I helped streamline the lead-to-quotation process for a signage company. When a new lead comes in, we automatically use SerpAPI and RapidAPI to gather a list of potential vendors. Quotations are then requested from these vendors, submitted via email, and automatically extracted using Python. All leads, vendor info, and quotations are organized in Airtable, and the system intelligently selects the best quotation based on predefined criteria — all orchestrated seamlessly with Make.com (http://Make.com) automation.
1
142
𝐑𝐀𝐆 𝐀𝐈 𝐊𝐧𝐨𝐰𝐥𝐞𝐝𝐠𝐞 𝐏𝐥𝐚𝐭𝐟𝐨𝐫𝐦 | 𝐈𝐧𝐭𝐞𝐥𝐥𝐢𝐠𝐞𝐧𝐭 𝐒𝐞𝐚𝐫𝐜𝐡, 𝐀𝐈 𝐀𝐧𝐬𝐰𝐞𝐫𝐬 & 𝐕𝐞𝐜𝐭𝐨𝐫 𝐃𝐚𝐭𝐚𝐛𝐚𝐬𝐞
I designed and built a RAG-powered AI knowledge platform that lets businesses search documents, websites, databases, and internal knowledge using natural language.
The system processes content, creates embeddings, stores them in a vector database, retrieves the most relevant information, and uses AI to generate accurate, source-grounded answers.
My services include: RAG development, document ingestion, semantic search, vector database setup, OpenAI/LLM integration, internal knowledge assistants, API integrations, and analytics.
The solution helps teams find information faster, reduce repetitive research, improve answer consistency, and build scalable AI-powered knowledge systems.
𝐓𝐞𝐜𝐡 𝐒𝐭𝐚𝐜𝐤:
OpenAI, LangChain, RAG, Pinecone, Qdrant, Weaviate, FAISS, Chroma, Python, FastAPI, PostgreSQL, APIs.
3
502
Just wrapped up my Autonomous Resume Verifier for the Micro1 Challenge! I built this AI agent to automate candidate screening by parsing and evaluating resumes instantly.
Tech Stack: Python, Streamlit, Llama 3 & Groq API.
Check out the video to see it in action! Let me know what you think.
#ArtificialIntelligence #Python #Streamlit #Llama3 #Groq #Micro1Challenge #WebDevelopment #AIAgent #FreelanceDeveloper
3
3
682
AI-Powered PDF Data Extraction
Organizations often face challenges in extracting useful information from a large volume of unstructured data in PDF format.
The lack of standardized data formats makes it difficult to efficiently retrieve relevant information, when dealing with documents.
The goal of this solution was to develop a flexible automated solution that allows users to specify entities to extract, enabling quick and accurate data retrieval from diverse PDFs.
The demo is available on request.
0
42
Kaizen is a Python learning platform for kids ages 12-14 — that specific age window matters because most coding-for-kids products target either much younger (Scratch/blocks) or much older (Codecademy-style courses for adults). The 12-14 zone is underserved: they've outgrown drag-and-drop blocks but they're not ready for "Watch this 2-hour video and take notes."
The product is built around a narrative: the digital realm of Coderia is being corrupted, and the kid's job is to save it by writing real Python. Eight story realms (Echo Valley → Logic Peaks → Loop Lakes → ...), 94 lessons, one connected arc. Every lesson is real Python that runs, not blocks.
0
178