Spaces:
Running
Running
File size: 13,786 Bytes
dbd33b2 507c938 dbd33b2 66a5452 dbd33b2 a61b32e dbd33b2 66a5452 dbd33b2 507c938 a61b32e 507c938 dbd33b2 507c938 a61b32e 507c938 a61b32e 507c938 dbd33b2 507c938 a61b32e 507c938 a61b32e 507c938 a61b32e 66a5452 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 |
import sqlite3
import os
class DatabaseHandler:
def __init__(self, db_path='data/sqlite.db'):
self.db_path = db_path
self.conn = None
self.create_tables()
self.update_schema()
def create_tables(self):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
# Existing tables
cursor.execute('''
CREATE TABLE IF NOT EXISTS videos (
id INTEGER PRIMARY KEY AUTOINCREMENT,
youtube_id TEXT UNIQUE,
title TEXT,
channel_name TEXT,
processed_date TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
upload_date TEXT,
view_count INTEGER,
like_count INTEGER,
comment_count INTEGER,
video_duration TEXT,
transcript_content TEXT
)
''')
cursor.execute('''
CREATE TABLE IF NOT EXISTS user_feedback (
id INTEGER PRIMARY KEY AUTOINCREMENT,
video_id INTEGER,
query TEXT,
feedback INTEGER,
timestamp TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
FOREIGN KEY (video_id) REFERENCES videos (id)
)
''')
cursor.execute('''
CREATE TABLE IF NOT EXISTS embedding_models (
id INTEGER PRIMARY KEY AUTOINCREMENT,
model_name TEXT UNIQUE,
description TEXT
)
''')
cursor.execute('''
CREATE TABLE IF NOT EXISTS elasticsearch_indices (
id INTEGER PRIMARY KEY AUTOINCREMENT,
video_id INTEGER,
index_name TEXT,
embedding_model_id INTEGER,
FOREIGN KEY (video_id) REFERENCES videos (id),
FOREIGN KEY (embedding_model_id) REFERENCES embedding_models (id)
)
''')
# New tables for ground truth and evaluation
cursor.execute('''
CREATE TABLE IF NOT EXISTS ground_truth (
id INTEGER PRIMARY KEY AUTOINCREMENT,
video_id TEXT,
question TEXT,
generation_date TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
UNIQUE(video_id, question)
)
''')
cursor.execute('''
CREATE TABLE IF NOT EXISTS search_performance (
id INTEGER PRIMARY KEY AUTOINCREMENT,
video_id TEXT,
hit_rate REAL,
mrr REAL,
evaluation_date TIMESTAMP DEFAULT CURRENT_TIMESTAMP
)
''')
cursor.execute('''
CREATE TABLE IF NOT EXISTS search_parameters (
id INTEGER PRIMARY KEY AUTOINCREMENT,
video_id TEXT,
parameter_name TEXT,
parameter_value REAL,
score REAL,
evaluation_date TIMESTAMP DEFAULT CURRENT_TIMESTAMP
)
''')
cursor.execute('''
CREATE TABLE IF NOT EXISTS rag_evaluations (
id INTEGER PRIMARY KEY AUTOINCREMENT,
video_id TEXT,
question TEXT,
answer TEXT,
relevance TEXT,
explanation TEXT,
evaluation_date TIMESTAMP DEFAULT CURRENT_TIMESTAMP
)
''')
conn.commit()
def update_schema(self):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute("PRAGMA table_info(videos)")
columns = [column[1] for column in cursor.fetchall()]
new_columns = [
("upload_date", "TEXT"),
("view_count", "INTEGER"),
("like_count", "INTEGER"),
("comment_count", "INTEGER"),
("video_duration", "TEXT"),
("transcript_content", "TEXT")
]
for col_name, col_type in new_columns:
if col_name not in columns:
cursor.execute(f"ALTER TABLE videos ADD COLUMN {col_name} {col_type}")
conn.commit()
def add_video(self, video_data):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
INSERT OR REPLACE INTO videos
(youtube_id, title, channel_name, upload_date, view_count, like_count, comment_count, video_duration, transcript_content)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
''', (
video_data['video_id'],
video_data['title'],
video_data['author'],
video_data['upload_date'],
video_data['view_count'],
video_data['like_count'],
video_data['comment_count'],
video_data['video_duration'],
video_data['transcript_content']
))
conn.commit()
return cursor.lastrowid
def add_user_feedback(self, video_id, query, feedback):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
INSERT INTO user_feedback (video_id, query, feedback)
VALUES (?, ?, ?)
''', (video_id, query, feedback))
conn.commit()
def add_embedding_model(self, model_name, description):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
INSERT OR IGNORE INTO embedding_models (model_name, description)
VALUES (?, ?)
''', (model_name, description))
conn.commit()
return cursor.lastrowid
def add_elasticsearch_index(self, video_id, index_name, embedding_model_id):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
INSERT INTO elasticsearch_indices (video_id, index_name, embedding_model_id)
VALUES (?, ?, ?)
''', (video_id, index_name, embedding_model_id))
conn.commit()
def get_video_by_youtube_id(self, youtube_id):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('SELECT * FROM videos WHERE youtube_id = ?', (youtube_id,))
return cursor.fetchone()
def get_elasticsearch_index(self, video_id, embedding_model):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
SELECT ei.index_name
FROM elasticsearch_indices ei
JOIN embedding_models em ON ei.embedding_model_id = em.id
JOIN videos v ON ei.video_id = v.id
WHERE v.youtube_id = ? AND em.model_name = ?
''', (video_id, embedding_model))
result = cursor.fetchone()
return result[0] if result else None
def get_all_videos(self):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
SELECT youtube_id, title, channel_name, upload_date
FROM videos
ORDER BY upload_date DESC
''')
return cursor.fetchall()
def get_elasticsearch_index_by_youtube_id(self, youtube_id):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
SELECT ei.index_name
FROM elasticsearch_indices ei
JOIN videos v ON ei.video_id = v.id
WHERE v.youtube_id = ?
''', (youtube_id,))
result = cursor.fetchone()
return result[0] if result else None
def get_transcript_content(self, youtube_id):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
SELECT transcript_content
FROM videos
WHERE youtube_id = ?
''', (youtube_id,))
result = cursor.fetchone()
return result[0] if result else None
# This method is no longer needed as transcript is added in add_video
# def add_transcript_content(self, youtube_id, transcript_content):
# with sqlite3.connect(self.db_path) as conn:
# cursor = conn.cursor()
# cursor.execute('''
# UPDATE videos
# SET transcript_content = ?
# WHERE youtube_id = ?
# ''', (transcript_content, youtube_id))
# conn.commit()
def add_ground_truth_questions(self, video_id, questions):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
for question in questions:
try:
cursor.execute('''
INSERT OR IGNORE INTO ground_truth (video_id, question)
VALUES (?, ?)
''', (video_id, question))
except sqlite3.IntegrityError:
continue # Skip duplicate questions
conn.commit()
def get_ground_truth_by_video(self, video_id):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
SELECT gt.*, v.channel_name
FROM ground_truth gt
JOIN videos v ON gt.video_id = v.youtube_id
WHERE gt.video_id = ?
ORDER BY gt.generation_date DESC
''', (video_id,))
return cursor.fetchall()
def get_ground_truth_by_channel(self, channel_name):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
SELECT gt.*, v.channel_name
FROM ground_truth gt
JOIN videos v ON gt.video_id = v.youtube_id
WHERE v.channel_name = ?
ORDER BY gt.generation_date DESC
''', (channel_name,))
return cursor.fetchall()
def get_all_ground_truth(self):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
SELECT gt.*, v.channel_name
FROM ground_truth gt
JOIN videos v ON gt.video_id = v.youtube_id
ORDER BY gt.generation_date DESC
''')
return cursor.fetchall()
def save_search_performance(self, video_id, hit_rate, mrr):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
INSERT INTO search_performance (video_id, hit_rate, mrr)
VALUES (?, ?, ?)
''', (video_id, hit_rate, mrr))
conn.commit()
def save_search_parameters(self, video_id, parameters, score):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
for param_name, param_value in parameters.items():
cursor.execute('''
INSERT INTO search_parameters (video_id, parameter_name, parameter_value, score)
VALUES (?, ?, ?, ?)
''', (video_id, param_name, param_value, score))
conn.commit()
def save_rag_evaluation(self, evaluation_data):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
cursor.execute('''
INSERT INTO rag_evaluations
(video_id, question, answer, relevance, explanation)
VALUES (?, ?, ?, ?, ?)
''', (
evaluation_data['video_id'],
evaluation_data['question'],
evaluation_data['answer'],
evaluation_data['relevance'],
evaluation_data['explanation']
))
conn.commit()
def get_latest_evaluation_results(self, video_id=None):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
if video_id:
cursor.execute('''
SELECT * FROM rag_evaluations
WHERE video_id = ?
ORDER BY evaluation_date DESC
''', (video_id,))
else:
cursor.execute('''
SELECT * FROM rag_evaluations
ORDER BY evaluation_date DESC
''')
return cursor.fetchall()
def get_latest_search_performance(self, video_id=None):
with sqlite3.connect(self.db_path) as conn:
cursor = conn.cursor()
if video_id:
cursor.execute('''
SELECT * FROM search_performance
WHERE video_id = ?
ORDER BY evaluation_date DESC
LIMIT 1
''', (video_id,))
else:
cursor.execute('''
SELECT * FROM search_performance
ORDER BY evaluation_date DESC
''')
return cursor.fetchall() |