You will get a production-ready bilingual chatbot OpenAI API or custom local model
Rising Talent
Rising Talent
Project details
I will deliver a production-ready bilingual chatbot that uses the OpenAI API by default and, in the Advanced tier, can integrate an optionally fine-tuned local model for stronger domain or language control. Answers are grounded with a Retrieval-Augmented Generation (RAG) layer built from your PDFs/URLs, so the bot cites relevant sources and stays on-topic. We’ll define intents, tone, and safety policies; then I provide a prompt kit, FastAPI endpoint, and a Dockerized app you can run on your own infrastructure. If you need UI, I can supply a web widget or Telegram bot. Quality is measured with a small Q/A test set (hit-rate), latency checks, and refusal rules for unsafe inputs. Delivery is chat-only with fast async feedback, and all code/data remain private (NDA available via Upwork).
Machine Learning Tools
ChatGPT, GPT-3, MLflow, NLTK, NumPy, NVIDIA AI Platform, OpenCV, pandas, Python, PyTorch, scikit-learn, TensorFlow, Vertex AIWhat's included
| Service Tiers |
Starter
$149
|
Standard
$349
|
Advanced
$699
|
|---|---|---|---|
| Delivery Time | 2 days | 4 days | 7 days |
Number of Revisions | 1 | 2 | 3 |
Number of Model Variations | 0 | 0 | 0 |
Number of Scenarios | 0 | 0 | 0 |
Number of Graphs/Charts | 0 | 0 | 1 |
Model Validation/Testing | |||
Model Documentation | |||
Data Source Connectivity | - | ||
Source Code |
Optional add-ons
You can add these on the next page.
Additional Revision
+$49
Extra Platform (Telegram/WhatsApp/Web widget)
+$99
24h Rush Delivery
+$99
Index + embed extra 100 PDF pages
+$79Frequently asked questions
About Dejan
PhD, Senior ML Engineer | YOLO+SAHI CV | LLMs (RAG, QLoRA)
Vranje, Serbia - 5:03 am local time
• Computer Vision: YOLOv5/8 + SAHI + WBF for small-object UAV imagery; +24% mAP@0.50:0.95 with FN↓ at a defined operating point. Real-time PyTorch/OpenCV/CUDA pipelines.
• NLP / LLMs: Led a bilingual GPT-2–class model effort; QLoRA fine-tuning, RAG (Elasticsearch/FAISS), cross-encoder reranking, evaluation (BLEU/ROUGE/BERTScore).
• Ops & Quality: Reproducible repos (Docker, W&B, CI), deterministic runs, clear metric reports. Own GPU server.
• Domains: Legal-tech, safety-critical CV (UAV/remote sensing), time-series forecasting, academia.
• Deliverables: one-command run + configs, README with stability notes, PR curves & tables, short metric brief, post-delivery support window.
• Collaboration: Upwork Messages (chat-only), fixed-price milestones for speed & predictability. Availability: 30+ hrs/week, 24–48h turnaround per revision wave.
Steps for completing your project
After purchasing the project, send requirements so Dejan can start the project.
Delivery time starts when Dejan receives requirements from you.
Dejan works on your project following the steps below.
Revisions may occur after the delivery date.
Intake & baseline chat
Define intents, tone, and safety; spin up baseline OpenAI chat with prompt kit.
RAG assembly (docs/URLs)
Clean & chunk documents; build embeddings/vector store; retrieval evaluation; prompt iteration.