feat(rag): Implement indexing and retrieval logic with AppController integration

src/rag_engine.py

@@ -91,6 +91,72 @@ class RAGEngine:
    metadatas=metadatas
   )
 
+ def _chunk_text(self, content: str) -> List[str]:
+  """Character-based chunking with overlap."""
+  chunks = []
+  if not content:
+   return chunks
+  chunk_size = self.config.chunk_size
+  overlap = self.config.chunk_overlap
+  start = 0
+  while start < len(content):
+   end = start + chunk_size
+   chunks.append(content[start:end])
+   if end >= len(content):
+    break
+   start += (chunk_size - overlap)
+  return chunks
+
+ def _chunk_code(self, content: str, file_path: str) -> List[str]:
+  """AST-aware chunking for Python code."""
+  try:
+   from src.file_cache import ASTParser
+   parser = ASTParser("python")
+   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
+  except Exception:
+   return self._chunk_text(content)
+
+ def index_file(self, file_path: str):
+  """Reads, chunks, and indexes a file into the vector store."""
+  if not self.config.enabled or self.collection == "mock":
+   return
+  
+  full_path = os.path.join(self.base_dir, file_path)
+  if not os.path.exists(full_path):
+   return
+   
+  try:
+   with open(full_path, "r", encoding="utf-8", errors="ignore") as f:
+    content = f.read()
+  except Exception:
+   return
+
+  # Remove old entries for this file
+  self.collection.delete(where={"path": file_path})
+  
+  if file_path.lower().endswith(".py"):
+   chunks = self._chunk_code(content, file_path)
+  else:
+   chunks = self._chunk_text(content)
+   
+  if not chunks:
+   return
+
+  ids = [f"{file_path}_{i}" for i in range(len(chunks))]
+  metadatas = [{"path": file_path, "chunk": i} for i in range(len(chunks))]
+  self.add_documents(ids, chunks, metadatas)
+
  def search(self, query: str, top_k: int = 5) -> List[Dict[str, Any]]:
   if not self.config.enabled or self.collection == "mock":
    return []