Explore a comprehensive tutorial on stress testing Qdrant, a semantic search engine, with 90,000 vectors. Learn how to split text into chunks, create vector lists, set up TensorFlow Hub and GPU environments, and generate data for machine learning models. Follow along as the process of uploading and testing the stress test is demonstrated, including uploading datasets to Algolia and managing record uploads. Gain insights into the power and efficiency of the search function, and understand the program's overall performance through a detailed examination of final numbers and results.
Stress Testing Qdrant - Semantic Search with 90,000 Vectors - Lightning Fast Search Microservice
David Shapiro ~ AI via YouTube
Overview
Syllabus
- Stress testing quadrant
- Splitting text into chunks
- Creating a list of vectors from text chunks
- Creating a data folder for a machine learning model
- Setting up TensorFlow Hub
- Setting up a Python virtual environment
- Setting up the TensorFlow GPU environment
- Generating data for a machine learning model
- Uploading and testing the quadrant stress test
- Uploading a dataset to an Algolia account
- Trying to upload records
- Uploading records
- A look at the final numbers
- The power and efficiency of the search function
- The efficiency of the program
Taught by
David Shapiro ~ AI
Related Courses
-
Operationalizing LLMs on Azure
-
Create a Large Language Model from Scratch with Python – Tutorial
-
Semantic Search for AI - Testing Out Qdrant Neural Search
-
TxtAI - Simplifying RAG and Semantic Search with an All-in-One Embeddings Database
-
Cohere AI's LLM for Semantic Search in Python
-
End-to-End LLM Project: Langchain with Pinecone Vector Database
