Kategorien durchsuchen
Entdecken
Fiverr Pro
Deutsch
$
USD
I will build a custom rag chatbot for your documents
Tomefy R
Über diesen Service
Turn your documents, knowledge base, or FAQ into a chatbot that actually
answers correctly not a generic wrapper around ChatGPT.
I build production-grade RAG (Retrieval-Augmented Generation) systems:
your documents are chunked, embedded, indexed, and retrieved with hybrid
search (semantic + keyword) so the AI answers from YOUR data, not from
guesses.
What you get:
Document ingestion pipeline (PDF, text, docs)
Embeddings with state-of-the-art models (BGE-M3)
Hybrid search + reranking for accurate retrieval
Clean API (FastAPI) you can plug into any app
Optional: RAGAS evaluation report so you know it actually works
Tech stack: Python, LlamaIndex, ChromaDB/FAISS, FastAPI, Groq/OpenAI/Gemini
Perfect for: internal knowledge bases, customer support bots, document
Q&A tools, research assistants.
Message me before ordering if you want a custom scope happy to advise
on what tier fits your use case.
Lerne Tomefy R kennen
Tomefy R
Data Scientist, RAG ML Engineer, Python FastAPI
- AusMadagaskar
- Mitglied seitMärz 2026
- ⌀ Antwortzeit1 Stunde
Sprachen
Englisch
I'm Tomefy, a Data Scientist & AI Engineer building production-ready AI systems beyond the notebook—from RAG chatbots to ML pipelines.
• Stack: Scikit-learn, XGBoost, CatBoost, LlamaIndex, Faiss, FastAPI, NestJS
• Expertise: Hybrid search & reranking, network anomaly detection, attrition prediction APIs
• Setup: Based in Madagascar, working remotely worldwide
• Languages: English & French (fluent)
Code that lasts, clear communication, realistic timelines.
Portfolio: portfolio-data-ai-omega.vercel.app
FAQ
Which LLM do you use?
Configurable: Groq (fast/cheap), OpenAI, Gemini, or local (Ollama) if you need data privacy.
Can it handle my language?
Yes, multilingual embeddings (BGE-M3) support French, English, and more.
Do I need to provide an API key?
Yes, for the LLM provider you choose (or I can advise on the cheapest option).
