hjxdl 0.1.8__py3-none-any.whl → 0.1.10__py3-none-any.whl

hdl/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.8'
-__version_tuple__ = version_tuple = (0, 1, 8)
+__version__ = version = '0.1.10'
+__version_tuple__ = version_tuple = (0, 1, 10)

hdl/utils/llm/chat.py

@@ -8,7 +8,7 @@ from openai import OpenAI
 def chat_oai_stream(
     base_url="http://127.0.0.1:8000/v1",
     api_key="dummy_key",
-    model="/data/models/Qwen-7B-Chat-Int4",
+    model="default_model",
     prompt="Who are you?",
     *args,
     **kwargs
@@ -48,7 +48,7 @@ def chat_oai_stream(
 def chat_oai_invoke(
     base_url="http://127.0.0.1:8000/v1",
     api_key="dummy_key",
-    model="/data/models/Qwen-7B-Chat-Int4",
+    model="default_model",
     prompt="Who are you?",
     *args,
     **kwargs
@@ -318,26 +318,47 @@ class GGUF_M(Llama):
 class OpenAI_M():
     def __init__(
         self,
-        model_path: str = None,
+        model_path: str = "default_model",
         device: str='gpu',
         generation_kwargs: dict = {},
         server_ip: str = "172.28.1.2",
         server_port: int = 8000,
+        api_key: str = "dummy_key",
+        *args,
+        **kwargs
     ):
-        """Initialize the class with the specified parameters.
+        """Initialize the OpenAI client.
         
         Args:
-            model_path (str, optional): Path to the model file. Defaults to None.
-            device (str, optional): Device to run the model on. Defaults to 'gpu'.
-            generation_kwargs (dict, optional): Additional keyword arguments for model generation. Defaults to {}.
-            server_ip (str, optional): IP address of the server. Defaults to "172.28.1.2".
-            server_port (int, optional): Port number of the server. Defaults to 8000.
+            model_path (str): Path to the model file. Defaults to "default_model".
+            device (str): Device to use for model inference. Defaults to 'gpu'.
+            generation_kwargs (dict): Additional keyword arguments for model generation. Defaults to {}.
+            server_ip (str): IP address of the server. Defaults to "172.28.1.2".
+            server_port (int): Port number of the server. Defaults to 8000.
+            api_key (str): API key for authentication. Defaults to "dummy_key".
+            *args: Variable length argument list.
+            **kwargs: Arbitrary keyword arguments.
+        
+        Attributes:
+            model_path (str): Path to the model file.
+            server_ip (str): IP address of the server.
+            server_port (int): Port number of the server.
+            base_url (str): Base URL for API requests.
+            api_key (str): API key for authentication.
+            client (OpenAI): OpenAI client for making API requests.
         """
         self.model_path = model_path
         self.server_ip = server_ip
         self.server_port = server_port
         self.base_url = "http://{self.server_ip}:{str(self.server_port)}/v1"
-    
+        self.api_key = api_key
+        self.client = OpenAI(
+            base_url=self.base_url,
+            api_key=self.api_key,
+            *args,
+            **kwargs
+        )
+        
     def invoke(
         self, 
         prompt : str,
@@ -355,33 +376,45 @@ class OpenAI_M():
         Returns:
             str: The response generated by the chatbot.
         """
-        resp = chat_oai_invoke(
-            base_url=self.base_url,
+        response = self.client.chat.completions.create(
             model=self.model_path,
-            prompt=prompt
+            messages=[{
+                "role": "user",
+                "content": prompt
+            }],
+            stream=False,
+            **kwargs
         )
-        return resp
-    
+        return response.choices[0].message.content
+
     def stream(
         self, 
         prompt : str,
         stop: list[str] | None = ["USER:", "ASSISTANT:"],
         # history: list = [],
         **kwargs: t.Any,
-    ) -> str:
-        """Generate a response by streaming conversation with the OpenAI chat model.
+    ):
+        """Generate text completion in a streaming fashion.
         
         Args:
-            prompt (str): The prompt to start the conversation.
-            stop (list[str], optional): List of strings that indicate when the conversation should stop. Defaults to ["USER:", "ASSISTANT:"].
-            **kwargs: Additional keyword arguments to pass to the chat model.
+            prompt (str): The text prompt to generate completion for.
+            stop (list[str], optional): List of strings to stop streaming at. Defaults to ["USER:", "ASSISTANT:"].
+            **kwargs: Additional keyword arguments to pass to the completion API.
         
-        Returns:
-            str: The response generated by the chat model.
+        Yields:
+            str: The generated text completion in a streaming fashion.
         """
-        resp = chat_oai_stream(
-            base_url=self.base_url,
+        response = self.client.chat.completions.create(
             model=self.model_path,
-            prompt=prompt
+            messages=[{
+                "role": "user",
+                "content": prompt
+            }],
+            stream=True,
+            **kwargs
         )
-        return resp
+        
+        for chunk in response:
+            content = chunk.choices[0].delta.content
+            if content:
+                yield content 

{hjxdl-0.1.8.dist-info → hjxdl-0.1.10.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hjxdl
-Version: 0.1.8
+Version: 0.1.10
 Summary: A collection of functions for Jupyter notebooks
 Home-page: https://github.com/huluxiaohuowa/hdl
 Author: Jianxing Hu

{hjxdl-0.1.8.dist-info → hjxdl-0.1.10.dist-info}/RECORD

@@ -1,5 +1,5 @@
 hdl/__init__.py,sha256=5sZZNySv08wwfzJcSDssGTqUn9wlmDsR6R4XB8J8mFM,70
-hdl/_version.py,sha256=PdJ7dZoz_SyEgX0MdrMfQYBFlGcwpemv6ibF8NKALBY,411
+hdl/_version.py,sha256=0iLmzkTe5cfY4SBtaPpUzHn9tXwbwplszcfp5pHW6nU,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
@@ -84,12 +84,12 @@ hdl/utils/database_tools/connect.py,sha256=KUnVG-8raifEJ_N0b3c8LkTTIfn9NIyw8LX6q
 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=gsbqWh8fTcJUENU6ZuMClZAuSOLFnD5VP8kXOxGh3Zw,13776
+hdl/utils/llm/chat.py,sha256=2r3lIAf14l3obfK2ee2z6gbdp1LU-qJiV9o7rlGG0fg,14853
 hdl/utils/llm/embs.py,sha256=Tf0FOYrOFZp7qQpEPiSCXzlgyHH0X9HVTUtsup74a9E,7174
 hdl/utils/llm/extract.py,sha256=2sK_WJzmYIc8iuWaM9DA6Nw3_6q1O4lJ5pKpcZo-bBA,6512
 hdl/utils/schedulers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hdl/utils/schedulers/norm_lr.py,sha256=bDwCmdEK-WkgxQMFBiMuchv8Mm7C0-GZJ6usm-PQk14,4461
-hjxdl-0.1.8.dist-info/METADATA,sha256=a9BaE0EGy5G9EM3Tbsi4LMmIrCMFJUuDjFnmmu_nBW4,542
-hjxdl-0.1.8.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-hjxdl-0.1.8.dist-info/top_level.txt,sha256=-kxwTM5JPhylp06z3zAVO3w6_h7wtBfBo2zgM6YZoTk,4
-hjxdl-0.1.8.dist-info/RECORD,,
+hjxdl-0.1.10.dist-info/METADATA,sha256=wyNIVGQpVGcszuRGBHAUeM8AuGUmelzADJ2yphmFUas,543
+hjxdl-0.1.10.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
+hjxdl-0.1.10.dist-info/top_level.txt,sha256=-kxwTM5JPhylp06z3zAVO3w6_h7wtBfBo2zgM6YZoTk,4
+hjxdl-0.1.10.dist-info/RECORD,,