adjustments to rag engine

src/rag_engine.py

@@ -8,14 +8,23 @@ from chromadb.config import Settings
 from src import models
 from src import mcp_client
 
-try:
- from sentence_transformers import SentenceTransformer
-except ImportError:
- SentenceTransformer = None
+_SENTENCE_TRANSFORMERS = None
+_GOOGLE_GENAI = None
 
+def _get_sentence_transformers():
+    global _SENTENCE_TRANSFORMERS
+    if _SENTENCE_TRANSFORMERS is None:
+        from sentence_transformers import SentenceTransformer
+        _SENTENCE_TRANSFORMERS = SentenceTransformer
+    return _SENTENCE_TRANSFORMERS
+
+def _get_google_genai():
+    global _GOOGLE_GENAI
+    if _GOOGLE_GENAI is None:
         from google import genai
         from google.genai import types
-from src import ai_client
+        _GOOGLE_GENAI = (genai, types)
+    return _GOOGLE_GENAI
 
 class BaseEmbeddingProvider:
     def embed(self, texts: List[str]) -> List[List[float]]:
@@ -23,9 +32,10 @@ class BaseEmbeddingProvider:
 
 class LocalEmbeddingProvider(BaseEmbeddingProvider):
     def __init__(self, model_name: str = 'all-MiniLM-L6-v2'):
-  if SentenceTransformer is None:
+        ST = _get_sentence_transformers()
+        if ST is None:
             raise ImportError("sentence-transformers is not installed")
-  self.model = SentenceTransformer(model_name)
+        self.model = ST(model_name)
 
     def embed(self, texts: List[str]) -> List[List[float]]:
         embeddings = self.model.encode(texts)
@@ -36,12 +46,15 @@ class GeminiEmbeddingProvider(BaseEmbeddingProvider):
         self.model_name = model_name
 
     def embed(self, texts: List[str]) -> List[List[float]]:
+        google_module = _get_google_genai()
+        if google_module is None:
+            raise ImportError("google-genai is not installed")
+        genai_pkg, types = google_module
+        from src import ai_client
         ai_client._ensure_gemini_client()
         client = ai_client._gemini_client
         if not client:
             raise ValueError("Gemini client not initialized")
-  
-  # For text-embedding-004, we can embed a batch
         res = client.models.embed_content(
             model=self.model_name,
             contents=texts,
@@ -131,12 +144,10 @@ class RAGEngine:
             tree = parser.parse(content)
             chunks = []
 
-   # Capture classes and top-level functions
             for node in tree.root_node.children:
                 if node.type in ("function_definition", "class_definition"):
                     chunks.append(content[node.start_byte:node.end_byte])
 
-   # Fallback if no structural chunks found or if file is small
             if not chunks or len(content) < self.config.chunk_size:
                 return self._chunk_text(content)
             return chunks
@@ -157,7 +168,6 @@ class RAGEngine:
         except Exception:
             return
 
-  # Incremental check: see if we already have this file with the same mtime
         try:
             res = self.collection.get(where={"path": file_path}, limit=1, include=["metadatas"])
             if res and res["metadatas"] and res["metadatas"][0]:
@@ -172,7 +182,6 @@ class RAGEngine:
         except Exception:
             return
 
-  # Remove old entries for this file
         self.collection.delete(where={"path": file_path})
 
         if file_path.lower().endswith(".py"):