I will build an ai chatbot using rag, llm apis, and vector db


About this gig
Want to add AI features to your application or build a chatbot that answers questions using your own data?
I will help you develop an AI-powered backend using LLM APIs, retrieval-augmented generation (RAG), and PostgreSQL pgvector where appropriate.
Services include:
- LLM API integration
- AI chat endpoints
- Document-based question answering
- Embeddings and vector search
- PostgreSQL pgvector integration
- Retrieval and prompt design
- Structured outputs and tool calling
- Integration with an existing application
A RAG system can retrieve relevant information from your documents or knowledge base before generating an answer. This can help ground responses in your content, but it does not guarantee that every answer will be correct.
I have hands-on experience with LLM APIs and RAG concepts, including a pgvector-backed support assistant designed to answer questions over live tenant data.
Please contact me before ordering to discuss your data sources, model provider, expected behavior, and deployment requirements.
Model usage and other third-party service charges are separate unless explicitly included in the offer.
Get to know Khaled H.
Software Engineer
- FromBangladesh
- Member sinceApr 2023
- Avg. response time1 hour
Languages
Bengali, English, Hindi
My Portfolio
FAQ
What is RAG?
Retrieval-augmented generation retrieves relevant content from your data and provides it to an LLM as context for its answer.
Can you build a chatbot for PDFs?
Yes, for an agreed document format, ingestion process and scope.
Will the chatbot always give accurate answers?
No. Accuracy depends on the data, retrieval quality, prompts, model and evaluation. Testing and safeguards are important.
Can it use my existing database?
Potentially. Access control, tenant isolation and query safety must be designed carefully before connecting AI to live business data.
Are LLM API costs included?
No, unless explicitly stated in the custom offer.
