Initial commit: core-api service extraction from portainer-core

src/models/embeddings_ollama.py

@@ -0,0 +1,136 @@
+"""
+Ollama-based embedding client for text vectorization
+
+Uses Ollama's embedding API instead of local sentence-transformers.
+This eliminates the need for PyTorch and heavy ML dependencies.
+"""
+import logging
+import httpx
+from typing import List, Optional
+from src.config import get_settings
+
+logger = logging.getLogger(__name__)
+settings = get_settings()
+
+
+class OllamaEmbeddingClient:
+    """Client for generating text embeddings using Ollama"""
+
+    def __init__(
+        self,
+        model_name: Optional[str] = None,
+        base_url: Optional[str] = None,
+        timeout: int = 30
+    ):
+        """
+        Initialize Ollama embedding client
+
+        Args:
+            model_name: Embedding model name (default: nomic-embed-text)
+            base_url: Ollama base URL (default from settings)
+            timeout: Request timeout in seconds
+        """
+        self.model_name = model_name or settings.embedding_model
+        self.base_url = (base_url or settings.ollama_base_url).rstrip("/")
+        self.timeout = timeout
+        self.dimension = settings.embedding_dimension
+
+        logger.info(f"Initializing OllamaEmbeddingClient with model: {self.model_name}")
+        logger.info(f"Ollama URL: {self.base_url}")
+
+    async def embed_text(self, text: str) -> List[float]:
+        """
+        Generate embedding for a single text using Ollama
+
+        Args:
+            text: Input text to embed
+
+        Returns:
+            List of floats representing the embedding vector
+        """
+        try:
+            async with httpx.AsyncClient(timeout=self.timeout) as client:
+                response = await client.post(
+                    f"{self.base_url}/api/embeddings",
+                    json={
+                        "model": self.model_name,
+                        "prompt": text
+                    }
+                )
+                response.raise_for_status()
+                result = response.json()
+                return result["embedding"]
+
+        except Exception as e:
+            logger.error(f"Error generating embedding via Ollama: {e}")
+            raise
+
+    async def embed_batch(self, texts: List[str]) -> List[List[float]]:
+        """
+        Generate embeddings for multiple texts
+
+        Args:
+            texts: List of input texts
+
+        Returns:
+            List of embedding vectors
+        """
+        embeddings = []
+        for text in texts:
+            embedding = await self.embed_text(text)
+            embeddings.append(embedding)
+        return embeddings
+
+    def get_dimension(self) -> int:
+        """
+        Get embedding dimension
+
+        Returns:
+            Embedding vector dimension
+        """
+        return self.dimension
+
+
+# Global instance
+_embedding_client: Optional[OllamaEmbeddingClient] = None
+
+
+def get_embedding_client() -> OllamaEmbeddingClient:
+    """
+    Get or create global Ollama embedding client instance
+
+    Returns:
+        OllamaEmbeddingClient instance
+    """
+    global _embedding_client
+    if _embedding_client is None:
+        _embedding_client = OllamaEmbeddingClient()
+    return _embedding_client
+
+
+async def embed_text_async(text: str) -> List[float]:
+    """
+    Async wrapper for embedding text
+
+    Args:
+        text: Input text
+
+    Returns:
+        Embedding vector
+    """
+    client = get_embedding_client()
+    return await client.embed_text(text)
+
+
+async def embed_batch_async(texts: List[str]) -> List[List[float]]:
+    """
+    Async wrapper for batch embedding
+
+    Args:
+        texts: List of input texts
+
+    Returns:
+        List of embedding vectors
+    """
+    client = get_embedding_client()
+    return await client.embed_batch(texts)