Florian Hartmann
b83546d833
Architecture (Agent 1):
- hermes_memory/tier2/{schema,facts,entities,relations,timeline}.py
- hermes_memory/tier3/{backend,chroma_backend,embedder}.py
- hermes_memory/graph/nx_store.py
- hermes_memory/api/memory_api.py (unified API)
- hermes_memory/cron/{consolidate,embed_queue,graph_refresh,prune}.py
- hermes_memory/config.py + pyproject.toml
Integration Plan (Agent 3):
- INTEGRATION_PLAN.md: Memory Provider Plugin strategy
- Hermes Core needs minimal changes
- sync_turn() + prefetch() hooks
- Skills integration via nextlevel_search/remember
Auto-Extraction (Agent 2):
- ARCHITECTURE.md: Full extraction pipeline docs
- Chunking, Pre-Filter, LLM Prompts, Classification
- Entity-Linking, Temporal Reasoning, Deduplication
All files: Python syntax checked, ECC standards applied.
45 lines
1.4 KiB
Python
45 lines
1.4 KiB
Python
"""Embedding-Wrapper für lokale Modelle."""
|
|
|
|
import hashlib
|
|
import logging
|
|
from pathlib import Path
|
|
from typing import List
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class LocalEmbedder:
|
|
"""Wrapper um sentence-transformers mit Caching."""
|
|
|
|
def __init__(self, model_name: str = "all-MiniLM-L6-v2", cache_dir: Path = None):
|
|
self.model_name = model_name
|
|
self.cache_dir = cache_dir or Path.home() / ".cache" / "hermes_memory" / "embeddings"
|
|
self.cache_dir.mkdir(parents=True, exist_ok=True)
|
|
self._model = None
|
|
self._dim = 384
|
|
|
|
def _load_model(self):
|
|
if self._model is None:
|
|
try:
|
|
from sentence_transformers import SentenceTransformer
|
|
self._model = SentenceTransformer(self.model_name)
|
|
self._dim = self._model.get_sentence_embedding_dimension()
|
|
except ImportError:
|
|
logger.error("sentence-transformers nicht installiert.")
|
|
raise
|
|
return self._model
|
|
|
|
def _cache_key(self, text: str) -> str:
|
|
return hashlib.sha256(text.encode("utf-8")).hexdigest() + ".npy"
|
|
|
|
def embed(self, texts: List[str]) -> List[List[float]]:
|
|
model = self._load_model()
|
|
return model.encode(texts, convert_to_numpy=True).tolist()
|
|
|
|
def embed_query(self, text: str) -> List[float]:
|
|
return self.embed([text])[0]
|
|
|
|
@property
|
|
def dim(self) -> int:
|
|
return self._dim
|