refactor: 🔨 Mostly working Ollama migration, few tweaks left

src/embedding.py

@@ -10,7 +10,7 @@ API_VERSION = CFG["api"]["api_version"]
 
 class LocalLMEmbeddings(Embeddings):
     def __init__(self, model: str, base_url: str = API_BASE, batch_size: int = 32):
-        self.url = f"{base_url}/{API_VERSION}embeddings"
+        self.url = f"{base_url}/api/embed"
         self.model = model
         self.batch_size = batch_size
 
@@ -22,10 +22,11 @@ class LocalLMEmbeddings(Embeddings):
             response = requests.post(
                 self.url, json=payload, timeout=120
             )  # Longer timeout for batches
+            # print(response)
             response.raise_for_status()
             data = response.json()
             # print(data)
-            return [item["embedding"] for item in data["data"]]
+            return data["embeddings"]
         except Exception as e:
             print(f"❌ Batch request failed: {e}")
             # Returning empty lists to maintain index integrity if needed,