I will build a python research agent for automated data collection and ranking


About this gig
Beyond basic scraping I build agents that collect data from multiple sources, then automatically rank, cluster, and structure it using ML (SentenceTransformers, scikit-learn).
Useful for market research, competitor monitoring, and lead generation where you need structured, ranked output not just raw scraped data.
What you get:
- Multi-source data collection pipeline
- Automatic deduplication and structuring
- ML-based ranking and clustering of results
- Clean export (CSV, JSON, or database)
- Optional scheduled automation with notifications
Stack: Python, FastAPI, SentenceTransformers, scikit-learn, Docker.
Message me before ordering if your target source has bot protection I'll confirm feasibility first.
Get to know Mikhail Esemchi
LLM Apps and AI Agents Developer, Python and FastAPI
- FromLatvia
- Member sinceFeb 2026
Languages
Russian, English, Latvian
My Portfolio
Other AI Development Services I Offer
FAQ
Can you handle sites with bot protection?
Discussed individually — depends on the target site's structure and anti-bot measures in place.
Can this run automatically on a schedule?
Yes, available as an add-on (Scheduled Runs) or included by request in Premium.
What output formats do you support?
CSV, JSON, or direct database integration (PostgreSQL).
