MemPalace: palace architecture, AAAK compression, knowledge graph
The memory system: - Palace structure: Wings (people/projects) → Rooms (topics) → Closets (AAAK compressed) → Drawers (verbatim transcripts) - Halls connect related rooms within a wing - Tunnels cross-reference rooms across wings - AAAK: 30x lossless compression dialect for AI agents - Knowledge graph: temporal entity-relationship triples (SQLite) - Palace graph: room-based navigation with tunnel detection - MCP server: 19 tools — search, graph traversal, agent diary, AAAK auto-teach - Onboarding: guided setup generates wing config + AAAK entity registry - Contradiction detection: catches wrong pronouns, names, ages - Auto-save hooks for Claude Code 96.6% Recall@5 on LongMemEval — highest zero-API score published. 100% with optional Haiku rerank (500/500). Local. Free. No API key required.
This commit is contained in:
Milla Jovovich
@@ -0,0 +1,253 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
normalize.py — Convert any chat export format to MemPalace transcript format.
|
||||
|
||||
Supported:
|
||||
- Plain text with > markers (pass through)
|
||||
- Claude.ai JSON export
|
||||
- ChatGPT conversations.json
|
||||
- Claude Code JSONL
|
||||
- Slack JSON export
|
||||
- Plain text (pass through for paragraph chunking)
|
||||
|
||||
No API key. No internet. Everything local.
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
|
||||
def normalize(filepath: str) -> str:
|
||||
"""
|
||||
Load a file and normalize to transcript format if it's a chat export.
|
||||
Plain text files pass through unchanged.
|
||||
"""
|
||||
try:
|
||||
with open(filepath, "r", encoding="utf-8", errors="replace") as f:
|
||||
content = f.read()
|
||||
except Exception as e:
|
||||
raise IOError(f"Could not read {filepath}: {e}")
|
||||
|
||||
if not content.strip():
|
||||
return content
|
||||
|
||||
# Already has > markers — pass through
|
||||
lines = content.split("\n")
|
||||
if sum(1 for line in lines if line.strip().startswith(">")) >= 3:
|
||||
return content
|
||||
|
||||
# Try JSON normalization
|
||||
ext = Path(filepath).suffix.lower()
|
||||
if ext in (".json", ".jsonl") or content.strip()[:1] in ("{", "["):
|
||||
normalized = _try_normalize_json(content)
|
||||
if normalized:
|
||||
return normalized
|
||||
|
||||
return content
|
||||
|
||||
|
||||
def _try_normalize_json(content: str) -> Optional[str]:
|
||||
"""Try all known JSON chat schemas."""
|
||||
|
||||
normalized = _try_claude_code_jsonl(content)
|
||||
if normalized:
|
||||
return normalized
|
||||
|
||||
try:
|
||||
data = json.loads(content)
|
||||
except json.JSONDecodeError:
|
||||
return None
|
||||
|
||||
for parser in (_try_claude_ai_json, _try_chatgpt_json, _try_slack_json):
|
||||
normalized = parser(data)
|
||||
if normalized:
|
||||
return normalized
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def _try_claude_code_jsonl(content: str) -> Optional[str]:
|
||||
"""Claude Code JSONL sessions."""
|
||||
lines = [line.strip() for line in content.strip().split("\n") if line.strip()]
|
||||
messages = []
|
||||
for line in lines:
|
||||
try:
|
||||
entry = json.loads(line)
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
if not isinstance(entry, dict):
|
||||
continue
|
||||
msg_type = entry.get("type", "")
|
||||
message = entry.get("message", {})
|
||||
if msg_type == "human":
|
||||
text = _extract_content(message.get("content", ""))
|
||||
if text:
|
||||
messages.append(("user", text))
|
||||
elif msg_type == "assistant":
|
||||
text = _extract_content(message.get("content", ""))
|
||||
if text:
|
||||
messages.append(("assistant", text))
|
||||
if len(messages) >= 2:
|
||||
return _messages_to_transcript(messages)
|
||||
return None
|
||||
|
||||
|
||||
def _try_claude_ai_json(data) -> Optional[str]:
|
||||
"""Claude.ai JSON export: [{"role": "user", "content": "..."}]"""
|
||||
if isinstance(data, dict):
|
||||
data = data.get("messages", data.get("chat_messages", []))
|
||||
if not isinstance(data, list):
|
||||
return None
|
||||
messages = []
|
||||
for item in data:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
role = item.get("role", "")
|
||||
text = _extract_content(item.get("content", ""))
|
||||
if role in ("user", "human") and text:
|
||||
messages.append(("user", text))
|
||||
elif role in ("assistant", "ai") and text:
|
||||
messages.append(("assistant", text))
|
||||
if len(messages) >= 2:
|
||||
return _messages_to_transcript(messages)
|
||||
return None
|
||||
|
||||
|
||||
def _try_chatgpt_json(data) -> Optional[str]:
|
||||
"""ChatGPT conversations.json with mapping tree."""
|
||||
if not isinstance(data, dict) or "mapping" not in data:
|
||||
return None
|
||||
mapping = data["mapping"]
|
||||
messages = []
|
||||
# Find root: prefer node with parent=None AND no message (synthetic root)
|
||||
root_id = None
|
||||
fallback_root = None
|
||||
for node_id, node in mapping.items():
|
||||
if node.get("parent") is None:
|
||||
if node.get("message") is None:
|
||||
root_id = node_id
|
||||
break
|
||||
elif fallback_root is None:
|
||||
fallback_root = node_id
|
||||
if not root_id:
|
||||
root_id = fallback_root
|
||||
if root_id:
|
||||
current_id = root_id
|
||||
visited = set()
|
||||
while current_id and current_id not in visited:
|
||||
visited.add(current_id)
|
||||
node = mapping.get(current_id, {})
|
||||
msg = node.get("message")
|
||||
if msg:
|
||||
role = msg.get("author", {}).get("role", "")
|
||||
content = msg.get("content", {})
|
||||
parts = content.get("parts", []) if isinstance(content, dict) else []
|
||||
text = " ".join(str(p) for p in parts if isinstance(p, str) and p).strip()
|
||||
if role == "user" and text:
|
||||
messages.append(("user", text))
|
||||
elif role == "assistant" and text:
|
||||
messages.append(("assistant", text))
|
||||
children = node.get("children", [])
|
||||
current_id = children[0] if children else None
|
||||
if len(messages) >= 2:
|
||||
return _messages_to_transcript(messages)
|
||||
return None
|
||||
|
||||
|
||||
def _try_slack_json(data) -> Optional[str]:
|
||||
"""
|
||||
Slack channel export: [{"type": "message", "user": "...", "text": "..."}]
|
||||
Optimized for 2-person DMs. In channels with 3+ people, alternating
|
||||
speakers are labeled user/assistant to preserve the exchange structure.
|
||||
"""
|
||||
if not isinstance(data, list):
|
||||
return None
|
||||
messages = []
|
||||
seen_users = {}
|
||||
last_role = None
|
||||
for item in data:
|
||||
if not isinstance(item, dict) or item.get("type") != "message":
|
||||
continue
|
||||
user_id = item.get("user", item.get("username", ""))
|
||||
text = item.get("text", "").strip()
|
||||
if not text or not user_id:
|
||||
continue
|
||||
if user_id not in seen_users:
|
||||
# Alternate roles so exchange chunking works with any number of speakers
|
||||
if not seen_users:
|
||||
seen_users[user_id] = "user"
|
||||
elif last_role == "user":
|
||||
seen_users[user_id] = "assistant"
|
||||
else:
|
||||
seen_users[user_id] = "user"
|
||||
last_role = seen_users[user_id]
|
||||
messages.append((seen_users[user_id], text))
|
||||
if len(messages) >= 2:
|
||||
return _messages_to_transcript(messages)
|
||||
return None
|
||||
|
||||
|
||||
def _extract_content(content) -> str:
|
||||
"""Pull text from content — handles str, list of blocks, or dict."""
|
||||
if isinstance(content, str):
|
||||
return content.strip()
|
||||
if isinstance(content, list):
|
||||
parts = []
|
||||
for item in content:
|
||||
if isinstance(item, str):
|
||||
parts.append(item)
|
||||
elif isinstance(item, dict) and item.get("type") == "text":
|
||||
parts.append(item.get("text", ""))
|
||||
return " ".join(parts).strip()
|
||||
if isinstance(content, dict):
|
||||
return content.get("text", "").strip()
|
||||
return ""
|
||||
|
||||
|
||||
def _messages_to_transcript(messages: list, spellcheck: bool = True) -> str:
|
||||
"""Convert [(role, text), ...] to transcript format with > markers."""
|
||||
if spellcheck:
|
||||
try:
|
||||
from mempalace.spellcheck import spellcheck_user_text
|
||||
|
||||
_fix = spellcheck_user_text
|
||||
except Exception:
|
||||
_fix = None
|
||||
else:
|
||||
_fix = None
|
||||
|
||||
lines = []
|
||||
i = 0
|
||||
while i < len(messages):
|
||||
role, text = messages[i]
|
||||
if role == "user":
|
||||
if _fix is not None:
|
||||
text = _fix(text)
|
||||
lines.append(f"> {text}")
|
||||
if i + 1 < len(messages) and messages[i + 1][0] == "assistant":
|
||||
lines.append(messages[i + 1][1])
|
||||
i += 2
|
||||
else:
|
||||
i += 1
|
||||
else:
|
||||
lines.append(text)
|
||||
i += 1
|
||||
lines.append("")
|
||||
return "\n".join(lines)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import sys
|
||||
|
||||
if len(sys.argv) < 2:
|
||||
print("Usage: python normalize.py <filepath>")
|
||||
sys.exit(1)
|
||||
filepath = sys.argv[1]
|
||||
result = normalize(filepath)
|
||||
quote_count = sum(1 for line in result.split("\n") if line.strip().startswith(">"))
|
||||
print(f"\nFile: {os.path.basename(filepath)}")
|
||||
print(f"Normalized: {len(result)} chars | {quote_count} user turns detected")
|
||||
print("\n--- Preview (first 20 lines) ---")
|
||||
print("\n".join(result.split("\n")[:20]))
|
||||
Reference in New Issue
Block a user