank posted a net profit of ₹16,736 crore for Q3 FY2025, up 16.2% from the same quarter last year. Net interest income grew 12.8% to ₹31,200 crore, while the net interest margin held steady at 3.65%. Gross non-performing assets declined to 1.12% from 1.35% a year ago. The bank's CASA ratio improved to 38.7%.
Infosys reported revenue of $4,939 million for Q3 FY2025, a sequential increase of 3.1% in constant currency. The company raised its FY2025 revenue guidance to 4.5%-5.0% growth. Large deal TCV reached $2.5 billion for the quarter. Digital transformation deals and cost optimization programs remained key growth drivers across North America and Europe.
Tata Motors announced a ₹16,000 crore investment plan to expand its electric vehicle manufacturing capacity across its Pune and Sanand plants. The company aims to produce 500,000 EVs annually by 2028. JLR, its British subsidiary, reported record revenue of £29 billion, driven by strong demand for the Range Rover and Defender models. The company's domestic PV market share reached 13.9%.
Asian Paints registered consolidated revenue of ₹35,492 crore for FY2025, growing 6.5% over the previous year. The decorative paints segment maintained market leadership with a 59% share. The company expanded into the home décor space through its Beautiful Homes stores, reaching 200 stores across 100 cities. Raw material cost moderation helped improve gross margins by 180 bps.
ICICI Bank reported a standalone net profit of ₹11,053 crore for Q3 FY2025, a year-on-year increase of 14.8%. The bank's net interest income rose 13.4% to ₹19,400 crore. Core operating profit grew 11.2% to ₹15,800 crore. Total advances grew 18.2% year-on-year, driven by strong retail loan growth across home loans, auto loans, and personal loans.
Wipro secured a $650 million contract from a leading European telecommunications provider for a five-year digital transformation engagement. The deal includes AI-driven network optimization, cloud migration, and customer experience platform modernization. This is Wipro's largest deal win in the current fiscal year and signals strengthening demand recovery in key verticals.
No comments yet. Be the first!