From fc41abb9a9a012fc286f3f168d81f0fbc54a6c10 Mon Sep 17 00:00:00 2001 From: Antonino Lorenzo <94693967+antoninoLorenzo@users.noreply.github.com> Date: Tue, 16 Jul 2024 20:12:52 +0200 Subject: [PATCH 1/3] Update EVALUATION.md --- EVALUATION.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/EVALUATION.md b/EVALUATION.md index af89165..4b4ca41 100644 --- a/EVALUATION.md +++ b/EVALUATION.md @@ -16,7 +16,7 @@ ## Introduction Our objective is to monitor and improve the RAG pipeline for **AI-OPS**, that requires context-specific data from -*Cybersecurity* and *Penetration Testing* fields; also we want the evaluation process to be as automated as possible. +*Cybersecurity* and *Penetration Testing* fields. The evaluation workflow is split in two steps: From 71eb27d7407c18c660a2466fbd50d250eb8ee9b0 Mon Sep 17 00:00:00 2001 From: Antonino Lorenzo <94693967+antoninoLorenzo@users.noreply.github.com> Date: Tue, 16 Jul 2024 20:13:11 +0200 Subject: [PATCH 2/3] Update EVALUATION.md --- EVALUATION.md | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) diff --git a/EVALUATION.md b/EVALUATION.md index 4b4ca41..dfebf20 100644 --- a/EVALUATION.md +++ b/EVALUATION.md @@ -1,11 +1,9 @@ **Table of Contents** 1. [Agent Evaluation](#agent-evaluation) 2. [RAG Evaluation](#rag-evaluation) - 1. [Introduction](#introduction) - 2. [Results](#results) - - 3. [Context Precision](#context-precision) - 4. [Context Recall](#context-recall) + - [Introduction](#introduction) + - [Results](#results) + # 📈Agent Evaluation From 6ae1859ac4f27451dc425d5a96e3ed600982ea8d Mon Sep 17 00:00:00 2001 From: Antonino Lorenzo <94693967+antoninoLorenzo@users.noreply.github.com> Date: Tue, 16 Jul 2024 20:14:58 +0200 Subject: [PATCH 3/3] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 0fc136a..4209035 100644 --- a/README.md +++ b/README.md @@ -8,7 +8,7 @@ 3. [Installation](#-install) - [End-User](#end-user) - [Development](#development) -4. [System Structure](#usage) +4. [Usage](#usage) - [Components](#components) - [Supported Models](#supported-ollama-models) 5. [Tools](#tools)