Sage
Universal Document Intelligence & Organizational Q&A Engine.
“Upload Excel sheets, PDFs, and CSVs and instantly query complex cross-departmental data with grounded organizational context.”
Replace with high-res UI dashboard screenshot, mockup, or banner (Recommended 1920x1080)
From Siloed Files to Instant Organizational Answers
Sage was conceived to solve the universal problem of organizational file sprawl: critical operational truth is locked across messy Excel financial models, vendor contract PDFs, customer survey CSVs, and policy documents. Sage provides a drag-and-drop ingestion gateway that parses, chunks, and semantically links heterogeneous files—empowering cross-functional teams to ask any question and receive instant, cited, cross-file intelligence connected directly to the organization's wider context.
Project at a Glance
A universal document intelligence platform that ingests unstructured PDFs, tabular spreadsheets, and raw CSVs, embedding them into a unified queryable knowledge graph for natural language exploration.
Multi-Format Document Ingestion, Hybrid Vector Search & Enterprise RAG
Operations, Finance & Cross-Functional Enterprise Teams
Q2 - Q4
90% reduction in ad-hoc document lookup time with cross-file query synthesis across Excel, PDF, and CSV files.
The Problem
Organizations generate mountains of documents every day, but knowledge remains trapped in silos. An operations lead looking for answers must cross-reference a Q3 budget Excel spreadsheet, a 50-page vendor service level PDF, and a customer feedback CSV. Standard LLMs hallucinate numbers or truncate large spreadsheets, while generic search engines only return keyword hits without synthesizing answers.
Tabular Data Blindness: Standard RAG pipelines treat spreadsheet rows as plain text, destroying numerical relationships and header associations.
Multi-Format Fragmentation: Teams waste hours manually correlating metrics from CSV dumps with contractual requirements in PDF files.
Hallucination in Financial/Operational Queries: LLMs generating plausible-sounding numerical summaries that do not match underlying ledger cells.
Zero Organizational Context: Generic file chat tools lack organizational domain awareness, treating company-specific acronyms and department codes as gibberish.
Goals
Technical Goals
- Multi-modal document parser preserving tabular structure from .xlsx, .csv, and scanned .pdf files.
- Hybrid retrieval combining dense vector embeddings with BM25 keyword and exact SQL/table queries.
- Sub-2-second question-answering over multi-gigabyte corporate document collections.
- 100% cited answers linking directly to page numbers, row indices, and source file metadata.
Business Goals
- Empower any employee to ask complex cross-departmental questions in natural language.
- Eliminate hours of manual spreadsheet auditing and document reading per team member each week.
- Accelerate onboarding and institutional knowledge transfer across departments.
My Role
Lead AI Systems Architect
Core Responsibilities
- Engineered the multi-format ingestion pipeline handling complex Excel sheets, formulas, and PDF layouts.
- Designed the hybrid retrieval architecture combining vector embeddings with tabular SQL generation.
- Formulated prompt synthesis templates enforcing exact cell-and-page citations.
- Built the FastAPI streaming backend and responsive document query workspace.
Primary Focus Areas
Solution
Sage ingests diverse documents (Excel, PDF, CSV), extracts tabular matrices and semantic passages, tags them with organizational metadata, and indexes them into a unified retrieval engine. When a user asks a question, Sage decomposes the query, fetches relevant spreadsheet numbers and policy paragraphs in parallel, and synthesizes a definitive answer with clickable citations.
Structure-Aware Table Extraction
Converts Excel grids and CSV data into queryable SQL tables and semantic markdown representations.
Cross-Document Contextual Fusion
Connects numbers in spreadsheets with explanations in accompanying PDF documentation.
Grounded Citation Guarantee
Every answer cites the exact filename, sheet tab, row number, or PDF page.
Architecture & Data Flow
End-to-end data pipeline connecting drag-and-drop document upload, multi-modal table extraction, hybrid vector/SQL indexing, query decomposition, and streaming grounded synthesis.
Drag & Drop Multi-Format Ingestion
FastAPI / PythonUploads Excel spreadsheets, CSVs, and PDFs via FastAPI with instant MIME validation.
Multi-Modal Parsing & Structuring
Unstructured.io / PandasUnstructured.io and Pandas extract text passages, layout bounding boxes, and tabular rows into structured schemas.
Hybrid Vector & Metadata Indexing
Qdrant / SQLite / BGE EmbeddingsText embeddings pass to Qdrant vector store; tabular matrices convert into queryable SQLite database tables.
Intent Decomposition & Multi-Hop Querying
LangChain / OpenAI GPT-4oQuery router splits prompt into qualitative semantic lookup and quantitative SQL aggregation.
Grounded Synthesis & Verifiable Citations
Server-Sent Events / SSEStreams answer back to user with clickable badge citations linking to specific cells or PDF pages.
Core Features
Universal File Ingestion Engine
All file formats supportedDrop in Excel spreadsheets, CSV exports, contract PDFs, and meeting docx files with zero manual tagging.
Cross-File Synthesis ('Kaboom' Q&A)
Cross-document intelligenceAsk questions that require connecting numbers in an Excel budget with vendor rules in a PDF agreement.
Exact Cell & Page Level Citations
100% cited answersEvery claim and number cites its exact origin: 'Q3_Financials.xlsx [Sheet: Opex, Row 42, Col D]'.
Organizational Acronym & Domain Memory
Domain-aware intelligenceUnderstands your organization's internal jargon, departmental abbreviations, and project codenames.
Engineering Decisions
Dual-Path Tabular Routing vs Naive Text Chunking
Why: Treating spreadsheets as text leads to catastrophic mathematical hallucinations; routing tabular data to an in-memory SQL engine ensures 100% accurate arithmetic calculations.
Challenges
Mathematical Hallucination: LLMs calculating inaccurate totals when reading raw numbers from text chunks.
Engineered a programmatic Python REPL tool gateway that executes actual code over extracted tables rather than relying on LLM mental math.
Zero mathematical errors across financial and inventory calculations.
Implementation Timeline
Multi-Format Extractor Engine
- Excel formula parser
- PDF layout bounding box extractor
- CSV sanitizer
Vector & Tabular Architecture
- Qdrant vector cluster setup
- SQLite dynamic table generator
- BM25 keyword search index
Query Decomposition & Synthesis
- Intent splitter
- Code execution sandbox
- Citation highlighter component
Enterprise Testing & Launch
- Departmental pilot testing
- Accuracy evaluation benchmark
- Production release
Results & Metrics
Verified accuracy across complex questions correlating spreadsheets and policy documents.
Sub-2-second query synthesis across multi-gigabyte organizational document archives.
Guaranteed 100% computational precision via programmatic table code execution.
Screenshots
Drop high-resolution interface screenshot here (Recommended 1920x1080)
Universal File Ingestion & Knowledge Base Explorer
Drag-and-drop workspace showing parsed Excel sheets, PDFs, and CSV datasets with entity tags.
Drop high-resolution interface screenshot here (Recommended 1920x1080)
Cross-File Synthesis View with Grounded Cell & Page Citations
Interactive conversational answer linking directly to specific spreadsheet cells and PDF highlights.
Demo Video
Sage Walkthrough Demo: 2-minute video demonstrating dropping an Excel budget sheet and a vendor contract PDF into Sage, asking cross-referencing questions, and viewing instant cited results.
Add iframe or video src in lib/case-studies-data.ts
Demonstration Highlights:
Lessons Learned
Never ask an LLM to perform arithmetic on raw text tables; parse the table into code-executable data structures and use programmatic execution.
Cross-referencing spreadsheets with qualitative policy PDFs requires decoupling numerical retrieval from semantic passage retrieval.
Tech Stack
NLP & Multi-Modal AI
Document Parsing & Data
Storage & Search
Backend & Frontend
Business Impact
Sage transformed fragmented corporate file folders into an active, intelligent oracle for daily operations.