fix(llms/xai): forward tools, add XAIConfig, parse tool_calls (#5190)

mem0/llms/xai.py

@@ -1,14 +1,36 @@
+import json
 import os
-from typing import Dict, List, Optional
+from typing import Dict, List, Optional, Union
 
 from openai import OpenAI
 
 from mem0.configs.llms.base import BaseLlmConfig
+from mem0.configs.llms.xai import XAIConfig
 from mem0.llms.base import LLMBase
+from mem0.memory.utils import extract_json
 
 
 class XAILLM(LLMBase):
-    def __init__(self, config: Optional[BaseLlmConfig] = None):
+    def __init__(self, config: Optional[Union[BaseLlmConfig, XAIConfig, Dict]] = None):
+        # Convert to XAIConfig if needed
+        if config is None:
+            config = XAIConfig()
+        elif isinstance(config, dict):
+            config = XAIConfig(**config)
+        elif isinstance(config, BaseLlmConfig) and not isinstance(config, XAIConfig):
+            # Convert BaseLlmConfig to XAIConfig so xai_base_url is available
+            config = XAIConfig(
+                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,
+            )
+
         super().__init__(config)
 
         if not self.config.model:
@@ -18,35 +40,71 @@ class XAILLM(LLMBase):
         base_url = self.config.xai_base_url or os.getenv("XAI_API_BASE") or "https://api.x.ai/v1"
         self.client = OpenAI(api_key=api_key, base_url=base_url)
 
+    def _parse_response(self, response, tools):
+        """
+        Process the response based on whether tools are used or not.
+
+        Args:
+            response: The raw response from API.
+            tools: The list of tools provided in the request.
+
+        Returns:
+            str or dict: The processed response.
+        """
+        if tools:
+            processed_response = {
+                "content": response.choices[0].message.content,
+                "tool_calls": [],
+            }
+
+            if response.choices[0].message.tool_calls:
+                for tool_call in response.choices[0].message.tool_calls:
+                    processed_response["tool_calls"].append(
+                        {
+                            "name": tool_call.function.name,
+                            "arguments": json.loads(extract_json(tool_call.function.arguments)),
+                        }
+                    )
+
+            return processed_response
+        else:
+            return response.choices[0].message.content
+
     def generate_response(
         self,
         messages: List[Dict[str, str]],
         response_format=None,
         tools: Optional[List[Dict]] = None,
         tool_choice: str = "auto",
+        **kwargs,
     ):
         """
-        Generate a response based on the given messages using XAI.
+        Generate a response based on the given messages using X.AI (Grok).
 
         Args:
             messages (list): List of message dicts containing 'role' and 'content'.
-            response_format (str or object, optional): Format of the response. Defaults to "text".
+            response_format (str or object, optional): Format of the response. Defaults to None.
             tools (list, optional): List of tools that the model can call. Defaults to None.
             tool_choice (str, optional): Tool choice method. Defaults to "auto".
+            **kwargs: Additional X.AI-specific parameters.
 
         Returns:
-            str: The generated response.
+            str or dict: The generated response. A string when tools are not requested;
+            a dict ``{"content": ..., "tool_calls": [...]}`` when tools are requested.
         """
-        params = {
-            "model": self.config.model,
-            "messages": messages,
-            "temperature": self.config.temperature,
-            "max_tokens": self.config.max_tokens,
-            "top_p": self.config.top_p,
-        }
+        params = self._get_supported_params(messages=messages, **kwargs)
+        params.update(
+            {
+                "model": self.config.model,
+                "messages": messages,
+            }
+        )
 
         if response_format:
             params["response_format"] = response_format
+        if tools:
+            params["tools"] = tools
+            params["tool_choice"] = tool_choice
 
         response = self.client.chat.completions.create(**params)
-        return response.choices[0].message.content
+        return self._parse_response(response, tools)