Update max_token and formatting (#2273)

docs/components/llms/models/aws_bedrock.mdx

@@ -24,7 +24,7 @@ config = {
         "config": {
             "model": "arn:aws:bedrock:us-east-1:123456789012:model/your-model-name",
             "temperature": 0.2,
-            "max_tokens": 1500,
+            "max_tokens": 2000,
         }
     }
 }

docs/components/llms/models/deepseek.mdx

@@ -19,7 +19,7 @@ config = {
         "config": {
             "model": "deepseek-chat",  # default model
             "temperature": 0.2,
-            "max_tokens": 1500,
+            "max_tokens": 2000,
             "top_p": 1.0
         }
     }

docs/components/llms/models/gemini.mdx

@@ -19,7 +19,7 @@ config = {
         "config": {
             "model": "gemini-1.5-flash-latest",
             "temperature": 0.2,
-            "max_tokens": 1500,
+            "max_tokens": 2000,
         }
     }
 }

docs/components/llms/models/google_AI.mdx

@@ -19,7 +19,7 @@ config = {
         "config": {
             "model": "gemini/gemini-pro",
             "temperature": 0.2,
-            "max_tokens": 1500,
+            "max_tokens": 2000,
         }
     }
 }

docs/components/llms/models/groq.mdx

@@ -17,7 +17,7 @@ config = {
         "config": {
             "model": "mixtral-8x7b-32768",
             "temperature": 0.1,
-            "max_tokens": 1000,
+            "max_tokens": 2000,
         }
     }
 }

docs/components/llms/models/litellm.mdx

@@ -14,7 +14,7 @@ config = {
         "config": {
             "model": "gpt-4o-mini",
             "temperature": 0.2,
-            "max_tokens": 1500,
+            "max_tokens": 2000,
         }
     }
 }

docs/components/llms/models/openai.mdx

@@ -18,7 +18,7 @@ config = {
         "config": {
             "model": "gpt-4o",
             "temperature": 0.2,
-            "max_tokens": 1500,
+            "max_tokens": 2000,
         }
     }
 }

docs/components/llms/models/together.mdx

@@ -15,7 +15,7 @@ config = {
         "config": {
             "model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
             "temperature": 0.2,
-            "max_tokens": 1500,
+            "max_tokens": 2000,
         }
     }
 }

docs/components/llms/models/xAI.mdx

@@ -21,7 +21,7 @@ config = {
         "config": {
             "model": "grok-2-latest",
             "temperature": 0.1,
-            "max_tokens": 1000,
+            "max_tokens": 2000,
         }
     }
 }

docs/examples/mem0-with-ollama.mdx

@@ -37,7 +37,7 @@ config = {
         "config": {
             "model": "llama3.1:latest",
             "temperature": 0,
-            "max_tokens": 8000,
+            "max_tokens": 2000,
             "ollama_base_url": "http://localhost:11434",  # Ensure this URL is correct
         },
     },

docs/features/custom-prompts.mdx

@@ -53,7 +53,7 @@ config = {
         "config": {
             "model": "gpt-4o",
             "temperature": 0.2,
-            "max_tokens": 1500,
+            "max_tokens": 2000,
         }
     },
     "custom_prompt": custom_prompt,

docs/integrations/llama-index.mdx

@@ -80,7 +80,7 @@ config = {
         "config": {
             "model": "gpt-4o",
             "temperature": 0.2,
-            "max_tokens": 1500,
+            "max_tokens": 2000,
         },
     },
     "embedder": {

docs/open-source/graph_memory/overview.mdx

@@ -81,7 +81,7 @@ config = {
         "config": {
             "model": "gpt-4o",
             "temperature": 0.2,
-            "max_tokens": 1500,
+            "max_tokens": 2000,
         }
     },
     "graph_store": {

mem0/configs/llms/base.py

@@ -16,7 +16,7 @@ class BaseLlmConfig(ABC):
         model: Optional[str] = None,
         temperature: float = 0.1,
         api_key: Optional[str] = None,
-        max_tokens: int = 3000,
+        max_tokens: int = 2000,
         top_p: float = 0.1,
         top_k: int = 1,
         # Openrouter specific
@@ -48,7 +48,7 @@ class BaseLlmConfig(ABC):
         :type temperature: float, optional
         :param api_key: OpenAI API key to be use, defaults to None
         :type api_key: Optional[str], optional
-        :param max_tokens: Controls how many tokens are generated, defaults to 3000
+        :param max_tokens: Controls how many tokens are generated, defaults to 2000
         :type max_tokens: int, optional
         :param top_p: Controls the diversity of words. Higher values (closer to 1) make word selection more diverse,
         defaults to 1

mem0/embeddings/azure_openai.py

@@ -26,7 +26,7 @@ class AzureOpenAIEmbedding(EmbeddingBase):
             default_headers=default_headers,
         )
 
-    def embed(self, text, memory_action:Optional[Literal["add", "search", "update"]] = None):
+    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
         """
         Get the embedding for the given text using OpenAI.
 

mem0/embeddings/base.py

@@ -18,7 +18,7 @@ class EmbeddingBase(ABC):
             self.config = config
 
     @abstractmethod
-    def embed(self, text, memory_action:Optional[Literal["add", "search", "update"]]):
+    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]]):
         """
         Get the embedding for the given text.
 

mem0/embeddings/gemini.py

@@ -18,7 +18,7 @@ class GoogleGenAIEmbedding(EmbeddingBase):
 
         genai.configure(api_key=api_key)
 
-    def embed(self, text, memory_action:Optional[Literal["add", "search", "update"]] = None):
+    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
         """
         Get the embedding for the given text using Google Generative AI.
         Args:

mem0/embeddings/huggingface.py

@@ -16,7 +16,7 @@ class HuggingFaceEmbedding(EmbeddingBase):
 
         self.config.embedding_dims = self.config.embedding_dims or self.model.get_sentence_embedding_dimension()
 
-    def embed(self, text, memory_action:Optional[Literal["add", "search", "update"]] = None):
+    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
         """
         Get the embedding for the given text using Hugging Face.
 

mem0/embeddings/ollama.py

@@ -39,7 +39,7 @@ class OllamaEmbedding(EmbeddingBase):
         if not any(model.get("name") == self.config.model for model in local_models):
             self.client.pull(self.config.model)
 
-    def embed(self, text, memory_action:Optional[Literal["add", "search", "update"]] = None):
+    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
         """
         Get the embedding for the given text using Ollama.
 

mem0/embeddings/openai.py

@@ -18,7 +18,7 @@ class OpenAIEmbedding(EmbeddingBase):
         base_url = self.config.openai_base_url or os.getenv("OPENAI_API_BASE")
         self.client = OpenAI(api_key=api_key, base_url=base_url)
 
-    def embed(self, text, memory_action:Optional[Literal["add", "search", "update"]] = None):
+    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
         """
         Get the embedding for the given text using OpenAI.
 

mem0/embeddings/together.py

@@ -17,7 +17,7 @@ class TogetherEmbedding(EmbeddingBase):
         self.config.embedding_dims = self.config.embedding_dims or 768
         self.client = Together(api_key=api_key)
 
-    def embed(self, text, memory_action:Optional[Literal["add", "search", "update"]] = None):
+    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
         """
         Get the embedding for the given text using OpenAI.
 

mem0/embeddings/vertexai.py

@@ -13,13 +13,13 @@ class VertexAIEmbedding(EmbeddingBase):
 
         self.config.model = self.config.model or "text-embedding-004"
         self.config.embedding_dims = self.config.embedding_dims or 256
-        
+
         self.embedding_types = {
             "add": self.config.memory_add_embedding_type or "RETRIEVAL_DOCUMENT",
             "update": self.config.memory_update_embedding_type or "RETRIEVAL_DOCUMENT",
-            "search": self.config.memory_search_embedding_type or "RETRIEVAL_QUERY"
+            "search": self.config.memory_search_embedding_type or "RETRIEVAL_QUERY",
         }
-        
+
         credentials_path = self.config.vertex_credentials_json
 
         if credentials_path:
@@ -31,7 +31,7 @@ class VertexAIEmbedding(EmbeddingBase):
 
         self.model = TextEmbeddingModel.from_pretrained(self.config.model)
 
-    def embed(self, text, memory_action:Optional[Literal["add", "search", "update"]] = None):
+    def embed(self, text, memory_action: Optional[Literal["add", "search", "update"]] = None):
         """
         Get the embedding for the given text using Vertex AI.
 
@@ -45,9 +45,9 @@ class VertexAIEmbedding(EmbeddingBase):
         if memory_action is not None:
             if memory_action not in self.embedding_types:
                 raise ValueError(f"Invalid memory action: {memory_action}")
-            
+
             embedding_type = self.embedding_types[memory_action]
-            
+
         text_input = TextEmbeddingInput(text=text, task_type=embedding_type)
         embeddings = self.model.get_embeddings(texts=[text_input], output_dimensionality=self.config.embedding_dims)
 

mem0/llms/groq.py

@@ -84,4 +84,4 @@ class GroqLLM(LLMBase):
             params["tool_choice"] = tool_choice
 
         response = self.client.chat.completions.create(**params)
-        return self._parse_response(response, tools)
+        return self._parse_response(response, tools)

mem0/llms/openai.py

@@ -63,7 +63,6 @@ class OpenAILLM(LLMBase):
         response_format=None,
         tools: Optional[List[Dict]] = None,
         tool_choice: str = "auto",
-        max_tokens: int = 100,
     ):
         """
         Generate a response based on the given messages using OpenAI.
@@ -81,7 +80,7 @@ class OpenAILLM(LLMBase):
             "model": self.config.model,
             "messages": messages,
             "temperature": self.config.temperature,
-            "max_tokens": max_tokens,
+            "max_tokens": self.config.max_tokens,
             "top_p": self.config.top_p,
         }
 

tests/llms/test_azure_openai.py

@@ -128,4 +128,4 @@ def test_generate_with_http_proxies(default_headers):
             api_version=None,
             default_headers=default_headers,
         )
-        mock_http_client.assert_called_once_with(proxies="http://testproxy.mem0.net:8000")
+        mock_http_client.assert_called_once_with(proxies="http://testproxy.mem0.net:8000")