Semantisk minne (vektoriserte fakta)

CREATE TABLE semantic_facts (
    id UUID PRIMARY KEY,
    user_id TEXT NOT NULL,
    fact TEXT NOT NULL,
    embedding vector(1536),
    source TEXT,                    -- 'extracted' / 'user-stated' / 'system'
    confidence REAL DEFAULT 1.0,
    created_at TIMESTAMPTZ DEFAULT NOW()
);

extract_prompt = '''
From the conversation below, list any new facts about the user.
Return JSON: [{"fact": "...", "confidence": 0.0-1.0}]

Conversation:
{transcript}
'''
print(extract_prompt.strip())

import uuid

for f in extracted:
    vec = embed(f['fact'])
    conn.execute('''
        INSERT INTO semantic_facts (id, user_id, fact, embedding, confidence, source)
        VALUES (%s, %s, %s, %s, %s, 'extracted')
    ''', (str(uuid.uuid4()), user_id, f['fact'], vec, f['confidence']))

def relevant_facts(user_id, query, k=5):
    qvec = embed(query)
    rows = conn.execute('''
        SELECT fact FROM semantic_facts
        WHERE user_id = %s
        ORDER BY embedding <=> %s LIMIT %s
    ''', (user_id, qvec, k))
    return [r[0] for r in rows]

facts = relevant_facts(user_id, user_question)
system = SYSTEM_PROMPT + '\n\nKnown facts:\n' + '\n'.join(facts)

def reconcile(user_id, new_fact):
    similar = relevant_facts(user_id, new_fact, k=3)
    response = llm.invoke(f'Is the new fact ({new_fact}) consistent with existing facts ({similar})? If contradicting, return the obsolete one.')
    if response.has_contradiction:
        mark_obsolete(response.obsolete_id)
    save_fact(new_fact)

rows = conn.execute('''
    SELECT fact FROM semantic_facts
    WHERE user_id = %s AND confidence > 0.6
    ORDER BY embedding <=> %s LIMIT %s
''', ...)

UPDATE semantic_facts
SET confidence = confidence * 0.95
WHERE created_at < NOW() - INTERVAL '30 days';

tools = [
    {'name': 'remember_fact', 'description': 'Save a new fact about the user'},
    {'name': 'forget_fact', 'description': 'Remove a stored fact'},
    {'name': 'recall_facts', 'description': 'Search relevant facts for a query'}
]
import json
print(json.dumps(tools, indent=2))