aljaz/enclava
1
0
Fork 0
mirror of https://github.com/aljazceru/enclava.git synced 2025-12-17 15:34:36 +01:00
Code Issues Packages Projects Releases Wiki Activity

adding ollama embeddings and expanding to metadata search

Browse Source
This commit is contained in:
Aljaz Ceru
2025-10-23 06:58:34 +02:00
parent 5d964dfd54
commit 8b6d241921
11 changed files with 289 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
backend/app/services/embedding_service.py
View File

@@ -19,8 +19,8 @@ class EmbeddingService:
"""Service for generating text embeddings using a local transformer model"""
def __init__(self, model_name: Optional[str] = None):
self.model_name = model_name or getattr(settings, "RAG_EMBEDDING_MODEL", "BAAI/bge-small-en")
self.dimension = 384 # bge-small produces 384-d vectors
self.model_name = model_name or getattr(settings, "RAG_EMBEDDING_MODEL", "BAAI/bge-m3")
self.dimension = 1024 # bge-m3 produces 1024-d vectors
self.initialized = False
self.local_model = None
self.backend = "uninitialized"
@@ -127,7 +127,7 @@ class EmbeddingService:
def _generate_fallback_embedding(self, text: str) -> List[float]:
"""Generate a single fallback embedding"""
dimension = self.dimension or 384
dimension = self.dimension or 1024
# Use hash for reproducible random embeddings
np.random.seed(hash(text) % 2**32)
return np.random.random(dimension).tolist()