From 332f49eeeeecf4a001ea265c054382ac54c32359 Mon Sep 17 00:00:00 2001
From: Jarian Cottingham <jarianc@proton.me>
Date: Mon, 2 Feb 2026 20:48:59 -0600
Subject: [PATCH] Implement optimized database schema and AI prompt - removed
 title field, summary to fact, removed financial_impact and main_points

---
 factsdb/ai_processor.py | 19 ++++++-------------
 factsdb/database.py     | 28 ++++++----------------------
 2 files changed, 12 insertions(+), 35 deletions(-)

diff --git a/factsdb/ai_processor.py b/factsdb/ai_processor.py
index e4eb54b..bd594c0 100644
--- a/factsdb/ai_processor.py
+++ b/factsdb/ai_processor.py
@@ -41,29 +41,22 @@ class AIEndpointClient:
     
     def extract_facts(self, text_content: str, prompt: str, model: str = "gpt-oss") -> Dict[str, Any]:
         """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.
 Return only valid JSON without any additional text.
 
-Article Title: {title}
 Article Content: {article_content[:3000]}...
 
 Extract the following information:
-1. Main topic/subject
-2. Key entities (companies, people, locations, organizations)
-3. Financial impact or implications
-4. Key dates or time periods mentioned
-5. Summary of main points
+1. Key entities (companies, people, locations, organizations)
+2. Key dates or time periods mentioned
+3. Main facts from the article
 
 Format the response as a JSON object with these fields:
 {
-    "title": "{title}",
-    "summary": "brief summary",
-    "main_topic": "main topic",
+    "fact": "main fact extracted from the article",
     "key_entities": ["entity1", "entity2"],
-    "financial_impact": "positive/negative/neutral",
-    "key_dates": ["date1", "date2"],
-    "main_points": ["point1", "point2", "point3"]
+    "key_dates": ["date1", "date2"]
 }"""
         
         # Use provided prompt or default
diff --git a/factsdb/database.py b/factsdb/database.py
index 2254a28..e47dfd0 100644
--- a/factsdb/database.py
+++ b/factsdb/database.py
@@ -29,13 +29,9 @@ class DatabaseManager:
                 CREATE TABLE IF NOT EXISTS facts (
                     id INTEGER PRIMARY KEY AUTOINCREMENT,
                     table_name TEXT NOT NULL,
-                    title TEXT,
-                    summary TEXT,
-                    main_topic TEXT,
+                    fact TEXT,
                     key_entities TEXT,
-                    financial_impact TEXT,
                     key_dates TEXT,
-                    main_points TEXT,
                     file_path TEXT,
                     extracted_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
                     processed BOOLEAN DEFAULT FALSE
@@ -125,22 +121,16 @@ class DatabaseManager:
             # Convert lists to JSON strings for storage
             key_entities = str(fact_data.get('key_entities', []))
             key_dates = str(fact_data.get('key_dates', []))
-            main_points = str(fact_data.get('main_points', []))
             
             cursor.execute('''
                 INSERT INTO facts (
-                    table_name, title, summary, main_topic, key_entities,
-                    financial_impact, key_dates, main_points, file_path
-                ) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
+                    table_name, fact, key_entities, key_dates, file_path
+                ) VALUES (?, ?, ?, ?, ?)
             ''', (
                 table_name,
-                fact_data.get('title'),
-                fact_data.get('summary'),
-                fact_data.get('main_topic'),
+                fact_data.get('fact'),
                 key_entities,
-                fact_data.get('financial_impact'),
                 key_dates,
-                main_points,
                 fact_data.get('file_path')
             ))
             
@@ -166,8 +156,7 @@ class DatabaseManager:
         with self.get_connection() as conn:
             cursor = conn.cursor()
             cursor.execute('''
-                SELECT id, table_name, title, summary, main_topic, key_entities,
-                       financial_impact, key_dates, main_points, file_path, extracted_at
+                SELECT id, table_name, fact, key_entities, key_dates, file_path, extracted_at
                 FROM facts 
                 WHERE table_name = ?
                 ORDER BY extracted_at DESC
@@ -185,8 +174,6 @@ class DatabaseManager:
                     fact['key_entities'] = eval(fact['key_entities'])
                 if fact['key_dates']:
                     fact['key_dates'] = eval(fact['key_dates'])
-                if fact['main_points']:
-                    fact['main_points'] = eval(fact['main_points'])
                 facts.append(fact)
             
             return facts
@@ -196,8 +183,7 @@ class DatabaseManager:
         with self.get_connection() as conn:
             cursor = conn.cursor()
             cursor.execute('''
-                SELECT id, table_name, title, summary, main_topic, key_entities,
-                       financial_impact, key_dates, main_points, file_path, extracted_at
+                SELECT id, table_name, fact, key_entities, key_dates, file_path, extracted_at
                 FROM facts 
                 WHERE id = ?
             ''', (fact_id,))
@@ -211,8 +197,6 @@ class DatabaseManager:
                     fact['key_entities'] = eval(fact['key_entities'])
                 if fact['key_dates']:
                     fact['key_dates'] = eval(fact['key_dates'])
-                if fact['main_points']:
-                    fact['main_points'] = eval(fact['main_points'])
                 return fact
             return None