Update app/backend/chromadb_utils.py

app/backend/chromadb_utils.py

@@ -1,49 +1,8 @@
 import chromadb
 from chromadb.utils import embedding_functions
 from .text_processing import text_chunking
-import torch
-from transformers import AutoTokenizer, AutoModel
 
 
-class SimpleEmbeddingFunction:
-    def __init__(self, model_path):
-        self.tokenizer = AutoTokenizer.from_pretrained(model_path, local_files_only=True)
-        self.model = AutoModel.from_pretrained(model_path, local_files_only=True)
-        self.model.eval()
-    
-    def __call__(self, texts):
-        if isinstance(texts, str):
-            texts = [texts]
-        
-        inputs = self.tokenizer(
-            texts, 
-            padding=True, 
-            truncation=True, 
-            return_tensors='pt',
-            max_length=384
-        )
-        
-        with torch.no_grad():
-            outputs = self.model(**inputs)
-            embeddings = outputs.last_hidden_state.mean(dim=1)
-            embeddings = torch.nn.functional.normalize(embeddings, p=2, dim=1)
-        
-        return embeddings.numpy().tolist()
-
-
-def initialize_chromadb(model_name, model_path):
-    import chromadb
-    
-    if not os.path.exists(model_path):
-        raise Exception(f"Local model not found at {model_path}")
-    
-    embedding_func = SimpleEmbeddingFunction(model_path)
-    client = chromadb.Client()
-    
-    return client, embedding_func
-
-
-"""
 def initialize_chromadb(EMBEDDING_MODEL, local_model_path=None):
     """
     Initialize ChromaDB client and embedding function, using a local model path if provided.
@@ -60,8 +19,7 @@ def initialize_chromadb(EMBEDDING_MODEL, local_model_path=None):
         )
 
     return client, embedding_func
-"""
-
+    
 
 def initialize_collection(client, embedding_func, collection_name):
     """