mirror of
https://github.com/zhayujie/chatgpt-on-wechat.git
synced 2026-06-02 00:57:41 +08:00
3ffb563a44
Add embedding_provider config knob with native support for openai / dashscope / doubao / zhipu / linkai, plus an in-chat /memory status and /memory rebuild-index workflow for switching vendors safely.
48 lines
1.5 KiB
Python
48 lines
1.5 KiB
Python
"""
|
|
Embedding-related index utilities.
|
|
|
|
We don't keep a sidecar state file — the SQLite index is the source of truth
|
|
and config.json is the source of intent. The two functions below are the
|
|
only things needing on-disk awareness:
|
|
|
|
detect_index_dim : read the dim of stored vectors (display-only)
|
|
cleanup_legacy_state_file: remove old embedding_state.json from earlier
|
|
versions; safe no-op when absent.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
import json
|
|
import os
|
|
from pathlib import Path
|
|
from typing import Optional, Union
|
|
|
|
PathLike = Union[str, os.PathLike]
|
|
|
|
|
|
def detect_index_dim(storage) -> Optional[int]:
|
|
"""Return the dim of the first stored embedding, or None if the index
|
|
has no embeddings. Used by /memory status."""
|
|
try:
|
|
row = storage.conn.execute(
|
|
"SELECT embedding FROM chunks WHERE embedding IS NOT NULL LIMIT 1"
|
|
).fetchone()
|
|
except Exception:
|
|
return None
|
|
if not row or not row["embedding"]:
|
|
return None
|
|
try:
|
|
emb = json.loads(row["embedding"])
|
|
return len(emb) if isinstance(emb, list) else None
|
|
except (json.JSONDecodeError, TypeError):
|
|
return None
|
|
|
|
|
|
def cleanup_legacy_state_file(db_path: PathLike) -> None:
|
|
"""Remove old embedding_state.json files from earlier versions.
|
|
Safe to call repeatedly; no-op if the file is absent."""
|
|
legacy = Path(db_path).parent / "embedding_state.json"
|
|
try:
|
|
legacy.unlink(missing_ok=True)
|
|
except Exception:
|
|
pass
|