lmorchard - Pebbling Club 🐧🪨

Evaluating Retrieval Augmented Generation for large-scale codebases

www.qodo.ai
2025-02-19T19:06:31.689Z
ai ml llm rag

Notes

By focusing on the answer correctness as a key success metric, and designing our datasets and metrics carefully, we’ve managed to build a reliable evaluation process which has helped us increase confidence in our system’s quality.

Feed

Embed

Unfurl

{ "expires": 1740078389825, "status": 200, "bodyLength": 146218, "author": "Assaf Pinhasi", "date": "2025-02-17T11:07:34.000Z", "description": "Read how Qodo evaluates RAG systems to optimize generative AI coding for large-scale codebases using LLM-as-a-judge and regression testing", "image": "https://www.qodo.ai/wp-content/uploads/2025/02/Evaluating-RAG-for-large-scale-codebases.png", "logo": "https://www.qodo.ai/wp-content/uploads/2025/02/cropped-qodo-fav-192x192.png", "publisher": "Qodo", "title": "Evaluating Retrieval Augmented Generation for large-scale codebases", "url": "https://www.qodo.ai/blog/evaluating-rag-for-large-scale-codebases/", "feed": "https://www.qodo.ai/feed/", "iframe": "<blockquote class=\"wp-embedded-content\" data-secret=\"0CXCgxWvgW\"><a href=\"https://www.qodo.ai/blog/evaluating-rag-for-large-scale-codebases/\">Evaluating RAG for large scale codebases</a></blockquote><iframe sandbox=\"allow-scripts\" security=\"restricted\" src=\"https://www.qodo.ai/blog/evaluating-rag-for-large-scale-codebases/embed/#?secret=0CXCgxWvgW\" width=\"600\" height=\"338\" title=\"“Evaluating RAG for large scale codebases” — Qodo\" data-secret=\"0CXCgxWvgW\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" class=\"wp-embedded-content\"></iframe><script>\n/*! This file is auto-generated */\n!function(d,l){\"use strict\";l.querySelector&&d.addEventListener&&\"undefined\"!=typeof URL&&(d.wp=d.wp||{},d.wp.receiveEmbedMessage||(d.wp.receiveEmbedMessage=function(e){var t=e.data;if((t||t.secret||t.message||t.value)&&!/[^a-zA-Z0-9]/.test(t.secret)){for(var s,r,n,a=l.querySelectorAll('iframe[data-secret=\"'+t.secret+'\"]'),o=l.querySelectorAll('blockquote[data-secret=\"'+t.secret+'\"]'),c=new RegExp(\"^https?:$\",\"i\"),i=0;i<o.length;i++)o[i].style.display=\"none\";for(i=0;i<a.length;i++)s=a[i],e.source===s.contentWindow&&(s.removeAttribute(\"style\"),\"height\"===t.message?(1e3<(r=parseInt(t.value,10))?r=1e3:~~r<200&&(r=200),s.height=r):\"link\"===t.message&&(r=new URL(s.getAttribute(\"src\")),n=new URL(t.value),c.test(n.protocol))&&n.host===r.host&&l.activeElement===s&&(d.top.location.href=t.value))}},d.addEventListener(\"message\",d.wp.receiveEmbedMessage,!1),l.addEventListener(\"DOMContentLoaded\",function(){for(var e,t,s=l.querySelectorAll(\"iframe.wp-embedded-content\"),r=0;r<s.length;r++)(t=(e=s[r]).getAttribute(\"data-secret\"))||(t=Math.random().toString(36).substring(2,12),e.src+=\"#?secret=\"+t,e.setAttribute(\"data-secret\",t)),e.contentWindow.postMessage({message:\"ready\",secret:t},\"*\")},!1)))}(window,document);\n</script>\n", "lang": "en", "video": null, "audio": null, "duration": 656 }
Using Llamafiles for Embeddings in Local RAG Applications

future.mozilla.org
2024-08-16T09:51:34.099Z
ml ai rag llamafile imported:raindrop

Unfurl

{ "date": "2024-05-15T12:00:00.000Z", "image": "https://storage.googleapis.com/future-prod-prod-storage/images/llamafile-640x640_tQCm5Mz.2e16d0ba.fill-1200x630.png", "logo": "https://future.mozilla.org/static/img/favicons/innovation/favicon-196x196.2af054fea211.png", "publisher": "Mozilla Innovations", "title": "Using Llamafiles for Embeddings in Local RAG Applications", "url": "http://future.mozilla.org/builders/news_insights/llamafiles-for-embeddings-in-local-rag-applications/", "lang": "en", "cached": true, "cachedAt": 1728192763448, "expires": 1728363553858, "status": 200, "bodyLength": 40418, "duration": 4859 }

0 - 50 of 2 items

10 25 50 100 250