Orensomekh commited on
Commit
ffadbea
·
verified ·
1 Parent(s): 66fa4d8

Delete Operational_Instructions/create-submission-result 1.ipynb

Browse files
Operational_Instructions/create-submission-result 1.ipynb DELETED
@@ -1,143 +0,0 @@
1
- {
2
- "cells": [
3
- {
4
- "cell_type": "code",
5
- "execution_count": null,
6
- "id": "a5e875f5",
7
- "metadata": {},
8
- "outputs": [
9
- {
10
- "ename": "",
11
- "evalue": "",
12
- "output_type": "error",
13
- "traceback": [
14
- "\u001b[1;31mRunning cells with 'Python 3.13.1' requires the ipykernel package.\n",
15
- "\u001b[1;31mRun the following command to install 'ipykernel' into the Python environment. \n",
16
- "\u001b[1;31mCommand: '/opt/homebrew/bin/python3 -m pip install ipykernel -U --user --force-reinstall'"
17
- ]
18
- }
19
- ],
20
- "source": [
21
- "import pandas as pd\n",
22
- "import jsonschema\n",
23
- "from jsonschema import validate\n",
24
- "import json\n",
25
- "\n",
26
- "# LiveRAG Answer JSON schema: \n",
27
- "json_schema = \"\"\"\n",
28
- "{ \n",
29
- "\"$schema\": \"http://json-schema.org/draft-07/schema#\", \n",
30
- "\n",
31
- " \"title\": \"Answer file schema\", \n",
32
- " \"type\": \"object\", \n",
33
- " \"properties\": { \n",
34
- " \"id\": { \n",
35
- " \"type\": \"integer\", \n",
36
- " \"description\": \"Question ID\" \n",
37
- " }, \n",
38
- " \"question\": { \n",
39
- " \"type\": \"string\", \n",
40
- " \"description\": \"The question\" \n",
41
- " }, \n",
42
- " \"passages\": { \n",
43
- " \"type\": \"array\", \n",
44
- " \"description\": \"Passages used and related FineWeb doc IDs, ordered by decreasing importance\", \n",
45
- " \"items\": { \n",
46
- " \"type\": \"object\", \n",
47
- " \"properties\": {\n",
48
- " \"passage\": { \n",
49
- " \"type\": \"string\", \n",
50
- " \"description\": \"Passage text\" \n",
51
- " }, \n",
52
- " \"doc_IDs\": {\n",
53
- " \"type\": \"array\", \n",
54
- " \"description\": \"Passage related FineWeb doc IDs, ordered by decreasing importance\", \n",
55
- " \"items\": { \n",
56
- " \"type\": \"string\", \n",
57
- " \"description\": \"FineWeb doc ID, e.g., <urn:uuid:d69cbebc-133a-4ebe-9378-68235ec9f091>\"\n",
58
- " } \n",
59
- " } \n",
60
- " },\n",
61
- " \"required\": [\"passage\", \"doc_IDs\"]\n",
62
- " }\n",
63
- " }, \n",
64
- " \"final_prompt\": {\n",
65
- " \"type\": \"string\",\n",
66
- " \"description\": \"Final prompt, as submitted to Falcon LLM\"\n",
67
- " },\n",
68
- " \"answer\": {\n",
69
- " \"type\": \"string\",\n",
70
- " \"description\": \"Your answer\"\n",
71
- " }\n",
72
- " },\n",
73
- " \"required\": [\"id\", \"question\", \"passages\", \"final_prompt\", \"answer\"]\n",
74
- "}\n",
75
- "\"\"\"\n",
76
- "\n",
77
- "# Code that generates the output\n",
78
- "answers = pd.DataFrame({\n",
79
- " \"id\": [1, 2],\n",
80
- " \"question\": [\"What is the capital of France?\", \"What is the capital of Germany?\"],\n",
81
- " \"passages\": [\n",
82
- " [\n",
83
- " {\"passage\": \"Paris is the capital and most populous city of France.\",\n",
84
- " \"doc_IDs\": [\"<urn:uuid:1234abcd-5678-efgh-9101-ijklmnopqrst>\", \"<urn:uuid:1234abcd-5678-efgh-9202-ijklmnopqrst>\"]},\n",
85
- " {\"passage\": \"France is located in Western Europe.\",\n",
86
- " \"doc_IDs\": [\"<urn:uuid:1234abcd-5678-efgh-9101-ijklmnopqrst>\"]}\n",
87
- " ],\n",
88
- " [\n",
89
- " {\"passage\": \"Berlin is the capital of Germany.\",\n",
90
- " \"doc_IDs\": [\"<urn:uuid:1234abcd-5678-efgh-9101-ijklmnopqrst>\"]}\n",
91
- " ]\n",
92
- " ],\n",
93
- " \"final_prompt\": [\n",
94
- " \"Using the following - Paris is the capital and most populous city of France - and - France is located in Western Europe - answer the question: What is the capital of France?\",\n",
95
- " \"Using the following - Berlin is the capital of Germany - answer the question: What is the capital of Germany?\"\n",
96
- " ],\n",
97
- " \"answer\": [\"Paris\", \"Berlin\"]\n",
98
- "})\n",
99
- "\n",
100
- "# Convert to JSON format\n",
101
- "answers_json = answers.to_json(orient='records', lines=True, force_ascii=False)\n",
102
- "\n",
103
- "# Or just save to a file\n",
104
- "answers.to_json(\"answers.jsonl\", orient='records', lines=True, force_ascii=False)\n",
105
- "\n",
106
- "# Load the file to make sure it is ok\n",
107
- "loaded_answers = pd.read_json(\"answers.jsonl\", lines=True)\n",
108
- "\n",
109
- "# Load the JSON schema\n",
110
- "schema = json.loads(json_schema)\n",
111
- "\n",
112
- "# Validate each Answer JSON object against the schema\n",
113
- "for answer in loaded_answers.to_dict(orient='records'):\n",
114
- " try:\n",
115
- " validate(instance=answer, schema=schema)\n",
116
- " print(f\"Answer {answer['id']} is valid.\")\n",
117
- " except jsonschema.exceptions.ValidationError as e:\n",
118
- " print(f\"Answer {answer['id']} is invalid: {e.message}\")"
119
- ]
120
- }
121
- ],
122
- "metadata": {
123
- "kernelspec": {
124
- "display_name": "Python 3",
125
- "language": "python",
126
- "name": "python3"
127
- },
128
- "language_info": {
129
- "codemirror_mode": {
130
- "name": "ipython",
131
- "version": 3
132
- },
133
- "file_extension": ".py",
134
- "mimetype": "text/x-python",
135
- "name": "python",
136
- "nbconvert_exporter": "python",
137
- "pygments_lexer": "ipython3",
138
- "version": "3.13.1"
139
- }
140
- },
141
- "nbformat": 4,
142
- "nbformat_minor": 5
143
- }