Episode 183 : Promptologues de l'infra
Listen now
Description
### Promptologues * How to Cut RAG Costs by 80% Using Prompt Compression -> https://towardsdatascience.com/how-to-cut-rag-costs-by-80-using-prompt-compression-877a07c6bedb * Prompt Compression avec LLMLingua -> https://github.com/microsoft/LLMLingua ### LLM Infra* Introducing Pinecone Serverless -> https://www.pinecone.io/blog/serverless/ * embedchain/embedchain: The Open Source RAG framework -> https://github.com/embedchain/embedchain * A Guide to Large Language Model Abstractions - Two Sigma -> https://www.twosigma.com/articles/a-guide-to-large-language-model-abstractions/ ### Data eng* How to Scale Your Data Pipelines and Data Products with Contract Testing and Dbt -> https://towardsdatascience.com/how-to-scale-your-data-pipelines-and-data-products-with-dbt-and-contract-testing-10c92ea9a443 * dbt Alternatives -> https://www.greenmountaindatasolutions.com/blog/alternatives-to-dbt-data-build-tool
More Episodes
Dans cet épisode on revient sur FoundationDB. FoundationDB est le socle de beaucoup de services (Icloud, Snowflake...) mais reste peu connue. Qui de mieux que l'équipe de spécialistes de Clever cloud qui l'a utilisé pour construire ses "Databases as a Service" pour en parler ?  C'est donc un...
Published 11/15/24
Published 11/15/24