improve readability (#6)

Author: jjmachan

rag-playground/basecamp-handbook/baseline.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "5d7d6d21",
+   "id": "8621e835",
    "metadata": {},
    "source": [
     "## Baseline\n",
@@ -13,7 +13,7 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "fae55e46",
+   "id": "a84d1f79",
    "metadata": {},
    "outputs": [
     {
@@ -59,7 +59,7 @@
   {
    "cell_type": "code",
    "execution_count": 4,
-   "id": "ea340a1b",
+   "id": "a2c5f874",
    "metadata": {},
    "outputs": [
     {
@@ -85,7 +85,7 @@
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "e59b71b8",
+   "id": "a6519df0",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -98,7 +98,7 @@
   {
    "cell_type": "code",
    "execution_count": 7,
-   "id": "5b6f4c8b",
+   "id": "baa208cd",
    "metadata": {},
    "outputs": [
     {
@@ -118,7 +118,7 @@
   {
    "cell_type": "code",
    "execution_count": 8,
-   "id": "821307b9",
+   "id": "118d251d",
    "metadata": {},
    "outputs": [
     {
@@ -137,7 +137,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b5e20959",
+   "id": "e165bd7a",
    "metadata": {},
    "source": [
     "### Running Evaluations"
@@ -146,7 +146,7 @@
   {
    "cell_type": "code",
    "execution_count": 11,
-   "id": "b7f13a15",
+   "id": "4ced68af",
    "metadata": {},
    "outputs": [
     {
@@ -192,7 +192,7 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "70b5b3b3",
+   "id": "e14aafad",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -203,7 +203,7 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "1a0bc417",
+   "id": "d5594de4",
    "metadata": {},
    "outputs": [
     {
@@ -273,7 +273,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e7c24549",
+   "id": "b4529e58",
    "metadata": {},
    "source": [
     "Seems like overall scores are good. Lets look into a bit more to see which questions gave bad results."
@@ -282,7 +282,7 @@
   {
    "cell_type": "code",
    "execution_count": 15,
-   "id": "8a0ad424",
+   "id": "f2211f35",
    "metadata": {},
    "outputs": [
     {
@@ -407,7 +407,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "f65cb827",
+   "id": "57138d44",
    "metadata": {},
    "source": [
     "With a small utility function we can see the question, answer, contexts."
@@ -416,7 +416,7 @@
   {
    "cell_type": "code",
    "execution_count": 45,
-   "id": "5b94e540",
+   "id": "e496210c",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -451,7 +451,7 @@
   {
    "cell_type": "code",
    "execution_count": 46,
-   "id": "9842219a",
+   "id": "ec86e750",
    "metadata": {},
    "outputs": [
     {
@@ -492,7 +492,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d85441a1",
+   "id": "ad2639ba",
    "metadata": {},
    "source": [
     "Seems like the question is a bit off and the LLM actually makes a lot of stuff to answer the questions because the retrieved context is not very good.\n",
@@ -528,7 +528,7 @@
   {
    "cell_type": "code",
    "execution_count": 44,
-   "id": "df5cc616",
+   "id": "d8310bef",
    "metadata": {},
    "outputs": [
     {
@@ -600,7 +600,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "b89aaf54",
+   "id": "7332640c",
    "metadata": {},
    "source": [
     "### why?\n",
@@ -610,7 +610,7 @@
   {
    "cell_type": "code",
    "execution_count": 47,
-   "id": "259c31da",
+   "id": "3431e6f3",
    "metadata": {},
    "outputs": [
     {