You will get a (free-to-run) LLM-Powered RAG chatbot/query web app for your documents
Rising Talent
Rising Talent
Project details
Have a pile of complex documents you wish you could talk to directly? This tool harnesses the power of open-source LLMs, retrieval-augmented generation (RAG) & a sleek Streamlit interface to give you a custom solution.
Features:
• optimised & customised extraction to ensure input data of the highest quality
• handles highly complex documents including tables & images
• optimised RAG workflow (with hybrid search & cross-encoder reranking) to guarantee relevant, complete & accurate responses
• built to minimise hallucination
• *ZERO* costs to run the app (free API/server/storage etc)🎊
As a seasoned NLP & LLM developer, I'm keenly aware of the basic tenet of AI models: 'you get what you put in'. LLMs like GPT-4 & LLaMA-3 are only as good as their input data, so I go above & beyond to ensure that:
• the document data extraction process is pristine (I offer customisation for your unique documents)
• the RAG protocol extracts the absolute best matches from your data for the LLM to use & respond with
You don't need to pay anything to run the app unless you want to! We can discuss paid options e.g. OpenAI models instead of open-source ones, AWS deployment vs Streamlit Cloud etc.
Features:
• optimised & customised extraction to ensure input data of the highest quality
• handles highly complex documents including tables & images
• optimised RAG workflow (with hybrid search & cross-encoder reranking) to guarantee relevant, complete & accurate responses
• built to minimise hallucination
• *ZERO* costs to run the app (free API/server/storage etc)🎊
As a seasoned NLP & LLM developer, I'm keenly aware of the basic tenet of AI models: 'you get what you put in'. LLMs like GPT-4 & LLaMA-3 are only as good as their input data, so I go above & beyond to ensure that:
• the document data extraction process is pristine (I offer customisation for your unique documents)
• the RAG protocol extracts the absolute best matches from your data for the LLM to use & respond with
You don't need to pay anything to run the app unless you want to! We can discuss paid options e.g. OpenAI models instead of open-source ones, AWS deployment vs Streamlit Cloud etc.
AI Algorithms
Large Language Model, Multimodal Large Language Model, Transformer ModelAI Applications
AI Chatbot, AI Content Creation, Conversational AI, Natural Language Generation, Natural Language Understanding, Sentiment Analysis, Text RecognitionAI Development Language
PythonAI Tools
Hugging Face, StreamlitAI Models
GPT-J, GPT-Neo, LLaMAWhat's included
| Service Tiers |
Starter
$585
|
Standard
$795
|
Advanced
$1,175
|
|---|---|---|---|
| Delivery Time | 3 days | 7 days | 12 days |
Number of Revisions | 0 | 0 | 0 |
AI Model Integration | |||
Batch Normalization | - | - | - |
Database Integration | - | - | - |
Detailed Code Comments | - | - | |
Image Upscaling | - | - | - |
MLOps | - | - | - |
Model Deployment | - | - | - |
Model Documentation | - | - | - |
Model Monitoring | - | - | - |
Model Testing & Optimization | - | - | |
Model Tuning | - | - | - |
Natural Language Processing | |||
NLP Tokenization | |||
Pre-Training | - | - | - |
Prompt Engineering | - | - | |
Setup File | - | - | - |
Source Code | - | - | - |
Optional add-ons
You can add these on the next page.
Fast Delivery
+$50 - $150
Additional Revision
+$250
Customise interface
(+ 2 Days)
+$135
19 reviews
(18)
(1)
(0)
(0)
(0)
This project doesn't have any reviews.
LN
Lisa N.
Nov 20, 2025
AI Image Generation & Prompting for Brand Protocol
Prodhi is skilled and experienced and has high standards for his work. We tried something experimental and although the outcome turned out not to be relevant to my needs, it was a useful exercise nevertheless. I can recommend Prodhi for branding projects incorporating Ai image generation and Ai prompt engineering.
JO
Joerg O.
Jul 8, 2025
Expert Prompt Engineer for Innovative AI-Driven Custom Game Company
IN
Iman N.
Feb 10, 2025
Prompt engineering for AI content creation tool
LN
Lisa N.
Jan 22, 2025
Prompt Engineer / Image Creator to consult on an Ai image + prompt brand protocol
This was my first consult with Prodhi. I was impressed and will work with him again.
RC
Rafael C.
Aug 21, 2024
LLM chatbot for virtual therapist
About Prodhi
GenAI Developer | n8n | NLP | LLMs | RAG | Prompt Engineering | Python
100%
Job Success
Reykjavik, Iceland - 9:23 pm local time
A snapshot of my core expertise:
- AI Content Generation & Automation: Multi-platform content pipelines with n8n workflows, automated social media systems, AI-powered visual content generation (carousels, reels), and intelligent scheduling. I've built comprehensive content ecosystems integrating Notion, Airtable, Claude API, and social media platforms - automating 60%+ of production workflows whilst maintaining quality control.
- LLM Applications & Fine-tuning: Prompt engineering, RAG systems, model fine-tuning (LoRA/QLoRA), and custom GPT implementations. I develop systems that go beyond basic API calls, including novel approaches like in-place DPO methodology to improve content quality and align brand tone without traditional fine-tuning overhead.
- Analytics & Performance Optimisation: Real-time dashboards, A/B testing frameworks, KPI tracking, and data-driven iteration. I build systems that measure what matters and feed insights back into production workflows.
- Healthcare & Pharmaceutical ML: Clinical data analysis, drug discovery pipelines, therapeutic chatbots, and biomedical informatics. My background in peer-reviewed cancer research (published in Nature Communications) means I approach technical problems with scientific rigour and evidence-based methodologies.
Technical stack:
Python, SQL, R | PyTorch, TensorFlow, HuggingFace, LangChain | OpenAI & Anthropic APIs | n8n automation | Airtable, Notion integrations | AWS, GCP, Azure | Web scraping, ETL pipelines | Streamlit/Plotly dashboards
How I work:
I've delivered 23+ projects on Upwork with 100% client satisfaction. My approach combines technical execution with strategic and creative thinking. I don't just build what you ask for; I help identify what will actually solve your problem. Whether that's automating repetitive workflows, building custom AI tools, or processing/creating complex datasets, I prioritise measurable outcomes and clear documentation.
My biomedical research background (Amsterdam UMC, CIC BioGUNE, Dartmouth) gives me a strong foundation in experimental design, statistical validation, and handling complex technical challenges. I've worked with investment firms needing private LLM systems, pharmaceutical companies requiring clinical data analysis, and content teams building automated generation pipelines.
I'm currently completing an MSc in Applied Data Science & AI.
Available for automation architecture, AI/ML development, and technical product strategy projects.
Steps for completing your project
After purchasing the project, send requirements so Prodhi can start the project.
Delivery time starts when Prodhi receives requirements from you.
Prodhi works on your project following the steps below.
Revisions may occur after the delivery date.
Parse through documents to ensure extraction protocol is working correctly
Set up app