
En curso
Publicado
Pagado a la entrega
Project Summary We are seeking a senior developer or team to build a backend-only AI agent (no frontend) designed for Q&A over a private document base. The agent must connect to document sources (initially SharePoint or Google Drive), index their content, and answer user queries. The key technical differentiators for this project are: ag-ui Protocol: All communication with the agent must be handled via the standard ag-ui (Agent-User Interaction Protocol). Image Artifact Output: As a backend-only agent, the API response (via ag-ui) must include not only the synthesized text answer and source links but also dynamically generated PNG files. These images will be "screenshots" of the original document sections (PDF, DOCX, XLSX, etc.) with the relevant text highlighted. Core Functional Requirements 1. Document Ingestion and Synchronization Modular Sources: The agent must be able to ingest documents from a single source at a time, configurable via environment variables (secrets, endpoints, etc.). Initial Connectors: The first two connectors to be developed are for Microsoft SharePoint and Google Drive. File Format Support: Must be able to parse and index the following file types: pdf, pptx, xlsx, docx, md, .html, and .txt. Technical Suggestion (MCPs): We encourage the use of existing Model Context Protocol (MCP) servers (see [login to view URL]) to accelerate the integration with SharePoint and GDrive. The proponent must state if they will use this or a custom alternative. Indexing Process: On startup, the agent must perform a full indexing of the document repository. It must expose a status endpoint (e.g., /api/v1/status) that indicates the indexing status (e.g., "Connecting", "Indexing {X/Y} docs", "Complete"). It must have a synchronization mechanism (daily or, ideally, webhook-based) to detect new/modified/deleted files and update its internal vector database. 2. Q&A Logic (RAG) The agent will receive queries (prompts) via its ag-ui endpoint. It must search its vector database for the most relevant information chunks to answer the query. The logic must be advanced, capable of synthesizing a coherent answer based on multiple sources, not just returning raw text chunks. 3. Artifact Generation (The Key Requirement) Along with the synthesized text answer, the API response must return a list of "matches." For each match, it must provide: The link or identifier of the source document. An on-the-fly generated PNG image file. Image Specifications: The image must be a "screenshot" of the relevant section of the original document. It must include a visual highlight (e.g., a yellow box) over the exact text that was used. The image must be readable. If a single match spans two pages (e.g., in a PDF), a single image containing both pages should be generated (or the proponent must justify an alternative). The proponent must explain their technical strategy for rendering non-visual formats (like .xlsx, .md, .docx) for this image generation. Technical Architecture Requirements API Protocol: The agent must act as an ag-ui compatible server. All interaction will be based on this protocol. Tech Stack: The proponent is free to choose the stack (e.g., Python, LangChain/LlamaIndex, Vector DB) but must specify it clearly in their proposal. LLM (Language Model): The agent must use OpenRouter as the router for all LLM calls. It must be tested to work with at least one open-source model (developer's choice) available on OpenRouter. Scalability: The architecture must be designed to handle a document base of "all types" (from a few small files to thousands of large documents). Execution: The agent must be executable with uvx. Deliverables The complete Git repository with all the agent's source code. A detailed [login to view URL] file with: Installation instructions for dependencies. A guide for setting up all environment variables (for the data source, OpenRouter, etc.). Execution instructions (the uvx command). The scope does not include deployment to a server; the deliverable is the finalized, executable source code. Information Required in Your Proposal To be considered, your proposal must include: Detailed Tech Stack: A list of the technologies (Python, libraries, vector DB) you plan to use. (CRITICAL) Image Generation Strategy: A detailed technical plan for "Core Functional Requirement #3." How will you convert and render .xlsx, .docx, md, etc., to generate images with highlights? What specific libraries will you use for this? Ingestion Approach: Confirm if you will use the suggested MCPs (from [login to view URL]) for GDrive/SharePoint or if you propose a manual, custom integration. LLM for Testing: Specify which open-source model (via OpenRouter) you will use for development and testing. Portfolio: Examples of past work related to RAG, AI agents, or complex document processing. Cost, Timeline, and Terms: A time estimate (in weeks) and the total project cost. Currency: All quotes must be in Euros (EUR) or Dollars (USD).
ID del proyecto: 39934691
21 propuestas
Proyecto remoto
Activo hace 3 meses
Fija tu plazo y presupuesto
Cobra por tu trabajo
Describe tu propuesta
Es gratis registrarse y presentar ofertas en los trabajos

HELLO, WE HAVE WORKED ON SIMILAR PROJECTS AND CAN PROVIDE EXAMPLES WE COMPLETELY UNDERSTAND YOUR REQUIREMENT FOR A HEADLESS AI RAG AGENT WITH IMAGE ARTIFACT GENERATION AND AG-UI PROTOCOL SUPPORT. With over 8 years of experience in AI, LLM integration, and document intelligence systems, our team can build a high-performance backend that handles document ingestion, intelligent retrieval, dynamic highlighting, and artifact rendering efficiently. We’ll architect a robust, modular system — ensuring clean scalability, fast synchronization, and accurate image-based context delivery for every query. WORKING FLOW → Requirement Analysis → finalize document sources (SharePoint, GDrive) & ingestion method (MCP or custom integration). Data Processing → full parsing + vectorization using LangChain/LlamaIndex → store embeddings in a vector DB. RAG Agent Setup → query processing via OpenRouter LLM → generate contextual answers with source references. Image Rendering → convert docs (PDF/DOCX/XLSX) → highlight matched text → generate PNG artifacts dynamically. Testing & Documentation → uvx execution setup → README with all configs → delivery of complete Git repository. INCLUDED SERVICES: ✔ UNLIMITED REVISIONS UNTIL SATISFACTION ✔ 2 YEARS OF POST-LAUNCH SUPPORT ✔ FULL SOURCE CODE UPON DELIVERY — Christina
€6.000 EUR en 7 días
6,5
6,5
21 freelancers están ofertando un promedio de €7.068 EUR por este trabajo

I have thoroughly reviewed the project requirements for Headless AI RAG Agent Development with Image Generation and AG-UI Protocol -- 2, and I am confident that my skills in Python, Engineering, Software Architecture, AI Chatbot Development, and Bot Development align perfectly with the needs of this project. I am willing to adjust the budget as we discuss the full scope, ensuring we work within your financial parameters. My extensive 15-year experience reflects a commitment to client satisfaction through quality work. Let's discuss the project details and get started right away. Please go through my profile to see my past work. Looking forward to your response.
€7.000 EUR en 21 días
7,2
7,2

Hi, Could you clarify any specific requirements you have for the document ingestion process? It sounds like a great project! I can build the backend AI agent to handle Q&A over a private document base, ensuring it connects seamlessly to SharePoint and Google Drive. I plan to use Python with libraries like PyPDF2 for PDF parsing and Pillow for PNG generation. For the image generation, I can create highlights over the relevant text using a combination of pdf2image and OpenCV. I would also recommend integrating with the MCPs for efficient document access. With over 5 years in backend development and experience with AI agents, I’m confident in delivering a robust solution. My timeline for this project is around 6 weeks, and I’d estimate the cost at $3,000 USD. Looking forward to the opportunity! Best Regards, Badar Madni
€8.500 EUR en 60 días
6,3
6,3

With over a decade of industry experience, particularly in AI Chatbot Development and Python, my team at Bluewebspark is well-prepared to deliver a top-notch solution for your Headless AI RAG Agent development project. We have successfully built cutting-edge software and mobile app solutions for over 50 businesses, streamlining their operations, enhancing their decision-supporting capabilities and enabling successful digital transformations. Our areas of expertise align perfectly with the requirements for this project, including document ingestion and synchronization, Q&A logic development (RAG), deep understanding of the Ag-ui Protocol, and image generation for different document formats. If you choose us for this project, you not only get a technically adept team but also a partner dedicated to empowering businesses through technology. Thank you again for considering Bluewebspark Technologies – I look forward to serving you with integrity, intelligence, and innovation!
€8.000 EUR en 7 días
6,7
6,7

Hi, Pedro N. I 've read your project description. I've successfully delivered similar projects. I have solid experience with Python, AI Chatbot Development, AI Development, Bot Development, LLM Integration, Software Architecture, LLM Prompt Engineering and Engineering. Please check out my portfolio: https://www.freelancer.com/u/jermeek Let's chat! Best Jeremy
€8.325 EUR en 1 día
5,3
5,3

Hello, I can build a backend-only AI agent for Q&A over private documents, fully ag-ui compatible, with synthesized text answers and PNG artifacts highlighting relevant sections. Tech Stack: Python 3.11+, LangChain/LlamaIndex for RAG, Weaviate/FAISS for vector DB, OpenRouter for LLM calls (tested with LLaMA 2 7B), and document libraries: pdfplumber, python-docx, python-pptx, openpyxl, markdown2, BeautifulSoup. For image rendering: Pillow, reportlab, pdf2image, and Playwright for HTML/Markdown. Image Generation Strategy: PDFs converted via pdf2image with text highlighted; DOCX/PPTX rendered on canvas using python-docx/python-pptx + Pillow; XLSX rendered as tables via openpyxl + Pillow; Markdown/HTML rendered headlessly with Chromium and highlighted. Multi-page matches are combined into a single PNG, ensuring readability and clear highlights of relevant text. Ingestion: Prefer MCP servers for SharePoint/Google Drive. On startup, full indexing into the vector DB with /api/v1/status for progress. Supports daily or webhook-based incremental sync. File types supported: pdf, pptx, xlsx, docx, md, html, txt. RAG Logic: Queries come via ag-ui; agent searches vector DB, synthesizes coherent responses across multiple sources, and returns text + source links + PNG artifacts. Execution: Runs via uvx, modular design for new sources or file types. Deliverables: Git repo with source code, README with setup/env instructions, RAG logic, indexing, and image artifact generation.
€7.500 EUR en 20 días
4,8
4,8

Hi -=-⭐⭐⭐⭐-=- Building Intelligent Document Agents with Image-Aware Context Understanding -=-⭐⭐⭐⭐-=- I have carefully reviewed your requirement for a backend-only AI RAG agent that integrates document ingestion, semantic search, and contextual image generation. Your focus on delivering a compliant, scalable, and intelligent system through the ag-ui protocol reflects a highly structured and innovative approach to enterprise-grade knowledge retrieval. I understand the need for an AI agent that not only answers accurately but also visually references the original document context for transparency and trust. With over nine years of experience designing advanced AI and backend ecosystems, I have developed systems integrating RAG architecture, vector databases, OCR-based image generation, and API-driven automation pipelines. My experience ensures a streamlined, modular, and future-ready architecture compatible with OpenRouter and custom AI workflows. 1. Document Ingestion 2. RAG Framework 3. Visual Highlighting 4. Secure Indexing 5. Scalable Architecture Let us schedule a quick chat to align your vision and next steps. Regards, Prasham Jain
€5.031 EUR en 23 días
4,2
4,2

As a senior Data Analyst and Scientist, I'm well versed with turning complex datasets into actionable business insights and have extensive experience in **backend development** using Python, one of the tech stacks you mentioned in the project description. I'm highly proficient with **API development**, which aligns directly with your project's technical requirements. Moreover, my exposure to **document parsing and indexing** of various file types empowers me to build a capable backend that can index, search, and retrieve documents efficiently. Another strength I bring to the table is my expertise in **Data Visualization**. Alongside synthesized text answers, your project requires dynamically generating PNG image files of relevant document sections. Using my command over **Power BI** and other data visualization tools, I can create highly readable screenshots of various formats (pdf, pptx, xlsx, docx) by intelligently highlighting the relevant text - ensuring none of the vital information goes unnoticed. Being an excellent problem solver with a keen eye for detail; executing daily or webhook-based synchronizations to detect new/modified/deleted files and update internal vector databases won't be a challenge for me. Lastly, my experience in handling large-scale analytics projects ensures that the system I build will be robust enough to accommodate your full spectrum of document types without compromising its scalability.
€7.500 EUR en 7 días
3,7
3,7

Hello! As per your project post, you’re looking to build a Headless AI RAG Agent backend-only intelligent system designed for Q&A over private document repositories. The goal is to create a protocol-compliant AI agent that ingests, indexes, and retrieves data from SharePoint or Google Drive, then delivers both synthesized text answers and dynamically generated image artifacts highlighting the relevant document sections all communicated via the ag-ui standard protocol. My focus will be on delivering a modular backend MVP featuring: document ingestion and indexing (SharePoint + Google Drive connectors), vector-based semantic search (RAG pipeline), synthesized multi-source Q&A responses, image artifact generation (highlighted document sections as PNGs), and a live status/sync API endpoint for real-time progress tracking. I specialize in AI-driven backend systems, document intelligence, and RAG pipeline development using Python (FastAPI), LangChain/LlamaIndex, and OpenRouter APIs, with robust handling for various document types like PDF, DOCX, PPTX, XLSX, MD, and HTML. Let’s connect to define the architecture stack, artifact rendering approach, and synchronization model, ensuring the agent is production-grade, protocol-compliant, and optimized for enterprise-level document workloads. Best regards, Nikita Gupta
€5.000 EUR en 7 días
2,3
2,3

Madrid, Spain
Forma de pago verificada
Miembro desde oct 28, 2025
$20000-50000 USD
₹750-1250 INR /hora
$30-250 USD
₹1500-12500 INR
$8-15 USD /hora
$10-30 AUD
₹100-36000 INR /hora
$30-250 USD
$30-60 USD
$45-60 USD
$30-250 USD
₹1500-12500 INR
₹12500-37500 INR
₹150000-250000 INR
$30-250 USD
$30-250 CAD
₹1500-12500 INR
$25-50 AUD /hora
$30-250 CAD
₹1000-3000 INR