jarianc/FactsDB
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Implement optimized database schema and AI prompt - removed title field, summary to fact, removed financial_impact and main_points

Browse Source
This commit is contained in:
Jarian Cottingham 2026-02-02 20:48:59 -06:00
parent 9344a69636
commit 332f49eeee
2 changed files with 12 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

19
factsdb/ai_processor.py
View File

@ -41,29 +41,22 @@ class AIEndpointClient:
def extract_facts(self, text_content: str, prompt: str, model: str = "gpt-oss") -> Dict[str, Any]: def extract_facts(self, text_content: str, prompt: str, model: str = "gpt-oss") -> Dict[str, Any]:
"""Extract facts from text using AI""" """Extract facts from text using AI"""
# Default prompt from requirements # Default prompt from requirements - optimized for facts extraction
default_prompt = """Extract key facts from the following article in structured JSON format. default_prompt = """Extract key facts from the following article in structured JSON format.
Return only valid JSON without any additional text. Return only valid JSON without any additional text.
Article Title: {title}
Article Content: {article_content[:3000]}... Article Content: {article_content[:3000]}...
Extract the following information: Extract the following information:
1. Main topic/subject 1. Key entities (companies, people, locations, organizations)
2. Key entities (companies, people, locations, organizations) 2. Key dates or time periods mentioned
3. Financial impact or implications 3. Main facts from the article
4. Key dates or time periods mentioned
5. Summary of main points
Format the response as a JSON object with these fields: Format the response as a JSON object with these fields:
{ {
"title": "{title}", "fact": "main fact extracted from the article",
"summary": "brief summary",
"main_topic": "main topic",
"key_entities": ["entity1", "entity2"], "key_entities": ["entity1", "entity2"],
"financial_impact": "positive/negative/neutral", "key_dates": ["date1", "date2"]
"key_dates": ["date1", "date2"],
"main_points": ["point1", "point2", "point3"]
}""" }"""
# Use provided prompt or default # Use provided prompt or default

28
factsdb/database.py
View File

@ -29,13 +29,9 @@ class DatabaseManager:
CREATE TABLE IF NOT EXISTS facts ( CREATE TABLE IF NOT EXISTS facts (
id INTEGER PRIMARY KEY AUTOINCREMENT, id INTEGER PRIMARY KEY AUTOINCREMENT,
table_name TEXT NOT NULL, table_name TEXT NOT NULL,
title TEXT, fact TEXT,
summary TEXT,
main_topic TEXT,
key_entities TEXT, key_entities TEXT,
financial_impact TEXT,
key_dates TEXT, key_dates TEXT,
main_points TEXT,
file_path TEXT, file_path TEXT,
extracted_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP, extracted_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
processed BOOLEAN DEFAULT FALSE processed BOOLEAN DEFAULT FALSE
@ -125,22 +121,16 @@ class DatabaseManager:
# Convert lists to JSON strings for storage # Convert lists to JSON strings for storage
key_entities = str(fact_data.get('key_entities', [])) key_entities = str(fact_data.get('key_entities', []))
key_dates = str(fact_data.get('key_dates', [])) key_dates = str(fact_data.get('key_dates', []))
main_points = str(fact_data.get('main_points', []))
cursor.execute(''' cursor.execute('''
INSERT INTO facts ( INSERT INTO facts (
table_name, title, summary, main_topic, key_entities, table_name, fact, key_entities, key_dates, file_path
financial_impact, key_dates, main_points, file_path ) VALUES (?, ?, ?, ?, ?)
) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
''', ( ''', (
table_name, table_name,
fact_data.get('title'), fact_data.get('fact'),
fact_data.get('summary'),
fact_data.get('main_topic'),
key_entities, key_entities,
fact_data.get('financial_impact'),
key_dates, key_dates,
main_points,
fact_data.get('file_path') fact_data.get('file_path')
)) ))
@ -166,8 +156,7 @@ class DatabaseManager:
with self.get_connection() as conn: with self.get_connection() as conn:
cursor = conn.cursor() cursor = conn.cursor()
cursor.execute(''' cursor.execute('''
SELECT id, table_name, title, summary, main_topic, key_entities, SELECT id, table_name, fact, key_entities, key_dates, file_path, extracted_at
financial_impact, key_dates, main_points, file_path, extracted_at
FROM facts FROM facts
WHERE table_name = ? WHERE table_name = ?
ORDER BY extracted_at DESC ORDER BY extracted_at DESC
@ -185,8 +174,6 @@ class DatabaseManager:
fact['key_entities'] = eval(fact['key_entities']) fact['key_entities'] = eval(fact['key_entities'])
if fact['key_dates']: if fact['key_dates']:
fact['key_dates'] = eval(fact['key_dates']) fact['key_dates'] = eval(fact['key_dates'])
if fact['main_points']:
fact['main_points'] = eval(fact['main_points'])
facts.append(fact) facts.append(fact)
return facts return facts
@ -196,8 +183,7 @@ class DatabaseManager:
with self.get_connection() as conn: with self.get_connection() as conn:
cursor = conn.cursor() cursor = conn.cursor()
cursor.execute(''' cursor.execute('''
SELECT id, table_name, title, summary, main_topic, key_entities, SELECT id, table_name, fact, key_entities, key_dates, file_path, extracted_at
financial_impact, key_dates, main_points, file_path, extracted_at
FROM facts FROM facts
WHERE id = ? WHERE id = ?
''', (fact_id,)) ''', (fact_id,))
@ -211,8 +197,6 @@ class DatabaseManager:
fact['key_entities'] = eval(fact['key_entities']) fact['key_entities'] = eval(fact['key_entities'])
if fact['key_dates']: if fact['key_dates']:
fact['key_dates'] = eval(fact['key_dates']) fact['key_dates'] = eval(fact['key_dates'])
if fact['main_points']:
fact['main_points'] = eval(fact['main_points'])
return fact return fact
return None return None