Merge branch 'main' into fix/vertexai-py-batch-size

gemini-embedding-* accepts one input text per predict request, but
embed_batch() chunked at 250 for every model while defaulting to
gemini-embedding-001. Derive the chunk size from the model instead.

mem0/configs/embeddings/base.py

@@ -20,8 +20,6 @@ class BaseEmbedderConfig(ABC):
         ollama_base_url: Optional[str] = None,
         # Openai specific
         openai_base_url: Optional[str] = None,
-        # Together specific
-        together_base_url: Optional[str] = None,
         # Huggingface specific
         model_kwargs: Optional[dict] = None,
         huggingface_base_url: Optional[str] = None,
@@ -60,8 +58,6 @@ class BaseEmbedderConfig(ABC):
         :type huggingface_base_url: Optional[str], optional
         :param openai_base_url: Openai base URL to be use, defaults to "https://api.openai.com/v1"
         :type openai_base_url: Optional[str], optional
-        :param together_base_url: Together base URL to be use, defaults to None
-        :type together_base_url: Optional[str], optional
         :param azure_kwargs: key-value arguments for the AzureOpenAI embedding model, defaults a dict inside init
         :type azure_kwargs: Optional[Dict[str, Any]], defaults a dict inside init
         :param http_client_proxies: The proxy server settings used to create self.http_client, defaults to None
@@ -81,7 +77,6 @@ class BaseEmbedderConfig(ABC):
         self.model = model
         self.api_key = api_key
         self.openai_base_url = openai_base_url
-        self.together_base_url = together_base_url
         self.embedding_dims = embedding_dims
 
         # AzureOpenAI specific

mem0/configs/llms/together.py

@@ -1,56 +0,0 @@
-from typing import Optional
-
-from mem0.configs.llms.base import BaseLlmConfig
-
-
-class TogetherConfig(BaseLlmConfig):
-    """
-    Configuration class for Together-specific parameters.
-    Inherits from BaseLlmConfig and adds Together-specific settings.
-    """
-
-    def __init__(
-        self,
-        # Base parameters
-        model: Optional[str] = None,
-        temperature: float = 0.1,
-        api_key: Optional[str] = None,
-        max_tokens: int = 2000,
-        top_p: float = 0.1,
-        top_k: int = 1,
-        enable_vision: bool = False,
-        vision_details: Optional[str] = "auto",
-        http_client_proxies: Optional[dict] = None,
-        # Together-specific parameters
-        together_base_url: Optional[str] = None,
-    ):
-        """
-        Initialize Together configuration.
-
-        Args:
-            model: Together model to use, defaults to None
-            temperature: Controls randomness, defaults to 0.1
-            api_key: Together API key, defaults to None
-            max_tokens: Maximum tokens to generate, defaults to 2000
-            top_p: Nucleus sampling parameter, defaults to 0.1
-            top_k: Top-k sampling parameter, defaults to 1
-            enable_vision: Enable vision capabilities, defaults to False
-            vision_details: Vision detail level, defaults to "auto"
-            http_client_proxies: HTTP client proxy settings, defaults to None
-            together_base_url: Together API base URL, defaults to None
-        """
-        # Initialize base parameters
-        super().__init__(
-            model=model,
-            temperature=temperature,
-            api_key=api_key,
-            max_tokens=max_tokens,
-            top_p=top_p,
-            top_k=top_k,
-            enable_vision=enable_vision,
-            vision_details=vision_details,
-            http_client_proxies=http_client_proxies,
-        )
-
-        # Together-specific parameters
-        self.together_base_url = together_base_url

mem0/embeddings/together.py

@@ -13,9 +13,8 @@ class TogetherEmbedding(EmbeddingBase):
 
         self.config.model = self.config.model or "intfloat/multilingual-e5-large-instruct"
         api_key = self.config.api_key or os.getenv("TOGETHER_API_KEY")
-        base_url = self.config.together_base_url or os.getenv("TOGETHER_API_BASE") or "https://api.together.ai/v1"
         self.config.embedding_dims = self.config.embedding_dims or 1024
-        self.client = Together(api_key=api_key, base_url=base_url)
+        self.client = Together(api_key=api_key)
 
     def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
         """

mem0/embeddings/vertexai.py

@@ -8,6 +8,14 @@ from mem0.embeddings.base import EmbeddingBase
 from mem0.utils.gcp_auth import GCPAuthenticator
 
 
+def _max_instances_per_request(model: str) -> int:
+    # Vertex AI's per-request input cap depends on the model family: gemini-embedding-*
+    # accepts exactly one input text per predict() call, while text-embedding-004/005 and
+    # text-multilingual-embedding-002 accept up to 250.
+    # https://docs.cloud.google.com/vertex-ai/docs/samples/aiplatform-sdk-embedding
+    return 1 if model.startswith("gemini-embedding") else 250
+
+
 class VertexAIEmbedding(EmbeddingBase):
     def __init__(self, config: Optional[BaseEmbedderConfig] = None):
         super().__init__(config)
@@ -72,8 +80,9 @@ class VertexAIEmbedding(EmbeddingBase):
                 raise ValueError(f"Invalid memory action: {memory_action}")
             embedding_type = self.embedding_types[memory_action]
         all_embeddings = []
-        for i in range(0, len(texts), 250):
-            chunk = texts[i : i + 250]
+        chunk_size = _max_instances_per_request(self.config.model)
+        for i in range(0, len(texts), chunk_size):
+            chunk = texts[i : i + chunk_size]
             inputs = [TextEmbeddingInput(text=t, task_type=embedding_type) for t in chunk]
             results = self.model.get_embeddings(texts=inputs, output_dimensionality=self.config.embedding_dims)
             all_embeddings.extend(r.values for r in results)

mem0/llms/together.py

@@ -1,6 +1,6 @@
 import json
 import os
-from typing import Dict, List, Optional, Union
+from typing import Dict, List, Optional
 
 try:
     from together import Together
@@ -8,40 +8,19 @@ except ImportError:
     raise ImportError("The 'together' library is required. Please install it using 'pip install together'.")
 
 from mem0.configs.llms.base import BaseLlmConfig
-from mem0.configs.llms.together import TogetherConfig
 from mem0.llms.base import LLMBase
 from mem0.memory.utils import extract_json
 
 
 class TogetherLLM(LLMBase):
-    def __init__(self, config: Optional[Union[BaseLlmConfig, TogetherConfig, Dict]] = None):
-        # Convert to TogetherConfig if needed
-        if config is None:
-            config = TogetherConfig()
-        elif isinstance(config, dict):
-            config = TogetherConfig(**config)
-        elif isinstance(config, BaseLlmConfig) and not isinstance(config, TogetherConfig):
-            # Convert BaseLlmConfig to TogetherConfig
-            config = TogetherConfig(
-                model=config.model,
-                temperature=config.temperature,
-                api_key=config.api_key,
-                max_tokens=config.max_tokens,
-                top_p=config.top_p,
-                top_k=config.top_k,
-                enable_vision=config.enable_vision,
-                vision_details=config.vision_details,
-                http_client_proxies=config.http_client_proxies,
-            )
-
+    def __init__(self, config: Optional[BaseLlmConfig] = None):
         super().__init__(config)
 
         if not self.config.model:
             self.config.model = "MiniMaxAI/MiniMax-M3"
 
         api_key = self.config.api_key or os.getenv("TOGETHER_API_KEY")
-        base_url = self.config.together_base_url or os.getenv("TOGETHER_API_BASE") or "https://api.together.ai/v1"
-        self.client = Together(api_key=api_key, base_url=base_url)
+        self.client = Together(api_key=api_key)
 
     def _parse_response(self, response, tools):
         """

mem0/utils/factory.py

@@ -13,7 +13,6 @@ from mem0.configs.llms.lmstudio import LMStudioConfig
 from mem0.configs.llms.minimax import MinimaxConfig
 from mem0.configs.llms.ollama import OllamaConfig
 from mem0.configs.llms.openai import OpenAIConfig
-from mem0.configs.llms.together import TogetherConfig
 from mem0.configs.llms.vllm import VllmConfig
 from mem0.configs.llms.xai import XAIConfig
 from mem0.configs.rerankers.base import BaseRerankerConfig
@@ -44,7 +43,7 @@ class LlmFactory:
         "ollama": ("mem0.llms.ollama.OllamaLLM", OllamaConfig),
         "openai": ("mem0.llms.openai.OpenAILLM", OpenAIConfig),
         "groq": ("mem0.llms.groq.GroqLLM", BaseLlmConfig),
-        "together": ("mem0.llms.together.TogetherLLM", TogetherConfig),
+        "together": ("mem0.llms.together.TogetherLLM", BaseLlmConfig),
         "aws_bedrock": ("mem0.llms.aws_bedrock.AWSBedrockLLM", AWSBedrockConfig),
         "litellm": ("mem0.llms.litellm.LiteLLM", BaseLlmConfig),
         "azure_openai": ("mem0.llms.azure_openai.AzureOpenAILLM", AzureOpenAIConfig),

tests/embeddings/test_together_embeddings.py

@@ -85,29 +85,3 @@ def test_explicit_config_overrides_defaults(mock_together_client):
     mock_together_client.embeddings.create.return_value = Mock(data=[Mock(embedding=[0.0] * 768)])
     embedder.embed("hello")
     mock_together_client.embeddings.create.assert_called_once_with(model="BAAI/bge-base-en-v1.5", input="hello")
-
-
-def test_together_embedding_base_url(monkeypatch):
-    # case1: default config uses Together's official base url
-    monkeypatch.delenv("TOGETHER_API_BASE", raising=False)
-    config = BaseEmbedderConfig(model=DEFAULT_MODEL, embedding_dims=DEFAULT_EMBEDDING_DIMS, api_key="api_key")
-    embedder = TogetherEmbedding(config)
-    assert str(embedder.client.base_url) == "https://api.together.ai/v1/"
-
-    # case2: with env variable TOGETHER_API_BASE
-    provider_base_url = "https://api.provider.com/v1/"
-    monkeypatch.setenv("TOGETHER_API_BASE", provider_base_url)
-    config = BaseEmbedderConfig(model=DEFAULT_MODEL, embedding_dims=DEFAULT_EMBEDDING_DIMS, api_key="api_key")
-    embedder = TogetherEmbedding(config)
-    assert str(embedder.client.base_url) == provider_base_url
-
-    # case3: with config.together_base_url (explicit config beats env var)
-    config_base_url = "https://api.config.com/v1/"
-    config = BaseEmbedderConfig(
-        model=DEFAULT_MODEL,
-        embedding_dims=DEFAULT_EMBEDDING_DIMS,
-        api_key="api_key",
-        together_base_url=config_base_url,
-    )
-    embedder = TogetherEmbedding(config)
-    assert str(embedder.client.base_url) == config_base_url

tests/embeddings/test_vertexai_embeddings.py

@@ -163,7 +163,9 @@ def test_invalid_memory_action(mock_text_embedding_model, mock_config):
 
 @patch("mem0.embeddings.vertexai.TextEmbeddingModel")
 def test_embed_batch_single_call(mock_text_embedding_model, mock_os_environ, mock_config):
-    mock_config.return_value.model = "gemini-embedding-001"
+    # text-embedding-005 accepts up to 250 inputs per request, so 2 texts fit in one call.
+    # (gemini-embedding-* only accepts 1 input per request; see test_embed_batch_default_model_sends_one_text_per_call.)
+    mock_config.return_value.model = "text-embedding-005"
     mock_config.return_value.embedding_dims = 256
 
     config = mock_config()
@@ -198,7 +200,9 @@ def test_embed_batch_empty_list(mock_text_embedding_model, mock_os_environ, mock
 
 @patch("mem0.embeddings.vertexai.TextEmbeddingModel")
 def test_embed_batch_count_mismatch_raises(mock_text_embedding_model, mock_os_environ, mock_config):
-    mock_config.return_value.model = "gemini-embedding-001"
+    # Use a 250-cap model so both texts land in a single chunk/call, keeping the mismatch
+    # (1 embedding returned for that one call) triggered by that single call.
+    mock_config.return_value.model = "text-embedding-005"
     mock_config.return_value.embedding_dims = 256
 
     config = mock_config()
@@ -261,8 +265,8 @@ def test_embed_batch_invalid_memory_action_raises(mock_text_embedding_model, moc
 
 @patch("mem0.embeddings.vertexai.TextEmbeddingModel")
 def test_embed_batch_chunking_triggers_two_api_calls(mock_text_embedding_model, mock_os_environ, mock_config):
-    """300 texts must produce exactly 2 get_embeddings calls (chunks of 250 and 50)."""
-    mock_config.return_value.model = "gemini-embedding-001"
+    """text-embedding-005 accepts up to 250 inputs/request: 300 texts -> 2 calls (chunks of 250 and 50)."""
+    mock_config.return_value.model = "text-embedding-005"
     mock_config.return_value.embedding_dims = 256
 
     config = mock_config()
@@ -278,3 +282,25 @@ def test_embed_batch_chunking_triggers_two_api_calls(mock_text_embedding_model,
 
     assert mock_text_embedding_model.from_pretrained.return_value.get_embeddings.call_count == 2
     assert len(result) == 300
+
+
+@patch("mem0.embeddings.vertexai.TextEmbeddingModel")
+def test_embed_batch_default_model_sends_one_text_per_call(mock_text_embedding_model, mock_os_environ, mock_config):
+    """gemini-embedding-001 (default) accepts 1 input/request: 300 texts -> 300 calls of 1 text each."""
+    mock_config.return_value.model = "gemini-embedding-001"
+    mock_config.return_value.embedding_dims = 256
+
+    config = mock_config()
+    embedder = VertexAIEmbedding(config)
+
+    def make_single_response(texts, output_dimensionality):
+        assert len(texts) == 1
+        return [Mock(values=[0.1, 0.2]) for _ in texts]
+
+    mock_text_embedding_model.from_pretrained.return_value.get_embeddings.side_effect = make_single_response
+
+    texts = [f"text {i}" for i in range(300)]
+    result = embedder.embed_batch(texts)
+
+    assert mock_text_embedding_model.from_pretrained.return_value.get_embeddings.call_count == 300
+    assert len(result) == 300

tests/llms/test_together.py

@@ -3,7 +3,6 @@ from unittest.mock import Mock, patch
 import pytest
 
 from mem0.configs.llms.base import BaseLlmConfig
-from mem0.configs.llms.together import TogetherConfig
 from mem0.llms.together import TogetherLLM
 
 
@@ -15,38 +14,6 @@ def mock_together_client():
         yield mock_client
 
 
-def test_together_llm_base_url(monkeypatch):
-    # case1: default config uses Together's official base url
-    monkeypatch.delenv("TOGETHER_API_BASE", raising=False)
-    config = BaseLlmConfig(
-        model="mistralai/Mixtral-8x7B-Instruct-v0.1", temperature=0.7, max_tokens=100, top_p=1.0, api_key="api_key"
-    )
-    llm = TogetherLLM(config)
-    assert str(llm.client.base_url) == "https://api.together.ai/v1/"
-
-    # case2: with env variable TOGETHER_API_BASE
-    provider_base_url = "https://api.provider.com/v1/"
-    monkeypatch.setenv("TOGETHER_API_BASE", provider_base_url)
-    config = TogetherConfig(
-        model="mistralai/Mixtral-8x7B-Instruct-v0.1", temperature=0.7, max_tokens=100, top_p=1.0, api_key="api_key"
-    )
-    llm = TogetherLLM(config)
-    assert str(llm.client.base_url) == provider_base_url
-
-    # case3: with config.together_base_url (explicit config beats env var)
-    config_base_url = "https://api.config.com/v1/"
-    config = TogetherConfig(
-        model="mistralai/Mixtral-8x7B-Instruct-v0.1",
-        temperature=0.7,
-        max_tokens=100,
-        top_p=1.0,
-        api_key="api_key",
-        together_base_url=config_base_url,
-    )
-    llm = TogetherLLM(config)
-    assert str(llm.client.base_url) == config_base_url
-
-
 def test_generate_response_without_tools(mock_together_client):
     config = BaseLlmConfig(model="mistralai/Mixtral-8x7B-Instruct-v0.1", temperature=0.7, max_tokens=100, top_p=1.0)
     llm = TogetherLLM(config)