add compute node for llama

src/aios_kernel/__init__.py

@@ -8,4 +8,5 @@ from .open_ai_node import OpenAI_ComputeNode
 from .role import AIRole,AIRoleGroup
 from .workflow import Workflow
 from .bus import AIBus
-from .workflow_env import WorkflowEnvironment,CalenderEnvironment,CalenderEvent
+from .workflow_env import WorkflowEnvironment,CalenderEnvironment,CalenderEvent
+from .local_llama_compute_node import LocalLlama_ComputeNode

src/aios_kernel/environment.py

@@ -115,7 +115,7 @@ class Environment:
     def get_value(self,key:str) -> Optional[str]:
         handler = self.get_handlers.get(key)
         if handler is not None:
-            return handler(key)
+            return handler()
     
         s = self.values.get(key)
         if isinstance(s,str):

src/aios_kernel/local_llama_compute_node.py

@@ -1,7 +1,7 @@
 
 import logging
 import requests
-from typing import Optional
+from typing import Optional, List
 from pydantic import BaseModel
 
 from .compute_task import ComputeTask, ComputeTaskState, ComputeTaskType
@@ -26,14 +26,18 @@ class LocalLlama_ComputeNode(Queue_ComputeNode):
         class GenerateResponse(BaseModel):
             error: Optional[int]
             msg: Optional[str]
-            results: Optional[str]
+            results: Optional[List[str]]
 
-        try:    
+        try:
+            prompt_msgs = []
+            for prompt in task.params["prompts"]:
+                prompt_msgs.append(prompt["content"])
+                
             body = {
-                "prompts": task.params["prompts"]
+                "prompts": prompt_msgs
             }
             
-            response = requests.post("http://aigc:7880/generate", data = body, verify=False)
+            response = requests.post("http://aigc:7880/generate", json = body, verify=False, headers={"Content-Type": "application/json"})
             response.close()
 
             logger.info(f"LocalLlama_ComputeNode task responsed, request: {body}, status-code: {response.status_code}, headers: {response.headers}, content: {response.content}")
@@ -47,19 +51,20 @@ class LocalLlama_ComputeNode(Queue_ComputeNode):
                     }
                 }
             else:
-                resp = GenerateResponse.parse_raw(response.content.decode("utf-8"))
-                if resp.error:
+                resp = response.json()
+                if "error" in resp:
                     return {
                         "state": ComputeTaskState.ERROR,
                         "error": {
-                            "code": resp.error,
-                            "message": "local llama failed:" + resp.msg
+                            "code": resp["error"],
+                            "message": "local llama failed:" + resp["msg"]
                         }
                     }
                 else:
                     return {
-                        "content": str(resp.results),
-                        "message": {}
+                        "state": ComputeTaskState.DONE,
+                        "content": str(resp["results"]),
+                        "message": str(resp["results"])
                     }
         except Exception as err:
             import traceback

src/aios_kernel/open_ai_node.py

@@ -54,11 +54,14 @@ class OpenAI_ComputeNode(ComputeNode):
         prompts = task.params["prompts"]
 
         logger.info(f"call openai {mode_name} prompts: {prompts}")
-        resp = openai.ChatCompletion.create(model=mode_name,
-                                            messages=prompts,
-                                            functions=task.params["inner_functions"],
-                                            max_tokens=task.params["max_token_size"],
-                                            temperature=0.7) # TODO: add temperature to task params?
+        try:
+            resp = openai.ChatCompletion.create(model=mode_name,
+                                                messages=prompts,
+                                                functions=task.params["inner_functions"],
+                                                max_tokens=task.params["max_token_size"],
+                                                temperature=0.7) # TODO: add temperature to task params?
+        except Exception as e:
+            logger.error(f"openai.ChatCompletion.create failed! {e}")
         
         logger.info(f"openai response: {resp}")
         

src/aios_kernel/workflow_env.py

@@ -58,7 +58,7 @@ class CalenderEnvironment(Environment):
     def stop(self):
         self.is_run = False
 
-    async def get_now(self) -> str:
+    def get_now(self) -> str:
         now = datetime.now()
         formatted_time = now.strftime('%Y-%m-%d %H:%M:%S')
         return formatted_time