Uploaded September 2025 | Updated September 2026, 1 week ago
This hands-on workshop teaches participants to build cost-effective evaluation systems for RAG applications using Azure Cosmos DB's vector search capabilities. Attendees will learn to implement semantic caching techniques that significantly reduce LLM evaluation costs while maintaining fast query performance. Participants will create a complete evaluation pipeline that measures retrieval quality, answer accuracy, and system performance using industry-standard metrics. By the end of this session, attendees will have production-ready code and benchmarking tools that can scale across different deployment environments.
#AzureCosmosDB #LLM #AI
Useful links:
• (GitHub) Azure Cosmos DB LLM Evaluation - github.com/FarahAbdo/azure-cosmos-llm-evaluation
• Subscribe to this channel - https://aka.ms/AzureCosmosDBYouTube
• Check out past meetups on YouTube to catch anything you might have missed - youtube.com/playlist?list=PLmamF3YkHLoJSJ1qdHDXXSlmkj2HKz-nb
• Want to present at a future meetup? Fill out our intake form - https://aka.ms/AzureCosmosDB/UserGroupSubmission
• Try Azure Cosmos DB Free - https://aka.ms/trycosmosdb
• Microsoft Reactor - https://aka.ms/Reactor
• Follow Azure Cosmos DB on X - twitter.com/AzureCosmosDB
• Follow Azure Cosmos DB on LinkedIn - linkedin.com/company/azure-cosmos-db
Speaker: Farah Abdou
Farah Abdou is a Machine-learning engineer, STEM advocate, and international tech speaker whose work bridges artificial intelligence research with large-scale industrial deployment. Best known for her contributions to natural-language processing (NLP), quantum reinforcement learning (QRL), and cloud-native AI systems, She has become a prominent voice for open-source innovation and women’s representation in technology across the Middle East and North Africa (MENA) region
This hands-on workshop teaches participants to build cost-effective evaluation systems for RAG applications using Azure Cosmos DB's vector search capabilities. Attendees will learn to implement semantic caching techniques that significantly reduce LLM evaluation costs while maintaining fast query performance. Participants will create a complete evaluation pipeline that measures retrieval quality, answer accuracy, and system performance using industry-standard metrics. By the end of this session, attendees will have production-ready code and benchmarking tools that can scale across different deployment environments.
#AzureCosmosDB #LLM #AI
Useful links:
• (GitHub) Azure Cosmos DB LLM Evaluation - github.com/FarahAbdo/azure-cosmos-llm-evaluation
• Subscribe to this channel - https://aka.ms/AzureCosmosDBYouTube
• Check out past meetups on YouTube to catch anything you might have missed - youtube.com/playlist?list=PLmamF3YkHLoJSJ1qdHDXXSlmkj2HKz-nb
• Want to present at a future meetup? Fill out our intake form - https://aka.ms/AzureCosmosDB/UserGroupSubmission
• Try Azure Cosmos DB Free - https://aka.ms/trycosmosdb
• Microsoft Reactor - https://aka.ms/Reactor
• Follow Azure Cosmos DB on X - twitter.com/AzureCosmosDB
• Follow Azure Cosmos DB on LinkedIn - linkedin.com/company/azure-cosmos-db
Speaker: Farah Abdou
Farah Abdou is a Machine-learning engineer, STEM advocate, and international tech speaker whose work bridges artificial intelligence research with large-scale industrial deployment. Best known for her contributions to natural-language processing (NLP), quantum reinforcement learning (QRL), and cloud-native AI systems, She has become a prominent voice for open-source innovation and women’s representation in technology across the Middle East and North Africa (MENA) region
