Method call

api/google_embedder_client.py:211–253

Call Google AI embedding API. Args: api_kwargs: API parameters model_type: Should be ModelType.EMBEDDER Returns: Google AI embedding response

(self, api_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED)

        max_time=5,
    )
    def call(self, api_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED):
        """Call Google AI embedding API.
        
        Args:
            api_kwargs: API parameters
            model_type: Should be ModelType.EMBEDDER
            
        Returns:
            Google AI embedding response
        """
        if model_type != ModelType.EMBEDDER:
            raise ValueError(f"GoogleEmbedderClient only supports EMBEDDER model type")
            
        safe_log_kwargs = {k: v for k, v in api_kwargs.items() if k not in {"content", "contents"}}
        if "content" in api_kwargs:
            safe_log_kwargs["content_chars"] = len(str(api_kwargs.get("content", "")))
        if "contents" in api_kwargs:
            try:
                contents = api_kwargs.get("contents")
                safe_log_kwargs["contents_count"] = len(contents) if hasattr(contents, "__len__") else None
            except Exception:
                safe_log_kwargs["contents_count"] = None
        log.info("Google AI Embeddings call kwargs (sanitized): %s", safe_log_kwargs)
        
        try:
            # Use embed_content for single text or batch embedding
            if "content" in api_kwargs:
                # Single embedding
                response = genai.embed_content(**api_kwargs)
            elif "contents" in api_kwargs:
                # Batch embedding - Google AI supports batch natively
                # Copy to avoid mutating the original dict (needed for retries)
                kwargs = api_kwargs.copy()
                contents = kwargs.pop("contents")
                response = genai.embed_content(content=contents, **kwargs)
            else:
                raise ValueError("Either 'content' or 'contents' must be provided")
                
            return response
            
        except Exception as e:
            log.error(f"Error calling Google AI Embeddings API: {e}")
            raise

    async def acall(self, api_kwargs: Dict = {}, model_type: ModelType = ModelType.UNDEFINED):
        """Async call to Google AI embedding API.