Upwork home
Sign up
Project Catalog
DesignDesign
Video & AudioVideo & Audio
Development & ITDevelopment & IT
MarketingMarketing
Writing & TranslationWriting & Translation
MoreMore

You will get a Custom RAG Application with Python & LangChain.

Filip J.Status: Offline
Filip J. Filip J.
5.0
Preview image

Let a pro handle the details

Buy Other AI & Machine Learning services from Filip, priced and ready to go.
Filip J.Status: Offline
Filip J. Filip J.
5.0
Preview image

Let a pro handle the details

Buy Other AI & Machine Learning services from Filip, priced and ready to go.

Project details

Are you tired of AI chatbots that hallucinate or make up facts? Standard LLMs don't know your business. A Custom Retrieval-Augmented Generation (RAG) application solves this by connecting a powerful AI directly to your private data (PDFs, Notion, databases, internal wikis).

As a specialized AI Engineer, I don't just write basic scripts; I build production-grade, secure AI systems. Whether you need a simple proof-of-concept to test an idea (Starter), a functional web app (Standard), or a full-stack internal knowledge base deployed to your own servers (Advanced), I will architect a reliable solution using Python, LangChain, and state-of-the-art vector databases.

Your data remains secure, and your AI provides accurate, verifiable answers based strictly on your documents. Let's turn your raw data into an intelligent, automated asset.
AI Development Type
Knowledge Representation
AI Development Language
Python
What's included
Service Tiers Starter
$500
Standard
$1,500
Advanced
$3,000
Delivery Time 5 days 10 days 21 days
Number of Revisions
123
AI Model Integration
Detailed Code Comments
Knowledge Graph
-
-
-
Model Documentation
-
Ontology
-
Source Code
Taxonomy
-
Optional add-ons You can add these on the next page.
Live Handoff & Training Call
+$100

Frequently asked questions

5.0
3 reviews
100% Complete
(3)
1% Complete
(0)
1% Complete
(0)
1% Complete
(0)
1% Complete
(0)

AM

Anthony M.
5.00
Jun 4, 2026
AI Vehicle Buyer's Assistant Filip is one of the best freelancers I've worked with. Technically excellent, highly responsive, commercially minded, and genuinely invested in the success of the project. He consistently exceeded expectations, solved problems before they became issues, and delivered work of an exceptionally high standard. A rare combination of technical skill, professionalism, and ownership. Highly recommended. ★★★★★

HS

Heather S.
5.00
Mar 27, 2026
AI Orchestration Engineer for Multi-Agent E-commerce MVP (Grok / Claude / JSON Workflow) Filip delivered exactly what was scoped. The orchestrator foundation is clean, well structured, and fully functional. Checkpointing works, the Grok to Claude fallback fires correctly, and the code is commented and deployable from day one. He asked the right clarifying questions before starting, flagged a prompt inconsistency I had missed, and communicated clearly throughout. Would work with him again without hesitation.

NA

Nour A.
5.00
Feb 18, 2026
Hybrid Search & Semantic Retrieval Engineer (Postgres + Embeddings) Bit of a superstar actually

great communicator, expert, work with this guy hes great
Filip J.Status: Offline

About Filip

Filip J.Status: Offline
Agentic AI | Python | RAG | OpenClaw | n8n
65% Job Success
5.0  (3 reviews)
Skopje, North Macedonia - 4:23 pm local time
Note on my Job Success Score: My score recently dropped because I had to cancel a contract with a client who attempted to extort me for free work. Please check my portfolio and past 5-star reviews to see my actual track record.

AI Engineer & Full-Stack Developer specializing in production-grade LLM applications. I build systems that turn experimental AI into reliable, scalable business tools.

What I deliver:
→ AI Chatbots & Agents with autonomous Tool Calling (SQL queries, API execution)
→ Hybrid RAG pipelines (BM25 + Vector search) for accurate retrieval
→ Full-stack SaaS with FastAPI, PostgreSQL, Vue.js, and Docker
→ Real-time streaming (SocketIO, token-by-token responses)

Recent work:
• Built hybrid search engine for academic platform (PostgreSQL + pgvector) — 5-star review
• Engineered embeddable AI chat widget (like Intercom) with multi-agent orchestration
• Developed AI Support Copilot that autonomously executes SQL via LLM function calling

Tech stack: Python, FastAPI, PostgreSQL, pgvector, OpenAI API, LangChain, Vue.js, Docker

I take projects from architecture to production. If you need AI that actually works in the real world, let's talk.

Steps for completing your project

After purchasing the project, send requirements so Filip can start the project.

Delivery time starts when Filip receives requirements from you.

Filip works on your project following the steps below.

Revisions may occur after the delivery date.

Architecture & Tech Stack Review

I will review your requirements and data sources to confirm the optimal vector database and LLM combination for your specific use case.

Data Ingestion & Vectorization

I will securely process, clean, and embed your private documents into the vector database so the AI can accurately retrieve the information.

Review the work, release payment, and leave feedback to Filip.