Sobes.tech

Can a race condition occur in asynchronous Python code?

202

How many documents were retrieved during the search? Was there a reranking?

186

How was the quality of the RAG system evaluated?

163

How did you monitor the service's operation? What did you look at in Grafana?

155

What else can be optimized in the predict method? (creating a DataFrame each time)

142

Why is it better to use POST instead of GET for this endpoint?

139

Write a web service in FastAPI that accepts a POST request with data (income, age, loan amount) and returns an ML model prediction (loan approval).

138

How to optimize a service so that a synchronous CPU task (model prediction) does not block the FastAPI event loop?

137

Tell about the entire pipeline of the RAG system: what documents were used, how they were loaded and processed?

133

What is Singleton and how to use it for model loading? What are the disadvantages of Singleton?

133

How long does the entire RAG pipeline from request to response usually take?

125

How were documents uploaded to the vector database? How was chunking performed?

116

If a local ML model (for example, a reranker) is used in an asynchronous service and is called synchronously, what problem arises and how can it be solved?

115

How were embeddings obtained? Through which model and how was it run?

109

How does multithreading work in Python considering GIL? What are the differences between threads and processes?

106