Update agents/agents_nodes.py

agents/agents_nodes.py

@@ -12,32 +12,31 @@ from tools.financial_tools import time_value_tool
 
 # LLM instantation
 
-# text_generator = pipeline(
-#     "text-generation",  # Task type
-#     # model="deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
-#     # model="google/gemma-3n-E2B-it",
-#     # model="google/gemma-3n-e4b-it",
-#     model="Qwen/Qwen3-Embedding-0.6B",
-#     # device="cuda" if torch.cuda.is_available() else "cpu",
-#     device= "cpu",
-#     torch_dtype=torch.bfloat16,
-#     max_new_tokens=700  # Limit output length
-# )
-
-llm_endpoint = HuggingFaceEndpoint(
-    endpoint_url="<your_endpoint_url>",
-    task="text-generation",
-    max_new_tokens=1024,
-    do_sample=False
+text_generator = pipeline(
+    "text-generation",  # Task type
+    # model="deepseek-ai/DeepSeek-R1-0528-Qwen3-8B",
+    # model="google/gemma-3n-E2B-it",
+    # model="google/gemma-3n-e4b-it",
+    model="Qwen/Qwen3-Embedding-0.6B",
+    # device="cuda" if torch.cuda.is_available() else "cpu",
+    device= "cpu",
+    torch_dtype=torch.bfloat16,
+    max_new_tokens=700  # Limit output length
 )
-# llm = HuggingFacePipeline(pipeline=text_generator)
-llm = ChatHuggingFace(llm=llm_endpoint)
 
-llm_instantiated = llm.bind_tools(    
-    [time_value_tool],
-    tool_choice={"type": "function", "function": {"name": "time_value_tool"}}
+llm = HuggingFacePipeline(pipeline=text_generator)
+
+llm_instantiated = llm.bind(
+    functions=[tool_schema],
+    function_call={"name": "time_value_tool"},
+    stop_sequences=["<|im_end|>"]
 )
 
+# llm_instantiated = llm.bind_tools(    
+#     [time_value_tool],
+#     tool_choice={"type": "function", "function": {"name": "time_value_tool"}}
+# )
+
 def agent_node(state: AgentState):
     response = llm_instantiated.invoke(state["messages"])
     if not (hasattr(response, 'tool_calls') and response.tool_calls):