kailash 0.6.3__py3-none-any.whl → 0.6.5__py3-none-any.whl

kailash/nodes/admin/user_management.py

@@ -208,7 +208,7 @@ class UserManagementNode(Node):
         ...     },
         ...     tenant_id="company"
         ... )
-        >>> result = node.run()
+        >>> result = node.execute()
         >>> user_id = result["user"]["user_id"]
 
         >>> # Update user profile
@@ -221,7 +221,7 @@ class UserManagementNode(Node):
         ...     },
         ...     tenant_id="company"
         ... )
-        >>> result = node.run()
+        >>> result = node.execute()
 
         >>> # Bulk create users
         >>> node = UserManagementNode(
@@ -232,7 +232,7 @@ class UserManagementNode(Node):
         ...     ],
         ...     tenant_id="company"
         ... )
-        >>> result = node.run()
+        >>> result = node.execute()
         >>> created_count = result["bulk_result"]["created_count"]
     """
 
@@ -511,7 +511,7 @@ class UserManagementNode(Node):
         """
 
         try:
-            self._db_node.run(
+            self._db_node.execute(
                 query=insert_query,
                 parameters=[
                     user.user_id,
@@ -561,7 +561,7 @@ class UserManagementNode(Node):
         WHERE user_id = $1 AND tenant_id = $2
         """
 
-        result = self._db_node.run(
+        result = self._db_node.execute(
             query=query, parameters=[user_id, tenant_id], result_format="dict"
         )
 
@@ -624,7 +624,7 @@ class UserManagementNode(Node):
         WHERE email = $1 AND tenant_id = $2
         """
 
-        result = self._db_node.run(
+        result = self._db_node.execute(
             query=query, parameters=[email, tenant_id], result_format="dict"
         )
 
@@ -661,7 +661,7 @@ class UserManagementNode(Node):
         WHERE username = $1 AND tenant_id = $2
         """
 
-        result = self._db_node.run(
+        result = self._db_node.execute(
             query=query, parameters=[username, tenant_id], result_format="dict"
         )
 
@@ -751,7 +751,7 @@ class UserManagementNode(Node):
         """
 
         try:
-            self._db_node.run(query=update_query, parameters=parameters)
+            self._db_node.execute(query=update_query, parameters=parameters)
 
             # Get updated user
             updated_user = self._get_user_by_id(user_id, tenant_id)
@@ -788,7 +788,7 @@ class UserManagementNode(Node):
             """
 
         try:
-            self._db_node.run(query=delete_query, parameters=[user_id, tenant_id])
+            self._db_node.execute(query=delete_query, parameters=[user_id, tenant_id])
 
             return {
                 "result": {
@@ -845,12 +845,12 @@ class UserManagementNode(Node):
 
         try:
             # Get users
-            result = self._db_node.run(
+            result = self._db_node.execute(
                 query=list_query, parameters=parameters, result_format="dict"
             )
 
             # Get total count
-            count_result = self._db_node.run(
+            count_result = self._db_node.execute(
                 query=count_query, parameters=parameters[:-2], result_format="dict"
             )
 
@@ -920,7 +920,7 @@ class UserManagementNode(Node):
         """
 
         try:
-            self._db_node.run(
+            self._db_node.execute(
                 query=update_query, parameters=[new_status.value, user_id, tenant_id]
             )
 
@@ -952,7 +952,7 @@ class UserManagementNode(Node):
         """
 
         try:
-            self._db_node.run(
+            self._db_node.execute(
                 query=update_query, parameters=[password_hash, user_id, tenant_id]
             )
 
@@ -1141,7 +1141,7 @@ class UserManagementNode(Node):
             WHERE role_id IN ({placeholders}) AND tenant_id = ${len(user.roles) + 1}
             """
 
-            result = self._db_node.run(
+            result = self._db_node.execute(
                 query=role_query,
                 parameters=user.roles + [tenant_id],
                 result_format="dict",
@@ -1207,7 +1207,7 @@ class UserManagementNode(Node):
         search_pattern = f"%{search_query}%"
 
         try:
-            result = self._db_node.run(
+            result = self._db_node.execute(
                 query=query,
                 parameters=[tenant_id, search_pattern, limit, offset],
                 result_format="dict",
@@ -1350,7 +1350,7 @@ class UserManagementNode(Node):
         )
         """
 
-        result = self._db_node.run(
+        result = self._db_node.execute(
             operation="execute",
             query=store_token_query,
             parameters={
@@ -1387,7 +1387,7 @@ class UserManagementNode(Node):
         AND expires_at > CURRENT_TIMESTAMP
         """
 
-        result = self._db_node.run(
+        result = self._db_node.execute(
             operation="query",
             query=verify_query,
             parameters={"token": token, "tenant_id": tenant_id},
@@ -1408,7 +1408,7 @@ class UserManagementNode(Node):
         AND tenant_id = :tenant_id
         """
 
-        update_result = self._db_node.run(
+        update_result = self._db_node.execute(
             operation="execute",
             query=update_query,
             parameters={
@@ -1424,7 +1424,7 @@ class UserManagementNode(Node):
         WHERE session_id = :token
         """
 
-        self._db_node.run(
+        self._db_node.execute(
             operation="execute", query=delete_token_query, parameters={"token": token}
         )
 
@@ -1461,7 +1461,7 @@ class UserManagementNode(Node):
         else:
             raise NodeValidationError("Either username or email must be provided")
 
-        result = self._db_node.run(
+        result = self._db_node.execute(
             operation="query", query=auth_query, parameters=params
         )
 
@@ -1487,7 +1487,7 @@ class UserManagementNode(Node):
         WHERE user_id = :user_id
         """
 
-        self._db_node.run(
+        self._db_node.execute(
             operation="execute",
             query=update_login_query,
             parameters={"user_id": user_data["user_id"]},

kailash/nodes/ai/a2a.py

@@ -74,7 +74,7 @@ class SharedMemoryPoolNode(Node):
         >>> memory_pool = SharedMemoryPoolNode()
         >>>
         >>> # Write memory from an agent
-        >>> result = memory_pool.run(
+        >>> result = memory_pool.execute(
         ...     action="write",
         ...     agent_id="researcher_001",
         ...     content="Found correlation between X and Y",
@@ -86,7 +86,7 @@ class SharedMemoryPoolNode(Node):
         >>> assert result["memory_id"] is not None
         >>>
         >>> # Read with attention filter
-        >>> memories = memory_pool.run(
+        >>> memories = memory_pool.execute(
         ...     action="read",
         ...     agent_id="analyst_001",
         ...     attention_filter={
@@ -98,14 +98,14 @@ class SharedMemoryPoolNode(Node):
         >>> assert len(memories["memories"]) > 0
         >>>
         >>> # Subscribe to specific segments
-        >>> memory_pool.run(
+        >>> memory_pool.execute(
         ...     action="subscribe",
         ...     agent_id="monitor_001",
         ...     segments=["findings", "alerts"]
         ... )
         >>>
         >>> # Semantic query across all memories
-        >>> results = memory_pool.run(
+        >>> results = memory_pool.execute(
         ...     action="query",
         ...     query="correlation analysis",
         ...     top_k=3
@@ -530,7 +530,7 @@ class A2AAgentNode(LLMAgentNode):
         >>> agent = A2AAgentNode()
         >>>
         >>> # Execute with A2A features
-        >>> result = agent.run(
+        >>> result = agent.execute(
         ...     agent_id="researcher_001",
         ...     agent_role="research_specialist",
         ...     provider="openai",
@@ -659,7 +659,7 @@ class A2AAgentNode(LLMAgentNode):
         # Read from shared memory if available
         shared_context = []
         if memory_pool:
-            memory_result = memory_pool.run(
+            memory_result = memory_pool.execute(
                 action="read", agent_id=agent_id, attention_filter=attention_filter
             )
             if memory_result.get("success"):
@@ -723,7 +723,7 @@ Relevant shared context from other agents:
                 )
 
                 # Write to memory pool with enhanced context
-                memory_pool.run(
+                memory_pool.execute(
                     action="write",
                     agent_id=agent_id,
                     content=insight["content"],
@@ -1197,7 +1197,7 @@ class A2ACoordinatorNode(CycleAwareNode):
         >>> coordinator = A2ACoordinatorNode()
         >>>
         >>> # Register agents
-        >>> coordinator.run(
+        >>> coordinator.execute(
         ...     action="register",
         ...     agent_info={
         ...         "id": "analyst_001",
@@ -1207,7 +1207,7 @@ class A2ACoordinatorNode(CycleAwareNode):
         ... )
         >>>
         >>> # Delegate task with best match strategy
-        >>> result = coordinator.run(
+        >>> result = coordinator.execute(
         ...     action="delegate",
         ...     task={
         ...         "type": "analysis",
@@ -1225,7 +1225,7 @@ class A2ACoordinatorNode(CycleAwareNode):
         >>> assert result["assigned_agent"] == "analyst_001"
         >>>
         >>> # Build consensus among agents
-        >>> consensus_result = coordinator.run(
+        >>> consensus_result = coordinator.execute(
         ...     action="consensus",
         ...     proposal="Implement new feature X",
         ...     voting_agents=["agent1", "agent2", "agent3"],
@@ -1324,7 +1324,7 @@ class A2ACoordinatorNode(CycleAwareNode):
 
         Examples:
             >>> coordinator = A2ACoordinatorNode()
-            >>> result = coordinator.run(context,
+            >>> result = coordinator.execute(context,
             ...     action=\"delegate\",
             ...     task={\"type\": \"analysis\", \"required_skills\": [\"data\"]},
             ...     coordination_strategy=\"best_match\"

kailash/nodes/ai/ai_providers.py

@@ -1624,18 +1624,16 @@ def get_provider(
 
         >>> # Get chat-only provider
         >>> chat_provider = get_provider("anthropic", "chat")
-        response = chat_provider.chat(messages, model="claude-3-sonnet")
+        >>> response = chat_provider.chat(messages, model="claude-3-sonnet")
 
-        Get embedding-only provider:
+        >>> # Get embedding-only provider
+        >>> embed_provider = get_provider("cohere", "embeddings")
+        >>> embeddings = embed_provider.embed(texts, model="embed-english-v3.0")
 
-        embed_provider = get_provider("cohere", "embeddings")
-        embeddings = embed_provider.embed(texts, model="embed-english-v3.0")
-
-        Check provider capabilities:
-
-        provider = get_provider("ollama")
-        capabilities = provider.get_capabilities()
-        print(f"Chat: {capabilities['chat']}, Embeddings: {capabilities['embeddings']}")
+        >>> # Check provider capabilities
+        >>> provider = get_provider("ollama")
+        >>> capabilities = provider.get_capabilities()
+        >>> print(f"Chat: {capabilities['chat']}, Embeddings: {capabilities['embeddings']}")
     """
     provider_class = PROVIDERS.get(provider_name.lower())
     if not provider_class:
@@ -1685,8 +1683,7 @@ def get_available_providers(
         >>> chat_providers = get_available_providers("chat")
 
         >>> # Get only embedding providers
-
-        embed_providers = get_available_providers("embeddings")
+        >>> embed_providers = get_available_providers("embeddings")
     """
     results = {}
 

kailash/nodes/ai/embedding_generator.py

@@ -63,7 +63,7 @@ class EmbeddingGeneratorNode(Node):
     Examples:
         >>> # Single text embedding
         >>> embedder = EmbeddingGeneratorNode()
-        >>> result = embedder.run(
+        >>> result = embedder.execute(
         ...     provider="openai",
         ...     model="text-embedding-3-large",
         ...     input_text="This is a sample document to embed",
@@ -72,7 +72,7 @@ class EmbeddingGeneratorNode(Node):
 
         >>> # Batch document embedding
         >>> batch_embedder = EmbeddingGeneratorNode()
-        >>> result = batch_embedder.run(
+        >>> result = batch_embedder.execute(
         ...     provider="huggingface",
         ...     model="sentence-transformers/all-MiniLM-L6-v2",
         ...     input_texts=[
@@ -87,24 +87,23 @@ class EmbeddingGeneratorNode(Node):
 
         >>> # Similarity calculation
         >>> similarity = EmbeddingGeneratorNode()
-        >>> result = similarity.run(
+        >>> result = similarity.execute(
         ...     operation="calculate_similarity",
         ...     embedding_1=[0.1, 0.2, 0.3],  # ... removed for doctest
         ...     embedding_2=[0.15, 0.25, 0.35],  # ... removed for doctest
         ...     similarity_metric="cosine"
         ... )
 
-        Cached embedding with MCP integration::
-
-            mcp_embedder = EmbeddingGeneratorNode()
-            result = mcp_embedder.run(
-                provider="azure",
-                model="text-embedding-3-small",
-                mcp_resource_uri="data://documents/knowledge_base.json",
-                operation="embed_mcp_resource",
-                cache_ttl=3600,
-                chunk_size=512
-            )
+        >>> # Cached embedding with MCP integration
+        >>> mcp_embedder = EmbeddingGeneratorNode()
+        >>> result = mcp_embedder.execute(
+        ...     provider="azure",
+        ...     model="text-embedding-3-small",
+        ...     mcp_resource_uri="data://documents/knowledge_base.json",
+        ...     operation="embed_mcp_resource",
+        ...     cache_ttl=3600,
+        ...     chunk_size=512
+        ... )
     """
 
     def get_parameters(self) -> dict[str, NodeParameter]:

kailash/nodes/ai/intelligent_agent_orchestrator.py

@@ -95,7 +95,7 @@ class IntelligentCacheNode(Node):
         >>> cache = IntelligentCacheNode()
         >>>
         >>> # Cache an expensive MCP tool call result
-        >>> result = cache.run(
+        >>> result = cache.execute(
         ...     action="cache",
         ...     cache_key="weather_api_nyc_20240106",
         ...     data={"temperature": 72, "humidity": 65, "conditions": "sunny"},
@@ -110,7 +110,7 @@ class IntelligentCacheNode(Node):
         >>> assert result["success"] == True
         >>>
         >>> # Direct cache hit by key
-        >>> cached = cache.run(
+        >>> cached = cache.execute(
         ...     action="get",
         ...     cache_key="weather_api_nyc_20240106"
         ... )
@@ -118,7 +118,7 @@ class IntelligentCacheNode(Node):
         >>> assert cached["data"]["temperature"] == 72
         >>>
         >>> # Semantic similarity hit (uses simple string matching in this mock implementation)
-        >>> similar = cache.run(
+        >>> similar = cache.execute(
         ...     action="get",
         ...     query="weather nyc",  # Simple match
         ...     similarity_threshold=0.3
@@ -127,7 +127,7 @@ class IntelligentCacheNode(Node):
         >>> has_hit = similar.get("hit", False)
         >>>
         >>> # Cache statistics
-        >>> stats = cache.run(action="stats")
+        >>> stats = cache.execute(action="stats")
         >>> assert "stats" in stats
         >>> assert "hit_rate" in stats["stats"]
     """
@@ -704,7 +704,7 @@ class MCPAgentNode(SelfOrganizingAgentNode):
 
         try:
             client = server_info["client"]
-            result = client.run(
+            result = client.execute(
                 server_config=server_info["config"],
                 operation="call_tool",
                 tool_name=tool_name,
@@ -789,7 +789,7 @@ class QueryAnalysisNode(Node):
         >>> analyzer = QueryAnalysisNode()
         >>>
         >>> # Analyze a complex multi-domain query
-        >>> result = analyzer.run(
+        >>> result = analyzer.execute(
         ...     query="Analyze our Q4 sales data, identify underperforming regions, and create a recovery strategy with timeline",
         ...     context={
         ...         "domain": "business_strategy",
@@ -810,7 +810,7 @@ class QueryAnalysisNode(Node):
         >>> assert result["analysis"]["team_suggestion"]["suggested_size"] >= 3
         >>>
         >>> # Simple query analysis
-        >>> simple = analyzer.run(
+        >>> simple = analyzer.execute(
         ...     query="What is the current temperature?",
         ...     context={"domain": "weather"}
         ... )
@@ -1402,7 +1402,7 @@ class OrchestrationManagerNode(Node):
     def _analyze_query(self, query: str, context: dict, mcp_servers: list) -> dict:
         """Analyze the incoming query."""
         analyzer = QueryAnalysisNode()
-        return analyzer.run(query=query, context=context, mcp_servers=mcp_servers)
+        return analyzer.execute(query=query, context=context, mcp_servers=mcp_servers)
 
     def _setup_infrastructure(
         self, pool_size: int, mcp_servers: list, enable_caching: bool
@@ -1503,7 +1503,7 @@ class OrchestrationManagerNode(Node):
             spec = agent_specializations[i % len(agent_specializations)]
 
             # Register agent with pool manager
-            registration = pool_manager.run(
+            registration = pool_manager.execute(
                 action="register",
                 agent_id=f"agent_{spec['role']}_{i:03d}",
                 capabilities=spec["capabilities"],
@@ -1543,7 +1543,7 @@ class OrchestrationManagerNode(Node):
 
         team_formation = TeamFormationNode()
 
-        return team_formation.run(
+        return team_formation.execute(
             problem_analysis=analysis,
             available_agents=agent_pool,
             formation_strategy=strategy,
@@ -1577,7 +1577,7 @@ class OrchestrationManagerNode(Node):
                 information_results.append(agent_result)
 
                 # Store in memory
-                solution_memory.run(
+                solution_memory.execute(
                     action="write",
                     agent_id=agent["id"],
                     content=agent_result,
@@ -1593,7 +1593,7 @@ class OrchestrationManagerNode(Node):
                 for cap in ["analysis", "machine_learning", "processing"]
             ):
                 # Get previous information
-                memory_result = solution_memory.run(
+                memory_result = solution_memory.execute(
                     action="read",
                     agent_id=agent["id"],
                     attention_filter={"tags": ["information"], "threshold": 0.3},
@@ -1605,7 +1605,7 @@ class OrchestrationManagerNode(Node):
                 )
                 analysis_results.append(agent_result)
 
-                solution_memory.run(
+                solution_memory.execute(
                     action="write",
                     agent_id=agent["id"],
                     content=agent_result,
@@ -1621,7 +1621,7 @@ class OrchestrationManagerNode(Node):
                 for cap in ["synthesis", "writing", "coordination"]
             ):
                 # Get all previous work
-                memory_result = solution_memory.run(
+                memory_result = solution_memory.execute(
                     action="read",
                     agent_id=agent["id"],
                     attention_filter={"threshold": 0.2},
@@ -1661,7 +1661,7 @@ class OrchestrationManagerNode(Node):
         cache_key = f"{agent_id}_{hashlib.md5(task.encode()).hexdigest()[:8]}"
 
         if cache:
-            cached_result = cache.run(
+            cached_result = cache.execute(
                 action="get", cache_key=cache_key, query=task, similarity_threshold=0.7
             )
 
@@ -1693,7 +1693,7 @@ class OrchestrationManagerNode(Node):
 
         # Cache the result
         if cache:
-            cache.run(
+            cache.execute(
                 action="cache",
                 cache_key=cache_key,
                 data=result,
@@ -1729,7 +1729,7 @@ class OrchestrationManagerNode(Node):
         """Evaluate solution quality."""
         evaluator = SolutionEvaluatorNode()
 
-        return evaluator.run(
+        return evaluator.execute(
             solution=solution["final_solution"],
             problem_requirements={
                 "quality_threshold": quality_threshold,
@@ -1848,7 +1848,7 @@ class ConvergenceDetectorNode(Node):
         >>> detector = ConvergenceDetectorNode()
         >>>
         >>> # Typical convergence detection scenario
-        >>> result = detector.run(
+        >>> result = detector.execute(
         ...     solution_history=[
         ...         {
         ...             "iteration": 1,
@@ -1888,7 +1888,7 @@ class ConvergenceDetectorNode(Node):
         ...     {"evaluation": {"overall_score": 0.71}, "duration": 95},
         ...     {"evaluation": {"overall_score": 0.715}, "duration": 90}
         ... ]
-        >>> result2 = detector.run(
+        >>> result2 = detector.execute(
         ...     solution_history=stagnant_history,
         ...     quality_threshold=0.9,
         ...     improvement_threshold=0.05,

kailash/nodes/ai/iterative_llm_agent.py

@@ -92,14 +92,14 @@ class IterativeLLMAgentNode(LLMAgentNode):
     Examples:
         >>> # Basic iterative agent
         >>> agent = IterativeLLMAgentNode()
-        >>> result = agent.run(
+        >>> result = agent.execute(
         ...     messages=[{"role": "user", "content": "Find and analyze healthcare AI trends"}],
         ...     mcp_servers=["http://localhost:8080"],
         ...     max_iterations=3
         ... )
 
         >>> # Advanced iterative agent with custom convergence
-        >>> result = agent.run(
+        >>> result = agent.execute(
         ...     messages=[{"role": "user", "content": "Research and recommend AI implementation strategy"}],
         ...     mcp_servers=["http://ai-registry:8080", "http://knowledge-base:8081"],
         ...     max_iterations=5,