hjxdl 0.1.39__py3-none-any.whl → 0.1.41__py3-none-any.whl

hdl/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.39'
-__version_tuple__ = version_tuple = (0, 1, 39)
+__version__ = version = '0.1.41'
+__version_tuple__ = version_tuple = (0, 1, 41)

hdl/utils/llm/chat.py

@@ -198,47 +198,47 @@ class OpenAI_M():
             if content:
                 yield content
 
-    def get_decision(
+    def agent_response(
         self,
-        prompt: str,
+        prompt : str,
+        stream = True,
         **kwargs: t.Any
     ):
-        """Get decision based on the provided prompt and additional keyword arguments.
+        """'''Generate agent response based on the given prompt.
 
         Args:
-            prompt (str): The prompt for decision making.
+            prompt (str): The prompt for which agent response is generated.
+            stream (bool, optional): Flag to determine if the response should be streamed. Defaults to True.
             **kwargs: Additional keyword arguments.
 
         Returns:
-            dict: A dictionary containing the decision.
-
-        Example:
-            decision = get_decision("Should I buy this product?", option1="yes", option2="no")
+            str: The agent response based on the prompt.
+        '''
         """
+        decision_dict = self.get_decision(prompt, **kwargs)
+        if decision_dict.get("function_name", None) is None:
+            return self.stream(prompt, **kwargs)
+        else:
+            tool_result = str(self.get_tool_result(prompt, **kwargs))
+            prompt_final = "根据上下文回答最后的用户问题：\n上下文信息：\n"
+            prompt_final += tool_result
+            prompt_final += f"\n用户的问题：\n{prompt}"
+            if stream:
+                return self.stream(prompt_final, **kwargs)
+            else:
+                return self.invoke(prompt_final, **kwargs)
+
+    def get_decision(self, prompt: str, **kwargs: t.Any):
+        # 该方法与之前一致...
         prompt_final = FN_TEMPLATE
         for tool in self.tools:
             prompt_final += self.tool_desc.get(tool.__name__, "")
         prompt_final += f"\n用户的问题：\n{prompt}"
-        # print(prompt_final)
-        decision_dict_str = self.invoke(prompt_final ,**kwargs)
-        print(decision_dict_str)
+        decision_dict_str = self.invoke(prompt_final, **kwargs)
         return decision_dict_str
-        # return json.loads(decision_dict)
-
-    def get_tool_result(
-        self,
-        prompt: str,
-        **kwargs: t.Any
-    ):
-        """Get the result from a tool based on the provided prompt and keyword arguments.
 
-            Args:
-                prompt (str): The prompt to get the decision for.
-                **kwargs: Additional keyword arguments to pass to the decision function.
-
-            Returns:
-                str: The result from the selected tool based on the decision made.
-        """
+    def get_tool_result(self, prompt: str, **kwargs: t.Any):
+        # 同步方法与之前一致...
         decision_dict_str = self.get_decision(prompt, **kwargs)
         try:
             decision_dict = json.loads(decision_dict_str)
@@ -259,11 +259,7 @@ class OpenAI_M():
                 print(e)
                 return ""
 
-    async def get_tool_result_async(
-        self,
-        prompt: str,
-        **kwargs: t.Any
-    ):
+    async def get_tool_result_async(self, prompt: str, **kwargs: t.Any):
         """
         Asynchronous version of the get_tool_result function that can run in parallel using multiprocessing.
 
@@ -274,6 +270,10 @@ class OpenAI_M():
         Returns:
             str: The result from the selected tool based on the decision made.
         """
+
+        def run_tool_with_kwargs(tool, func_kwargs):
+            return tool(**func_kwargs)
+
         decision_dict_str = await asyncio.to_thread(self.get_decision, prompt, **kwargs)
         try:
             decision_dict = json.loads(decision_dict_str)
@@ -292,38 +292,8 @@ class OpenAI_M():
 
                 loop = asyncio.get_running_loop()
                 with ProcessPoolExecutor() as pool:
-                    result = await loop.run_in_executor(pool, tool_final, **func_kwargs)
+                    result = await loop.run_in_executor(pool, run_tool_with_kwargs, tool_final, func_kwargs)
                 return result
             except Exception as e:
                 print(e)
-                return ""
-
-    def agent_response(
-        self,
-        prompt : str,
-        stream = True,
-        **kwargs: t.Any
-    ):
-        """'''Generate agent response based on the given prompt.
-
-        Args:
-            prompt (str): The prompt for which agent response is generated.
-            stream (bool, optional): Flag to determine if the response should be streamed. Defaults to True.
-            **kwargs: Additional keyword arguments.
-
-        Returns:
-            str: The agent response based on the prompt.
-        '''
-        """
-        decision_dict = self.get_decision(prompt, **kwargs)
-        if decision_dict.get("function_name", None) is None:
-            return self.stream(prompt, **kwargs)
-        else:
-            tool_result = str(self.get_tool_result(prompt, **kwargs))
-            prompt_final = "根据上下文回答最后的用户问题：\n上下文信息：\n"
-            prompt_final += tool_result
-            prompt_final += f"\n用户的问题：\n{prompt}"
-            if stream:
-                return self.stream(prompt_final, **kwargs)
-            else:
-                return self.invoke(prompt_final, **kwargs)
+                return ""

{hjxdl-0.1.39.dist-info → hjxdl-0.1.41.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hjxdl
-Version: 0.1.39
+Version: 0.1.41
 Summary: A collection of functions for Jupyter notebooks
 Home-page: https://github.com/huluxiaohuowa/hdl
 Author: Jianxing Hu

{hjxdl-0.1.39.dist-info → hjxdl-0.1.41.dist-info}/RECORD

@@ -1,5 +1,5 @@
 hdl/__init__.py,sha256=GffnD0jLJdhkd-vo989v40N90sQbofkayRBwxc6TVhQ,72
-hdl/_version.py,sha256=6nXIPX9zBoWwZZ8FWkd2Pe2QAfUPdNNa0BUqqXMd0RE,413
+hdl/_version.py,sha256=65hEflmRlvVz3zHSlCs2w2jXSKc7YICoUmNE8oYJni4,413
 hdl/args/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdl/args/loss_args.py,sha256=s7YzSdd7IjD24rZvvOrxLLFqMZQb9YylxKeyelSdrTk,70
 hdl/controllers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -127,7 +127,7 @@ hdl/utils/desc/template.py,sha256=a3NcSihzZMm9Bk76iDVe54_xBDceGmLebS0XMONE3nk,11
 hdl/utils/general/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdl/utils/general/glob.py,sha256=8-RCnt6L297wMIfn34ZAMCsGCZUjHG3MGglGZI1cX0g,491
 hdl/utils/llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-hdl/utils/llm/chat.py,sha256=rQKsIqw2pj2CkhfOaJ2Oahgt3XgmkgrHBgkxs6dfE0U,10770
+hdl/utils/llm/chat.py,sha256=-k5fnxzOciSHh7nKF7EnEOF1D-wrIu1mupgg5REPxmY,9974
 hdl/utils/llm/embs.py,sha256=Tf0FOYrOFZp7qQpEPiSCXzlgyHH0X9HVTUtsup74a9E,7174
 hdl/utils/llm/extract.py,sha256=2sK_WJzmYIc8iuWaM9DA6Nw3_6q1O4lJ5pKpcZo-bBA,6512
 hdl/utils/llm/llama_chat.py,sha256=watcHGOaz-bv3x-yDucYlGk5f8FiqfFhwWogrl334fk,4387
@@ -135,7 +135,7 @@ hdl/utils/schedulers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hS
 hdl/utils/schedulers/norm_lr.py,sha256=bDwCmdEK-WkgxQMFBiMuchv8Mm7C0-GZJ6usm-PQk14,4461
 hdl/utils/weather/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdl/utils/weather/weather.py,sha256=k11o6wM15kF8b9NMlEfrg68ak-SfSYLN3nOOflFUv-I,4381
-hjxdl-0.1.39.dist-info/METADATA,sha256=DUifflUXAgFT-Jaxbmb2ZvDnjb-0nhkFKYSuyZAeN6Q,737
-hjxdl-0.1.39.dist-info/WHEEL,sha256=UvcQYKBHoFqaQd6LKyqHw9fxEolWLQnlzP0h_LgJAfI,91
-hjxdl-0.1.39.dist-info/top_level.txt,sha256=-kxwTM5JPhylp06z3zAVO3w6_h7wtBfBo2zgM6YZoTk,4
-hjxdl-0.1.39.dist-info/RECORD,,
+hjxdl-0.1.41.dist-info/METADATA,sha256=BSH-xT-DtotFaVKeyIoPIjU0Y23K4vgb-FJoQQg4pv0,737
+hjxdl-0.1.41.dist-info/WHEEL,sha256=UvcQYKBHoFqaQd6LKyqHw9fxEolWLQnlzP0h_LgJAfI,91
+hjxdl-0.1.41.dist-info/top_level.txt,sha256=-kxwTM5JPhylp06z3zAVO3w6_h7wtBfBo2zgM6YZoTk,4
+hjxdl-0.1.41.dist-info/RECORD,,