From cd6bc19caa6c4c3a1e03633fec8d110f98382b18 Mon Sep 17 00:00:00 2001 From: Pradip Nichite Date: Fri, 23 Oct 2026 19:55:05 +0530 Subject: [PATCH] Lead the README with what the product does and how to use it Opens with what Document Intelligence does, the three ways to use it (live application, self-hosted install, API), what you can do, and who it is for, then a short research section linking the improvement history, then the screenshots. The detailed AI Demos engineering example moves below the architecture section, unchanged. Verdicts and history untouched. Co-Authored-By: Claude Opus 5.5 --- README.md | 107 +++++++++++++++++++++++++++++++++++++++--------------- 1 file changed, 77 insertions(+), 30 deletions(-) diff --git a/README.md b/README.md index 61f0288..45ee9ff 100644 --- a/README.md +++ b/README.md @@ -1,14 +1,61 @@ # FutureSmart Document Intelligence -**A working, opinionated Document Intelligence application by [FutureSmart AI](https://futuresmart.ai/), released under Apache-2.0. A complete UI and backend reference application that shows how [AI Demos](https://aidemos.com/) research becomes product improvements.** +**An open-source Document Intelligence application by [FutureSmart AI](https://futuresmart.ai/).** -Upload documents into a collection, extract the fields you define into a typed -table, and ask questions answered from the documents with their sources. Use the -web application, or call the same ingestion, search and chat API from your own -software. +Turn documents into structured, searchable information. -**[Try the live application →](https://futuresmart.ai/solutions/document-intelligence)** -FutureSmart's hosted service, nothing to install. To run it yourself, see [Install](#install). +Upload PDFs, invoices, resumes, contracts, reports and other supported documents. +Define the fields you want to extract, organize the results into structured +tables, explore your documents through the Knowledge View, and ask questions +using RAG. + +Use the hosted application, deploy it in your own environment, or integrate its +capabilities through APIs. + +**[Try the Live Application](https://futuresmart.ai/solutions/document-intelligence)** · +**[View Installation Guide](#install)** · +**[Explore the API](docs/api/rag-service.md)** + +Open source · Apache-2.0 · Self-hostable · API accessible + +## What you can do + +**Structured data extraction.** Define fields with their types and descriptions, +process documents, and inspect the extracted values in a structured table. +Search, sort and filter it, and export the results as CSV. + +**Knowledge View.** Explore the documents in a collection, their extracted +fields, summaries and the text read from each file, in one place. + +**Document question answering.** Ask questions about a collection or chosen +documents and get answers grounded in them, with the documents each answer used. + +**Document Intelligence APIs.** Use ingestion, extraction configuration, search +and grounded chat from your own applications through the +[documented REST API](docs/api/rag-service.md). The search API returns the +matching passages themselves. + +## Who it is for + +- **Teams with a pile of documents to read**: invoices for finance and + operations, resumes for recruiting, contracts for legal and procurement, + reports and policies for everyone else. +- **Developers who need document extraction and RAG in their own product**, + through an API instead of building ingestion, indexing and retrieval from + scratch. +- **Engineers who want a working reference architecture** they can read, run, + self-host and change. + +## Improved through real-world AI research + +We evaluate FutureSmart Document Intelligence through the Structured Document +Extraction and Managed RAG benchmarks on [AI Demos](https://aidemos.com/). + +The findings help us identify limitations, investigate issues and improve the +application. We document engineering decisions, fixes, verification results and +ongoing work publicly. + +[Explore our research-driven improvement history →](docs/improvements/README.md) ![Six synthetic invoices in one collection, with currency, due date, invoice number, payment terms, total and vendor extracted into typed columns](docs/images/structured-extraction.jpg) @@ -30,7 +77,29 @@ was drawn from. -## How AI Demos research improves Document Intelligence +## A complete reference application, not just a library + +One repository contains the FastAPI backend, the Next.js web application, the +Celery ingestion/indexing worker, deployment configuration, tests and examples. +The supported stack is Docker Compose with PostgreSQL, Qdrant, Redis and S3/SQS +(LocalStack locally, real AWS for durable deployments). The web UI is optional; +the worker is required. + +What it does: + +- **Collections and ingestion.** PDF, DOCX, TXT, Markdown, HTML, web pages and + audio. Text-based files and web pages are read locally; scanned, layout and + visual modes use an optional LlamaParse key, and Firecrawl is an optional + scraper. +- **Structured extraction.** Define fields with types and descriptions; each + document's values appear in a typed table you can inspect and export as CSV. +- **Grounded answers.** Ask questions about a collection or chosen documents and + see which documents the answer used. The search API returns the matching + passages themselves. +- **RAG as a service.** Authenticated REST API for ingestion, search and chat, + with OpenAPI docs and a server-side example client. + +## How research findings become fixes We test this application in the [AI Demos](https://aidemos.com/) Structured Document Extraction and Managed RAG benchmarks, then use what the testing finds @@ -66,28 +135,6 @@ lists what is and is not published. We prioritize a dependable, deployable product and reproducible evidence over commercial feature parity or a higher benchmark score. -## A complete reference application, not just a library - -One repository contains the FastAPI backend, the Next.js web application, the -Celery ingestion/indexing worker, deployment configuration, tests and examples. -The supported stack is Docker Compose with PostgreSQL, Qdrant, Redis and S3/SQS -(LocalStack locally, real AWS for durable deployments). The web UI is optional; -the worker is required. - -What it does: - -- **Collections and ingestion.** PDF, DOCX, TXT, Markdown, HTML, web pages and - audio. Text-based files and web pages are read locally; scanned, layout and - visual modes use an optional LlamaParse key, and Firecrawl is an optional - scraper. -- **Structured extraction.** Define fields with types and descriptions; each - document's values appear in a typed table you can inspect and export as CSV. -- **Grounded answers.** Ask questions about a collection or chosen documents and - see which documents the answer used. The search API returns the matching - passages themselves. -- **RAG as a service.** Authenticated REST API for ingestion, search and chat, - with OpenAPI docs and a server-side example client. - ## Install You need Git, Docker with Compose v2, Python 3, and one `OPENAI_API_KEY`.