vector-vault 7.3.1__tar.gz → 7.3.2__tar.gz

{vector_vault-7.3.1 → vector_vault-7.3.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vector_vault
-Version: 7.3.1
+Version: 7.3.2
 Summary: Quickly create RAG apps, Agents, and Unleash the full power of AI with Vector Vault
 Home-page: https://github.com/John-Rood/VectorVault
 Author: VectorVault.io

{vector_vault-7.3.1 → vector_vault-7.3.2}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="vector_vault",
-    version="7.3.1",
+    version="7.3.2",
     packages=find_packages(),
     author="VectorVault.io",
     author_email="john@johnrood.com",

{vector_vault-7.3.1 → vector_vault-7.3.2}/vector_vault.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: vector-vault
-Version: 7.3.1
+Version: 7.3.2
 Summary: Quickly create RAG apps, Agents, and Unleash the full power of AI with Vector Vault
 Home-page: https://github.com/John-Rood/VectorVault
 Author: VectorVault.io

{vector_vault-7.3.1 → vector_vault-7.3.2}/vectorvault/ai.py

@@ -216,12 +216,10 @@ class OpenAIPlatform(LLMPlatform):
             'gpt-5', 'gpt-5-mini', 'gpt-5-nano', 'gpt-5-chat-latest'
         ]
         self.no_stream_list = [
-            'o1-2024-12-17', 'o1-preview-2024-09-12', 'o1-mini-2024-09-12'
+            'o1', 'o1-mini',  
         ]
         self.no_temperature_list = [
-            'o1', 'o1-mini', 'o1-2024-12-17',
-            'o1-preview-2024-09-12', 'o1-mini-2024-09-12',
-            'o3', 'o3-mini', 'o3-mini-2025-01-31'
+            'o1', 'o1-mini', 'o3', 'o3-mini', 
         ]
         self.default_model = self.model_token_limits['default']
 
@@ -235,7 +233,7 @@ class OpenAIPlatform(LLMPlatform):
                     "messages": messages
                 }
                 # Include temperature only if the model actually supports it
-                if temperature is not None and temperature != 0 and model not in self.different_inference_list:
+                if temperature is not None and temperature != 0 and model not in self.no_temperature_list:
                     params["temperature"] = temperature
                 response = openai.chat.completions.create(**params)
                 response_queue.put(response.choices[0].message.content)

{vector_vault-7.3.1 → vector_vault-7.3.2}/vectorvault/vault.py

@@ -174,35 +174,35 @@ class Vault:
     def openai(self):
         """Lazy initialization of OpenAI platform"""
         if self._openai is None:
-            self._initialize_platforms()
+            self._openai = OpenAIPlatform()
         return self._openai
 
     @property
     def grok(self):
         """Lazy initialization of Grok platform"""
         if self._grok is None:
-            self._initialize_platforms()
+            self._grok = GrokPlatform(self.grok_key)
         return self._grok
 
     @property
     def anthropic(self):
         """Lazy initialization of Anthropic platform"""
         if self._anthropic is None:
-            self._initialize_platforms()
+            self._anthropic = AnthropicPlatform(self.anthropic_key)
         return self._anthropic
 
     @property
     def gemini(self):
         """Lazy initialization of Gemini platform"""
         if self._gemini is None:
-            self._initialize_platforms()
+            self._gemini = GeminiPlatform(self.gemini_key)
         return self._gemini
 
     @property
     def cerebras(self):
         """Lazy initialization of Cerebras platform"""
         if self._cerebras is None:
-            self._initialize_platforms()
+            self._cerebras = CerebrasPlatform(self.cerebras_key)
         return self._cerebras
 
     def get_total_items(self, vault: str = None):
@@ -305,17 +305,17 @@ class Vault:
         if model == 'default':
             return LLMClient(self.openai, **client_kwargs)
 
-        # Check OpenAI first since it's most common and always available
+        # Prefer checking OpenAI first to avoid initializing other SDKs unnecessarily
         if model in self.openai.model_token_limits:
             return LLMClient(self.openai, **client_kwargs)
-        elif self.anthropic_key and model in self.anthropic.model_token_limits:
-            return LLMClient(self.anthropic, **client_kwargs)
-        elif self.cerebras_key and model in self.cerebras.model_token_limits:
-            return LLMClient(self.cerebras, **client_kwargs)
-        elif self.grok_key and model in self.grok.model_token_limits:
+        elif model in self.grok.model_token_limits:
             return LLMClient(self.grok, **client_kwargs)
-        elif self.gemini_key and model in self.gemini.model_token_limits:
+        elif model in self.cerebras.model_token_limits:
+            return LLMClient(self.cerebras, **client_kwargs)
+        elif model in self.gemini.model_token_limits:
             return LLMClient(self.gemini, **client_kwargs)
+        elif model in self.anthropic.model_token_limits:
+            return LLMClient(self.anthropic, **client_kwargs)
         else:
             print(f"Model '{model}' not found in any platform -> adding as a fine-tuned OpenAI model...")
             self.add_fine_tuned_model_to_platform(model)
@@ -1540,7 +1540,7 @@ class Vault:
         self.update_conversation_history(self.cuid, f'User: {text} \n\nAI: {response}') if self.cuid else None
         print("get chat time --- %s seconds ---" % (time.time() - start_time)) if self.verbose else 0
             
-        return {'response': response, 'context': context} if return_context else response
+        return {'response': response, 'context': context, 'search_input': search_input} if return_context else response
         
 
     def get_chat_stream(self,