At what stage is the LLM included in the RAG pipeline?
Python
Can you list the main microservice design patterns?
Complete the query: display the username and the number of people invited by him (only those who invited someone).
What technological tools and languages do you use in your work?
Have you encountered RAG and vector search?
How many DAU and transactions per day did you have on the platform?
How to limit parallelism when making 10 API requests, where the maximum is 3 simultaneous requests?
What database management systems have you worked with in your projects?
How will consumers read from partitions with 3 partitions and 4 consumers in one group? And with 4 partitions and 3 consumers?
What is RAG (Retrieval Augmented Generation)? Tell me what you know about working with LLM.
What search methods do you know in vector databases? What functions are used in pgvector?
How does Semaphore differ from Lock in asyncio?
How is inheritance from multiple classes simultaneously supported in Python?
Write a list sorting method using the bubble sort technique.
What is a lazy QuerySet in Django? Explain select_related and prefetch_related — what are they used for, and how do they differ?
Do you have experience working with vector databases? Have you been involved in data uploading and chunking?
Why might PostgreSQL choose Sequential Scan instead of B-tree index even if the index exists?
Share your professional experience and skills that you believe are relevant for this position.
What did you do at your previous job? Tell an interesting case.
What types of indexes are used in database management systems?